Browse Topic: Fuzzy logic

Items (333)

Attitude Control of a Variant Flying Wing UAV Based on L1 Adaptive and Fuzzy Clustering

2026-99-1858

7/17/2026

This study presents a full-envelope attitude-stabilisation and trajectory-tracking strategy for morphing flying-wing UAVs operating in highly nonlinear and strongly coupled conditions. The approach integrates fuzzy C-means (FCM) envelope partitioning with L1 adaptive control. Small-disturbance linear models are first generated at multiple altitude–Mach trim points; the FCM algorithm then performs unsupervised clustering in the state space, yielding representative subintervals that capture local flight-dynamic characteristics. The optimal cluster number and fuzziness exponent are selected using the partition coefficient, partition index, partition entropy, and Xie–Beni indices. For each sub-interval, an LQR baseline controller is designed and augmented by an L1 adaptive compensator, where a low-pass filter decouples adaptation from robustness to guarantee specified transient-performance bounds under matched/unmatched uncertainties, actuator saturation, and external disturbances. A feed-forward pre-filter realises online decoupling of the multi-input multi-output channels, thereby enhancing adaptability to variable sweep angles and large aerodynamic variations. Simulations covering low-speed/small-sweep and high-speed/large-sweep scenarios demonstrate that the proposed method sustains robust stability across the clustered envelope, outperforming conventional control schemes and confirming its engineering applicability.

Tang, Longhao, Sun, Xiaoxu, Liu, Changlin

Disaster Evolution and Risk Evaluation of Urban Transport Infrastructure under Extreme Rainfall–Flood Scenarios: A Case Study

2026-99-0554

7/10/2026

To investigate the disaster evolution characteristics and associated risks of heavy rainfall and flooding on urban transportation infrastructure, this study takes the extreme rainstorm event in Zhengzhou as a typical case. A multidimensional dynamic risk assessment model is employed to analyze the disaster evolution process and conduct risk evaluation. First, the three-stage evolution process and its characteristics are systematically examined. Then, based on the theory of natural disaster risk elements, a dynamic risk assessment model is constructed. The improved Order of Priority Approach (OPA) is used to determine the weights of multidimensional risk factors, and interval type-1 fuzzy logic is introduced to address the uncertainty of fuzzy indicators. Finally, the overall risk level of the heavy rainfall–flooding disaster chain is calculated and evaluated. The results indicate a high-risk level, which is consistent with the findings of the field investigation report, thereby validating the feasibility of the proposed disaster chain evaluation method combining multiple models. This analysis provides a theoretical basis for future studies on similar urban storm flood risk scenarios.

Zhang, Yongcheng, Wang, Jianwei, Wu, Ziyi, Wang, Yan, Luo, Qing, Kang, Pingping

Human-Machine Ergonomics Analysis of Civil Aircraft Electric Pilot Seats

2026-99-0570

7/10/2026

This paper uses a structured evaluation framework to study the ergonomics of electric pilot seats in modern civil aircraft. We have established a multi-level indicator system to examine the adjustability, pressure distribution, dynamic response and, fatigue relief effect of the seat. All experimental data were obtained from a full-scale cockpit simulator environment, where a ground-based mock-up and motion-free simulated cockpit were used to replicate real operational posture, control-reach conditions, and long-duration mission loads. This framework combines experimental measurement and fuzzy evaluation techniques to quantify the quality of human-computer interaction. Test results show that compared with ordinary seats, the prototype seat has a wider adjustment range, a more uniform pressure distribution, and a smoother dynamic response. It is particularly worth mentioning that it can delay the emergence of fatigue during long-term operation, which proves the advantages of the electric adjustment mechanism. The simulated-cockpit test conditions ensure that these results are reproducible and representative of actual cockpit usage scenarios. This findings not only provide theoretical guidance and engineering basis for optimizing the cockpit seat system, but also provide methodological reference for applying fuzzy analysis in aerospace ergonomics research.

Tian, Yanan, Pi, Zhengyang

Potential of ORC-Based Waste Heat Recovery in Conventional and Hybrid Heavy-Duty Powertrains

2026-37-0018

6/9/2026

Heavy-duty vehicles significantly contribute to greenhouse gas emissions and urban air pollution, especially during cold-starts and transients when engine and aftertreatment efficiencies drop. Waste heat recovery (WHR) via Organic Rankine Cycle (ORC) systems offers a practical solution to improve fuel efficiency and cut CO₂ in real-world heavy-duty operations. This study examines ORC-based WHR integration into conventional and hybrid powertrains of an Isuzu FTR850 truck, analyzing four configurations: Shell-and-Tube or Plate heat exchangers with simple or regenerative ORC layouts. For hybrids, it compares two engine sizes and energy management strategies: an optimized fuzzy logic approach versus constant-power operation to enhance exhaust heat recovery. A validated quasi-static simulation framework is used to predict fuel consumption and exhaust properties over representative duty cycles. 2D performance maps using exhaust temperature and mass flow as inputs are used to model the WHR under off-design conditions. Results show that the recovery of waste heat WHR depends on the hybridization level and strategy. Conventional powertrains benefit most from Shell-and-Tube exchangers, recovering ~2 kWh of electrical energy per 8-hour cycle and reducing fuel consumption by 0.5%. Hybrid setups recover up to 3.9 kWh from exhaust gases with a simple layout coupled with a Shell-and-Tube heat exchanger under constant-power control. Electricity is used to support onboard auxiliaries and battery charging, further lowering fuel demand (-44%) and emissions. Finally, a multi-objective optimization was performed to exploit the synergy between hybridization and WHR while maintaining acceptable payload and battery operating conditions.

Donateo, Teresa, Morrone, Pietropaolo

Hybrid Physics-Informed Neural Network and PID Control for Fault-Tolerant Autonomous Multi-Copters

2026-26-0770

6/1/2026

This paper addresses the critical challenge of fault-tolerant control in autonomous multi-copters, particularly under conditions of one or two rotor failures a scenario that often leads to severe instability and a complete loss of directional control due to unbalanced torque and resultant autorotation. Existing advanced control strategies, including optimal approaches such as LQR, typically require precise system modeling and state estimation, which are difficult to achieve in real-world, dynamic failure scenarios. Alternative methods like fuzzy logic, sliding mode control, and gain-scheduling either lack robust generalization or are impractical for enumerating all possible failure cases. In this work, a hybrid control framework integrating Physics Informed Neural Networks (PINN) with a standard PID controller is proposed for fault-tolerant operation of autonomous multi-copters subject to multiple actuator failures. PINNs incorporate governing physical laws as regularization in their loss functions, allowing them to learn optimal counter-torque actions and thrust balancing necessary to arrest autorotation and stabilize flight, despite limited training data and uncertainty in failure conditions. The calculated moments and thrust commands are executed via a robust PID scheme, enabling reliable real-time implementation and minimizing residual oscillations. This hybrid control architecture demonstrates significant potential to enhance the resilience and operational safety of autonomous multi-copters during unexpected motor failures. By leveraging PINN’s physics-based generalization and PID’s consistent execution, the proposed method offers an adaptive, model-agnostic approach for maintaining stable flight and directional control under severe actuator faults, with implications for next-generation fault-tolerant UAV systems deployed in complex environments.

Charapalle, Samruddhi, Venugopalan, Nandagopalan, Nerkundram Muralidharan, Arun, Sundararaj, Laveen

A Proposed Methodology for Human Operator Modeling and Development of a Virtual Operator Model for Control of a Simulated Compact Track Loader

2026-01-0146

4/7/2026

A methodology for performing Human Operator Modeling (HOM) using a Caterpillar Model 299D3 XE Compact Track Loader (CTL) is presented. The proposed method uses task analysis techniques to decompose material excavation and moving tasks into smaller, individual tasks presented in a task list. A method for verifying and refining the task list is presented, along with a procedure for identifying relevant human operator sensory information and analyzing human decision making in the context of CTL operation. This methodology is then partially verified through the analysis of a non-expert human operator in Vortex Studio, a realistic construction equipment simulator. A modified test course is executed by a non-expert human operator in the simulation environment, and the recorded data is used to create a quantitative Human Operator Model. From this, a Virtual Operator Model (VOM) feedback controller simulating the performance of the human operator is developed. The VOM is implemented using a state machine to transition between individual tasks. Fuzzy Logic Control (FLC), is implemented for each task to control bucket tilt, arm lift, and throttle, with controller parameters calculated from the quantitative HOM data. The VOM controller is verified using the same test course performed by the human operator. The performance of the human operator is compared to that of the VOM controller in order to validate the HOM and VOM methodology for a simulation environment.

Wang, Orson R., Norris, William R., Patterson, Albert E., Soylemezoglu, Ahmet, Nottage, Dustin S.

A Shared Autonomy Architecture: Utilizing an Advanced Personalized Control System (APeCS) and Shared Autonomy Arbiter (SAB)

2026-01-0147

4/7/2026

The shared autonomy framework has become an option with great potential in the field of autonomous vehicles. Human and machine control decisions typically demonstrate strengths in different scenarios. As a result, the robustness of systems can be enhanced by the collaboration between humans and autonomy. A shared autonomy architecture that takes into account both human and environmental factors was proposed in this work. The authority distribution between the human operator and the autonomy algorithm was determined by the Shared Autonomy Arbiter (SAB). Designed with a two-tier structure, the SAB incorporated a policy-level decision module, as well as a numerical-level arbitration tuning module. A fuzzy inference system (FIS) was incorporated to enhance the noise tolerance of the policy selection module. Furthermore, the human factor was taken into account by applying a projection to the users’ control input. The human operator’s control decision was projected by the Adaptive Personalized Control System (APeCS) to accommodate the skill levels and habits of various users. By incorporating a broad set of factors, this framework is suitable for diverse applications that require robustness in complex environments. Two case studies were included in this work to demonstrate its effectiveness. The first presented a concept design illustrating the application of the proposed architecture on autonomous vehicles operating in varied environments. The second showed that the proposed architecture can serve as a robust testbed by taking advantage of the authority modulating mechanism. By connecting a system under assessment and an established autonomy algorithm to the SAB, the new system can be tested robustly and safely through the flexible authority distribution.

Sang, I-Chen, Norris, William, Patterson, Albert, Sreenivas, Ramavarapu S., Soylemezoglu PhD, Ahmet, Nottage, Dustin S.

Backward Fuzzy Driving Control for 6×4 Off-Road Vehicles

2026-01-0148

4/7/2026

Off-road autonomous vehicle systems must be able to operate across unstructured and variable terrain while avoiding obstacles. This presents significant challenges in vehicle and control system design, especially for less conventional platforms such as 6×4 vehicles. While forward driving autonomy has developed and matured in recent years, effective reverse navigation remains an under-explored area of vehicle co-design. Reversing 6×4 vehicles have limited rear steering authority, an extended wheelbase, and asymmetric traction, which introduce complex dynamics into any control system that is used. To address this need, a robust and experimentally validated fuzzy logic control architecture for 6×4 reverse navigation was developed during the course of this project. This architecture incorporates both near-field and long-range path data with adaptive outputs controlling steering and velocity based on a rule base that covers the whole vehicle state space. This method has low computational cost and is robust to terrain changes, wheel slip, and actuator lag. To accomplish this, the controller coevolves with the vehicle design parameters, making this an effective co-design strategy. The vehicle design constraints are embedded into the controller through constraint-aware membership functions and rule tuning, reducing the need for terrain-specific calibration. The architecture is modular and scalable across numerous similar platforms, supporting rapid reconfiguration and vehicle design exploration for future autonomous off-road vehicles such as those used in expeditionary environments.

Dekhterman, Samuel R., Sreenivas, Ramavarapu S., Norris, William R., Patterson, Albert E., Soylemezoglu, Ahmet, Nottage, Dustin

Human-Like Automatic Braking Algorithm Based on Kinematic Cue: Yield Behavior Analysis and Fuzzy Controller Design

10-10-03-0019

2/25/2026

Pedestrians are among the most vulnerable participants in traffic, particularly when crossing the road. Extensive research has been conducted globally on the yielding behavior analysis of vehicle–pedestrian interaction and the design of automatic vehicle braking systems to mitigate pedestrian casualties. However, few studies have comprehensively addressed lateral risks using implicit kinematic cues in pedestrian–vehicle interactions. Moreover, the design of collision avoidance systems has rarely taken into account driving behavior, along with the pedestrian’s kinematics and crossing behavior. This article presents a human-like automatic braking fuzzy control strategy for pedestrian–vehicle collision avoidance, combining the advantages of professional driver emergency braking behavior and kinematic interaction cues. First, a high-fidelity driving simulator is used to investigate the yielding behavior of pedestrian–vehicle interaction when pedestrians cross the road. Second, the intrusion position (XP), as a new lateral risk index, is designed to overcome the limitation of lateral distance in complex pedestrian–vehicle interaction scenarios. Various metrics are considered to analyze driver emergency braking behavior using statistical methods from both lateral and longitudinal aspects. Subsequently, based on driver braking behavior, the human-like automatic braking fuzzy control strategy is proposed. Finally, simulation examples verify the reliability of the analysis results and the proposed controller’s effectiveness. Compared with a conventional automatic braking system, the timing of interventions of the proposed system is on average 2.9 s earlier, and the braking deceleration is reduced by 3.59 m/s2.

Zhang, Wenyan, Huang, Xiaorong, Sun, Shulei, Fu, Kairong, Xiong, Qing, Huang, Haibo

Yaw Coordinated Control Based on Fuzzy Control and Stability Region Theory

10-10-03-0018

2/23/2026

Electric vehicle chassis integration control aims to improve vehicle handling and comfort. Previous studies encountered significant practical limitations, such as computational overhead in real-time execution scenarios. Designing effective and efficient algorithms for actuator coordination remains challenging. This article presents a synergetic controller for chassis coordination, combining fuzzy logic and stability region theory. First, the controller targets are the yaw rate and side slip angle, which are obtained from a highly accurate multi-body dynamic model. In addition, based on the generated fuzzy rules, the system calculates the required additional yaw moments for each actuator and optimizes their output. Then, the designed controller can distribute control effort optimally in real-time between braking and rear-wheel steering based on the stability status of the vehicle. Furthermore, a stability factor approach is used to formulate a dynamic safety strategy executed by the chassis. It helps to create the safety boundary of the vehicle and avoid excessive force and angle of execution. Finally, real-vehicle tests are conducted, and the experimental results and real-vehicle tests demonstrate significant improvements: steering wheel angle reduction by 10%, enhanced yaw stability (9% higher safety threshold) for the slalom test, and better elk testing performance (>2%). The proposed method offers practical, real-world applicability and provides valuable insights and a reference for yaw control research in the automotive industry.

Liao, Yinsheng, Hu, Zhiming, Cheng, Yuanshu, Lin, Ruya, Sun, Yue, Gao, Sixiao, Zhang, Junzhi

RDAS: A Shared Control Strategy Considering Real-Time Driving Ability in Driver Takeover Tasks

10-10-02-0014

1/24/2026

Autonomous vehicles require drivers to assume control of the vehicle in situations where the vehicle control system cannot perform its intended task. A shared control-based approach to driving authority transfer can effectively mitigate the driving risks associated with diminished driver capability due to prolonged disengagement, but it may readily precipitate human–machine conflicts—oscillatory steering behavior, excessive driver workload, and unstable control during weight transitions. Addressing the characteristics of driver capability variations during takeover tasks, a shared control strategy incorporating real-time driving ability, termed the real-time driving ability strategy (RDAS), is proposed. Initially, a real-time capability assessment strategy based on an expected steering angle model is developed. By collecting driving data under conditions of adequate driver capability to train an adaptive neuro-fuzzy inference system (ANFIS) neural network, the expected steering angle is predicted, and the deviation between actual and expected steering angles in takeover scenarios of varying difficulty is used to evaluate real-time driver capability. Subsequently, we design a dynamic weight allocation strategy, integrating real-time driving ability and the phased characteristics of driver capability changes during the takeover process. Simulation analysis of driver takeover scenarios demonstrates that, compared to other strategies, even in the case of the smallest performance difference, the RDAS reduces the conflict load (Cl) index by 71.15%, thereby enhancing driving safety and stability in the early and late stages of takeover weight transitions.

Qi, Zhenliang, Liu, Ping, Duan, Haotian, Zhou, Zilong, Huang, Haibo

An Interpretable Deep Learning Decision-Making Framework for Autonomous Lane-Change Inspired by Human Driving Experiences

2025-01-7339

12/31/2025

Lane change plays a critical role in autonomous driving and directly affects traffic safety and efficiency. Although deep learning-based lane-change decision-making frameworks have achieved promising results, they still face fundamental challenges in producing human-consistent and trustworthy behavior, mainly due to: 1) Inadequate psychology-informed personalization, as most frameworks focus on physical variables but neglect psychological factors (e.g., risk tolerance, urgency), limiting their ability to capture individual differences in lane-change motivations. 2) Limited holistic understanding of traffic context, most frameworks lack consideration of high-level and interpretable indicators (e.g., traffic pressure) in comprehensively assessing dynamic traffic scenarios, limiting their capacity for human-like contextual understanding. 3) Lack of transparent and interpretable decision logic, as many frameworks operate as black boxes with opaque reasoning processes, hindering human-aligned explanation, weakening user trust, reducing accident traceability, and impeding model refinement. To this end, a policy-oriented contextual-reasoning fuzzy neural network (POCR-FNN) is proposed as a deep learning-based decision-making framework for personalized and interpretable autonomous lane-change. First, we develop a psychology-informed driving style classification by learning distinct fuzzy membership functions to enable style-specific policy learning. Second, we design a human-inspired local interaction-aware module that estimates traffic tension by combining interaction salience and contextual risk, enhancing contextual understanding. Finally, we integrate fuzzy logic with a deep learning-based policy network to enable rule-level decision reasoning with real-time interpretability and transparent traceability. Extensive experiments on multiple public highway and urban datasets demonstrate that POCR-FNN achieves state-of-the-art performance while significantly improving personalization and interpretability across various driving styles and scenarios.

Chen, Yanbo, Chen, Jiaqi, Yu, Huilong, Xi, Junqiang

Fuzzy Logic-Based Traction Control for a 4WD In-Wheel Electric Formula Vehicle

2025-36-0114

12/18/2025

Vehicle dynamic control is crucial for ensuring safety, efficiency and high performance. In formula-type electric vehicles equipped with in-wheel motors (4WD), traction control combined with torque vectoring enhances stability and optimizes overall performance. Precise regulation of the torque applied to each wheel minimizes energy losses caused by excessive slipping or grip loss, improving both energy efficiency and component durability. Effective traction control is particularly essential in high-performance applications, where maintaining optimal tire grip is critical for achieving maximum acceleration, braking, and cornering capabilities. This study evaluates the benefits of Fuzzy Logic-based traction control and torque distribution for each motor. The traction control system continuously monitors wheel slip, ensuring they operate within the optimal slip range. Then, torque is distributed to each motor according to its angular speed, maximizing vehicle efficiency and performance. Thus, a longitudinal dynamic model was implemented in MATLAB/Simulink, incorporating traction forces, rolling resistance, aerodynamic drag and downforce, and load transfer during acceleration and braking. Tire grip was also modeled using the Pacejka formula, with data from the Tire Test Consortium (TTC). As a result, the model allows the calculation of acceleration, velocity, position, and the vehicle’s slip ratio. To simulate vehicle dynamic behavior, a representative driving cycle was defined and associated with an auxiliary control that emulates the driver throttle and braking inputs, aiming to match the desired speed profile. This approach allows the development and calibration of the fuzzy logic traction control, optimizing the vehicle performance.

Oliveira, Vivian Fernandes, Hayashi, Daniela Tiemi, Dias, Gabriel Henrique Rodrigues, Andrade Estevos, Jaqueline, Guerreiro, Joel Filipe, Ribeiro, Rodrigo Eustaquio, Eckert, Jony Javorski

An Adaptive Speed Prediction Method for Tracked Vehicles

2025-99-0325

12/17/2025

This paper addresses the issue of decreased speed prediction accuracy in tracked vehicles due to external noise during operation, and proposes an adaptive speed prediction method based on fuzzy logic. Traditional prediction methods based on physical models struggle to handle the complex dynamic characteristics unique to tracked vehicles, while GPS-based speed measurement methods have poor reliability in areas with signal obstructions. In this study, Hall sensors are used to collect real-time motor speed data, which is preprocessed through mean filtering and outlier removal, and a piecewise linear regression model is established. On this basis, the fitting parameters are dynamically adjusted using fuzzy logic. Experimental results show that during acceleration (0→1.2 m/s), deceleration (1.2→0 m/s), and constant speed (0.4/0.8/1.2 m/s) phases, the maximum absolute error of this method is less than 0.234 m/s (deviation less than 20%), and the standard deviation is all below 5% of the target speed. Under conditions of rapid speed changes, this method still maintains good prediction stability, verifying its application value and robustness in the special operating environment of tracked vehicles.

Yang, Xinyu, Yu, Wenjie, Li, Ping, Zhang, Guoliang

Robust Lateral Trajectory Tracking of Intelligent Vehicles by Using Fuzzy Adaptive Dynamic Model Predictive Control

10-10-02-0009

12/3/2025

To further improve the smoothness and robustness of lateral trajectory tracking for intelligent vehicles under complex operating conditions, this study proposes and experimentally validates a fuzzy adaptive dynamic model predictive control (FADMPC) strategy on the basis of model predictive control (MPC) framework. Thereinto, a three-degrees-of-freedom vehicle dynamics model serves as the predictive model, and a recursive least-squares algorithm with a forgetting factor is used to estimate tire cornering stiffness, thereby improving model fidelity. A whale optimization algorithm (WOA)–based adaptive horizon scheduler is devised to address the sensitivity of the prediction horizon to vehicle speed and road friction, and a fuzzy regulator adjusts the weight on the lateral displacement error in the objective function in real time. Hardware-in-the-loop tests on jointed and split-road surfaces show that compared with adaptive dynamic MPC, traditional MPC, and linear quadratic regulator, the FADMPC markedly reduces the lateral tracking error and enhances vehicle stability while maintaining performance under variations in tire cornering stiffness and localization noise and satisfying on-board real-time constraints. As a unified control framework that combines model adaptation with online scheduling, the FADMPC offers an engineering pathway to robust trajectory tracking and provides theoretical and technical bases for on-board deployment and large-scale application.

Teng, Fei, Jin, Liqiang, Wang, Junnian, Yang, Chen, Fan, Jiapeng, Qiu, Neng, Li, Andong, Zhou, Yanbo

Energy-Efficient Thermal Management in Electric Vehicles Using Fuzzy Logic Control

2025-28-0415

10/30/2025

The rapid rise in electric vehicle (EV) adoption demands innovative thermal management solutions to boost battery performance and passenger comfort. This paper introduces a novel control strategy for simultaneous battery and cabin cooling in EVs, utilizing a two-stage fuzzy logic controller. The proposed system incorporates a detailed plant model to simulate real-world conditions and dynamically optimize compressor speed, ensuring energy-efficient thermal management. In the first stage, the fuzzy controller sets the initial compressor speed based on primary inputs such as battery and cabin temperatures. The second stage fine-tunes this speed by considering secondary parameters like condenser and chiller pressures, along with the power output ratio from the plant model. This multi-stage approach guarantees efficient cooling for both the battery and cabin while maintaining safe operating conditions. Our research showcases the efficacy of this control strategy in achieving optimal thermal management in EVs, tackling the challenges of maintaining battery and cabin temperatures under varying ambient conditions. The findings suggest ways to improve energy efficiency and make components last longer, leading to more sustainable and reliable electric transport.

Ponangi, Babu Rao, Meduri, Sunil, Pudota, Praveen, J, Anandu

Multivariable Fuzzy Sliding-Mode Torque Control for Internal Combustion Engines

03-18-05-0032

7/21/2025

Internal combustion engine torque control presents a persistent challenge due to pronounced nonlinearities, parametric uncertainties, and time-varying dynamics. While conventional controllers like the proportional–integral derivative (PID) are widely implemented, they often struggle to deliver high-performance results under transient conditions. To address this gap, this work introduces and experimentally validates a novel torque controller with fuzzy sliding-mode controller (FSMC) architecture, a hybrid control not previously applied to the domain of engine torque regulation. The proposed FSMC is specifically engineered to systematically mitigate the effects of system nonlinearities by integrating the robustness of sliding-mode theory with the adaptive, chattering-suppression capabilities of fuzzy logic. This study details the controller’s development, implementation, and rigorous experimental validation on an ethanol-fueled engine via a dynamometer test bench. The controller’s performance was benchmarked against a standard PID controller, demonstrating the FSMC’s capacity for high-fidelity reference tracking, achieving mean rise and fall times up to 1.4 s and a mean absolute error not exceeding 0.2 Nm. These results signify a substantial advance in control performance and engine safety, filling the identified gap in the literature and underscoring the potential of the proposed fuzzy sliding-mode strategy as an effective and robust solution for advanced torque control in internal combustion engines.

Silva, Marcos Henrique Carvalho, Maggio, André Vinícius Oliveira, Laganá, Armando Antônio Maria, Pereira, Bruno Silva, Justo, João Francisco

Fuzzy Sliding Mode Control of Intelligent Electric Vehicles Based on Phase Plane Stability Domain Boundaries

2025-01-8802

4/1/2025

In order to effectively improve the chassis handling stability and driving safety of intelligent electric vehicles (IEVs), especially in combing nonlinear observer and chassis control for improving road handling. Simultaneously, uncertainty with system input, are always existing, e.g., variable control boundary, varying road input or control parameters. Due to the higher fatality rate caused by variable factors, how to precisely chose and enforce the reasonable chassis prescribed performance control strategy of IEVs become a hot topic in both academia and industry. To issue the above mentioned, a fuzzy sliding mode control method based on phase plane stability domain is proposed to enhance the vehicle’s chassis performance during complex driving scenarios. Firstly, a two-degree-of-freedom vehicle dynamics model, accounting for tire non-linearity, was established. Secondly, combing with phase plane theory, the stability domain boundary of vehicle yaw rate and side-slip phase plane based on vehicle dynamic model was drew in real time. The boundary was validated with a high-fidelity CarSim® software. Thirdly, combining fuzzy logic and sliding mode control, a fuzzy sliding mode controller based on dynamically identified phase boundary was designed. The stability of the algorithm was validated using Lyapunov theory. Finally, using a cooperative platform of CarSim and Matlab/Simulink, the proposed approach was presented under sinusoidal and J-Turn conditions. Results confirm that the proposed fuzzy sliding mode control method based on phase plane stability domain significantly improves the vehicle’s chassis handling stability and driving safety under various conditions. The research achievements develop a reasonable algorithm to apply to the improving road handling and ride comfort performance for a IEVs.

Liao, Yinsheng, Wang, Zhenfeng, Guo, Fenghuan, Deng, Weili, Zhang, Zhijie, Zhao, Binggen, Zhao, Gaoming

A Control Strategy for Height Adjustment in Closed-Loop Air Spring Suspension System

2025-01-8798

4/1/2025

This study examines a closed air spring suspension system. To address issues such as over-inflation, over-deflation, and excessive overshoot during vehicle height adjustment, a threshold control method is implemented. This method controls the triggering conditions for height adjustment and effectively reduces overshoot while enhancing precision. Experimental results indicate that this control strategy decreases overshoot and improves accuracy. However, risks are associated with varying threshold settings across different control modules, which can lead to over-control. A fuzzy PID controller is developed to resolve this issue. This controller adjusts PID parameters in real time based on fuzzy rules, thereby refining height adjustments. During testing, it was found that the degree of electromagnetic valve opening could not be controlled by the fuzzy PID controller. Therefore, a control strategy to adjust the compressor speed is designed. Experiments show that the fuzzy PID controller, capable of regulating compressor speed, effectively addresses the problems associated with threshold control. Additionally, this approach increases the rate of height adjustment. Real vehicle tests confirm the feasibility of the proposed control strategy. The results demonstrate that the closed air spring suspension system achieves smoother and more efficient height adjustments with improved accuracy.

Zheng, Guoqing, Yin, Zhihong, Chen, Shiwen, Shangguan, Wen-Bin

Development of ANFIS Predictive Model for Additive Manufacturing (Fusion Deposition Modeling) of PETG Material for Automotive Components

2025-28-0124

2/7/2025

Additive Manufacturing (AM), particularly Fused Deposition Modeling (FDM), has emerged as a revolutionary method for fabricating complex geometries using a variety of materials. Polyethylene terephthalate glycol (PETG) is a thermoplastic material that is biodegradable and environmentally friendly, making it a preferred choice in additive manufacturing (AM) due to its affordability and ease of use. This study aims to optimize the FDM settings for PETG material and investigate the impact of key process parameters on printing performance. An experimental study was conducted to evaluate the influence of crucial factors in FDM, including layer thickness, infill density, printing speed, and nozzle temperature, on significant outcomes such as dimensional accuracy, surface quality, and mechanical properties. The use of the Grey Relational Analysis (GRA) approach enabled a systematic assessment of multi-performance characteristics, facilitating the optimization of the FDM process. The findings demonstrated that the GRA approach is an effective tool for determining optimal parameter settings to enhance printing productivity and ensure the production of high-quality components. This study provides deeper insights into the Fused Deposition Modeling (FDM) process for Polyethylene terephthalate glycol (PETG) material, offering valuable strategies for improving manufacturing processes. By leveraging the GRA approach, this work highlights a reliable method for enhancing printing efficiency and quality, thereby promoting the wider adoption of FDM technology across various industries such as prototyping, manufacturing, and healthcare.

Pasupuleti, Thejasree, Natarajan, Manikandan, Kumar, V, Kiruthika, Jothi, Katta, Lakshmi Narasimhamu, Silambarasan, R

Optimization of Wire Electrical Discharge Machining Parameters for Invar 36 Material Using Regression Modeling

2025-28-0122

2/7/2025

Wire Electrical Discharge Machining (WEDM) is a sophisticated machining technique that offers significant advantages for processing materials with elevated hardness and complex geometries. Invar 36, a nickel-iron alloy characterized by a reduced coefficient of thermal expansion, is extensively used in the aerospace, automotive, and electronic sectors due to its superior dimensional stability across a wide temperature range. The primary goals are to improve machining settings and develop regression models that can precisely predict critical performance metrics. Experimental experiments were conducted using a WEDM system to mill Invar 36 under diverse machining parameters, including pulse-on time, pulse-off time, and current setting percentage (%). The machining performance was assessed by quantifying the material removal rate (MRR) and surface roughness (Ra). The design of experiments (DOE) methodology was used to systematically explore the parameter space and identify the optimal machining settings. Regression models were developed using statistical methods to validate the link between independent variables and output metrics, allowing precise predictions of machining performance. This work improves the understanding of WEDM for Invar 36 material and provides significant insights into the influence of machining settings on process outcomes. The empirical connection presented serves as a valuable tool for optimizing WEDM variables, enhancing the machining process's performance, and maintaining the desired surface quality in Invar 36 components. This study advocates for the implementation of WEDM as an effective manufacturing technique for Invar 36-based applications, hence advancing precision engineering and materials processing.

Pasupuleti, Thejasree, Natarajan, Manikandan, Raju, Dhanasekar, Krishnamachary, PC, Silambarasan, R

Development of AI Prediction Tool for Fused Deposition Modeling of ABS Material for Automobile Applications

2025-28-0127

2/7/2025

Fused Deposition Modeling (FDM), a form of Additive Manufacturing (AM), has emerged as a groundbreaking technology for the production of complex shapes from a variety of materials. Acrylonitrile Butadiene Styrene (ABS) is an opaque thermoplastic that is frequently employed in additive manufacturing (AM) due to its affordability and user-friendliness. The purpose of this investigation is to enhance the FDM parameters for ABS material and develop predictive models that anticipate printing performance by employing the Adaptive Neuro-Fuzzy Inference System (ANFIS). Through experimental trials, an investigation was conducted to evaluate the influence of critical FDM parameters, including layer thickness, infill density, printing speed, and nozzle temperature, on critical outcomes, including mechanical properties, surface polish, and dimensional accuracy. The utilization of design of experiments (DOE) methodology facilitated a systematic examination of parameters. A predictive model was developed to forecast printing performance by utilizing input parameters and ANFIS. The ANFIS predictive models' ability to accurately predict the printing performance of ABS material was demonstrated by the results. Moreover, the models provide vital insights into the most effective parameter configurations for ensuring high-quality parts and maximizing printing efficiency. This investigation improves the understanding of Fused Deposition Modeling (FDM) for Acrylonitrile Butadiene Styrene (ABS) material and offers a practical instrument for manufacturing process optimization. By employing ANFIS predictive models, manufacturers can enhance the quality and productivity of printing. This will facilitate the expansion of the application of FDM technology in various sectors, including healthcare, manufacturing, and prototyping.

Natarajan, Manikandan, Pasupuleti, Thejasree, Kumar, V, Kiruthika, Jothi, Katta, Lakshmi Narasimhamu, Silambarasan, R

Advanced AI Tools for Haste Alloy Machining: ANFIS Approach to Advanced Machining Optimization

2025-28-0156

2/7/2025

The intention of this exploration is to evolve an optimization method for the Electrochemical Machining (ECM) process on Haste alloy material, taking into account various performance characteristics. The optimization relies on the amalgamation of the Taguchi method with an Adaptive Neuro-Fuzzy Inference System (ANFIS). Haste alloy is extensively utilized in the aerospace, nuclear, marine, and car sectors, specifically in situations that are prone to corrosion. The experimental trials are organized based on Taguchi's principles and involve three machining variables: feed rate, electrolyte flow rate, and electrolyte concentration. This examination examines performance indicators, including the pace at which material is removed and the roughness of the surface. It also includes geometric factors such as overcut, shape, and tolerance for orientation. The results suggest that the rate at which the feed is supplied is the most influential element affecting the necessary performance standards. For improving the accuracy of predictions, numerous regression models are created and performance metrics are constructed. A validation test was performed to authenticate the findings acquired through the ANFIS methodology. The test outcomes show that the suggested strategy is considerably more efficient than earlier approaches.

Pasupuleti, Thejasree, Natarajan, Manikandan, Ramesh Naik, Mude, Somsole, Lakshmi Narayana, Silambarasan, R

Enhanced Aero Engine Components Manufacturing through Predictive Models for Cupronickel Machining

2025-28-0137

2/7/2025

Electrochemical machining (ECM) is a highly efficient method for creating intricate structures in materials that conduct electricity, regardless of their level of hardness. Due to the growing demand for superior products and the necessity for quick design changes, decision-making in the manufacturing industry has become increasingly intricate. The preliminary intention of this work is to concentrate on Cupronickel and suggest the creation of an Adaptive Neuro-Fuzzy Inference System (ANFIS) model for the purpose of predictive modeling in ECM. The study employs a Taguchi-grey relational analysis (GRA) methodology to attain multi-objective optimization, with the target of maximizing material removal rate, minimizing surface roughness, and simultaneously achieving precise geometric tolerances. The ANFIS model suggested for Cupronickel provides more flexibility, efficiency, and accuracy compared to conventional approaches, allowing for enhanced monitoring and control in ECM operations. Moreover, the study investigates the use of Cupronickel in automotive applications, emphasizing its crucial function in industries that demand resilient materials in harsh settings. The experimental validation has confirmed a strong correlation between the projected results and the actual performance, hence confirming the effectiveness of the ANFIS-based strategy.

Pasupuleti, Thejasree, Natarajan, Manikandan, Ramesh Naik, Mude, Kiruthika, Jothi, Silambarasan, R

Smart Machining of Titanium Grade 7: ANFIS Application for Process Parameter Prediction

2025-28-0160

2/7/2025

Electrochemical machining (ECM) is a highly efficient method for creating intricate structures in materials that conduct electricity, regardless of their level of hardness. Due to the growing demand for superior products and the necessity for quick design adjustments, decision-making in the manufacturing industry has grown increasingly intricate. This study specifically examines Titanium Grade 7 and suggests the creation of an Adaptive Neuro-Fuzzy Inference System (ANFIS) model for predictive modelling in ECM. The study employs a Taguchi-grey relational analysis (GRA) methodology to attain multi-objective optimization, with the goal of concurrently maximizing material removal rate, minimizing surface roughness, and achieving precise geometric tolerances. Analysis of variance (ANOVA) is used to assess the relevance of process characteristics that impact these performance measures. The ANFIS model presented for Titanium Grade 7 provides more flexibility, efficiency, and accuracy in comparison to conventional approaches, allowing for greater monitoring and control in ECM operations. Moreover, the study investigates the potential uses of Titanium Grade 7 in the automotive industry, emphasizing its crucial function in sectors that demand resilient materials in corrosive surroundings. The experimental validation demonstrates a strong correlation between the projected results and the actual performance, so confirming the effectiveness of the ANFIS-based strategy.

Natarajan, Manikandan, Pasupuleti, Thejasree, D, Palanisamy, Kiruthika, Jothi, Silambarasan, R

Revolutionizing Titanium Alloy Machining: ANFIS Model for Advanced Machining Performance Optimization

2025-28-0046

2/7/2025

Electrochemical machining (ECM) is a highly efficient method for creating intricate structures in electrically conductive materials, regardless of their hardness. Due to the growing demand for superior products and the necessity for quick design adjustments, decision-making in the manufacturing industry has become increasingly complex. This study specifically examines Titanium Grade 19 and suggests the creation of an Adaptive Neuro-Fuzzy Inference System (ANFIS) model for predictive modeling in ECM. The study employs a Taguchi-grey relational analysis (GRA) methodology to attain multi-objective optimization, with the goal of concurrently maximizing material removal rate, minimizing surface roughness, and achieving precise geometric tolerances. Analysis of variance (ANOVA) is used to assess the relevance of process characteristics that impact these performance measures. The ANFIS model presented for Titanium Grade 19 provides more flexibility, efficiency, and accuracy in comparison to conventional approaches, allowing for greater monitoring and control in ECM operations. Moreover, the study investigates the potential uses of Titanium Grade 19 in the automotive industry, emphasizing its crucial function in sectors that demand resilient materials in corrosive environments. The experimental validation demonstrates a strong correlation between the projected results and the actual performance, confirming the effectiveness of the ANFIS-based strategy.

Pasupuleti, Thejasree, Natarajan, Manikandan, Raju, Dhanasekar, Kiruthika, Jothi, Katta, Lakshmi Narasimhamu, Silambarasan, R

AI-Driven Optimization of Advanced Machining for Haste Alloy by ANFIS Method

2025-28-0141

2/7/2025

Electrochemical machining (ECM) is a highly efficient method for creating intricate structures in materials that conduct electricity, independent of their level of hardness. Due to the increasing demand for superior products and the necessity for quick design modifications, decision-making in the manufacturing sector has become progressively more difficult. This study primarily examines the use of Haste alloy in vehicle applications and suggests creating regression models to predict performance parameters in ECM. The experiments are formulated based on Taguchi's ideas, and mathematical equations are derived using multiple regression models. The Taguchi approach is employed for single-objective optimization to ascertain the ideal combination of process parameters for optimizing the material removal rate. ANOVA is employed to evaluate the statistical significance of process parameters that impact performance indicators. The proposed regression models for Haste alloy are more versatile, efficient, and accurate in comparison to the current models, providing enhanced monitoring capabilities. The updated models have been verified, demonstrating a robust link between empirical data and projected results.

Natarajan, Manikandan, Pasupuleti, Thejasree, D, Palanisamy, Silambarasan, R, Krishnamachary, PC

Predictive Grey-ANFIS Model for High-Precision Machining of Nimonic Alloy in Automobiles

2025-28-0043

2/7/2025

The aim of this study is to create an Adaptive Neuro-Fuzzy Inference System (ANFIS) model for the Electrochemical Machining (ECM) process using Nimonic Alloy material, with a specific focus on several performance aspects. The optimization strategy utilizes the combination of the Taguchi method and ANFIS integration. Nimonic Alloy is widely employed in the aerospace, nuclear, marine, and car sectors, especially in situations that are susceptible to corrosion. The experimental trials are designed according to Taguchi's method and involve three machining variables: feed rate, electrolyte flow rate, and electrolyte concentration. This study investigates performance indicators, such as the rate at which material is removed, the roughness of the surface, and geometric characteristics, including overcut, shape, and tolerance for orientation. Based on the analysis, it has been determined that the feed rate is the main component that influences the intended performance criteria. In order to improve the precision of forecasts, numerous regression models are created and performance indicators are formulated. A validation test was performed to affirm the results achieved through the use of the ANFIS methodology. The test findings indicate that the proposed strategy surpasses previous methodologies to a significant degree.

Natarajan, Manikandan, Pasupuleti, Thejasree, C, Navya, Kiruthika, Jothi, Silambarasan, R

Intelligent Vehicle Trajectory Tracking Control Based on Variable Universe Fuzzy Rule Speed Planning and Piecewise Preview Model Prediction

02-18-01-0006

2/6/2025

Intelligent vehicles can utilize a variety of sensors, computing, and control technologies to autonomously perceive the environment and make decisions to achieve safe, efficient, and automated driving. If the speed planning of intelligent vehicles ignores the vehicle dynamics state, it leads to unreasonable planning speed and is not conducive to improving the accuracy of trajectory tracking control. Meanwhile, trajectory tracking usually does not consider the road and speed information beyond the prediction horizon, resulting in poor tracking precision that is not conducive to improving driving comfort. To solve these problems, this study proposes a new longitudinal speed planning method based on variable universe fuzzy rules and designs the piecewise preview model predictive control (PPMPC) to realize the vehicle trajectory tracking. First, the three-degrees-of-freedom vehicle dynamics model and trajectory tracking model are established and verified. Then, the variable universe fuzzy rules are introduced to design the longitudinal speed planning method, in which the road friction coefficient and road curvature are defined as the input of the speed planning method, and the vehicle lateral deviation is defined as the scaling factor input of the speed variable universe. Based on the dynamics model and trajectory tracking model, the PPMPC method is proposed to improve the accuracy and stability of trajectory tracking. During the PPMPC method design, the reference value of state quantity in the prediction horizon can be updated by using further road information and planning longitudinal speed information. Finally, the results show that the proposed planning algorithm can provide a reasonable longitudinal speed to reduce the tracking lateral error in the tracking control, and the proposed PPMPC can significantly improve the vehicle speed-tracking accuracy and control stability compared with the traditional model predictive control (MPC) method.

Zhang, Jie, Teng, Shipeng, Gao, Jianjie, Zhou, Xingxing, Zhou, Junchao

Vibration Suppression of a Flexible Appendage and Pitch Angle Fuzzy Regulation of a Spacecraft

01-18-01-0004

2/5/2025

In this work, the large-angle rotational movement and vibration suppression of a flexible spacecraft are carried out based on an adjustable system. First the spacecraft model is transformed into a canonical affine control form, then two fuzzy systems are used: The first (of Takagi–Sugeno type) estimates the feedback linearization control law as a whole, while the second (of Mamdani type) adjusts and stabilizes the control parameters using the gradient descent technique and based on the minimization of the control error rather than the tracking error. Stability results are presented in terms of Lyapunov’s theory, and simulation tests illustrate the significant transient robustness of the closed-loop system against perturbations, the accurate trajectory control, and vibration suppression of the flexible spacecraft. Consequently, as will be shown later, the error will stay confined and converges quickly to zero, confirming the smoothing property of the proposed method using fuzzy logic systems.

Bahita, Mohamed

A Two-Layer Fuzzy Control Energy Management Method for Hydrogen Fuel Cell Heavy-Duty Trucks Considering Fuel Cell Health State

2025-01-7092

1/31/2025

Hydrogen fuel cell trucks have enormous development potential in the pursuit of global carbon neutrality and sustainable development. However, their commercialization and mass production are facing challenges in various aspects, especially the durability problem of fuel cells. This paper is intended to set up a high-power hydrogen fuel cell system (FCS) model, considering the fuel cell degradation factors, and based on this, proposes a two-layer fuzzy energy management strategy (EMS) to optimize the life of fuel cell and the total energy consumption of the vehicle. The first control layer provides real-time energy distribution efficiently from multiple sources and thus allows flexibility in energy supply. The second layer regulates the dynamic adjustment of fuel cell output power with degradation of both fuel cells and batteries considered, to make the prolonging of system lifetime possible. In this respect, the equivalent hydrogen consumption, which incorporates fuel cell degradation, is used as the objective function. A genetic algorithm is employed to optimize the membership functions and rule weights involved in the fuzzy control system, considering the determination of the best energy management solution. Simulation results of a 115 kW fuel cell truck operating based on the China World Transient Vehicle Cycle (C-WTVC) conditions show that the proposed strategy reduces fuel cell degradation by 36.7% compared to that of traditional single-layer fuzzy control methods under extreme operating conditions. These results clearly depict gains in economic efficiency and sustainability of the system and hence indicate the advantages of the two-layer control strategy.

Hou, Quan, Wang, Han, Zhu, Dan

Enhanced Adaptive Cruise Control Strategies Considering Front and Rear Vehicles

10-09-01-0007

1/29/2025

Adaptive cruise control (ACC) systems have increasingly become more robust in adapting to the motion of the preceding vehicle and providing safety and comfort to the driver. But conventional ACC hangs with a concern for rear-end safety in the presence of traffic or aggressive car maneuvers. It often leads to getting dangerously close to the vehicle behind in scenarios where there is less space and time for the rear vehicle to adjust. This research article develops an ACC approach that considers the rear vehicle in addition to the front vehicle, thereby ensuring safety with the rear vehicle without compromising the safety of the front vehicle. Two novel methodologies are devised to enhance the ACC system. The first approach involves utilizing fuzzy logic to associate the inputs with the throttle and brake based on the inference rules within a fuzzy logic controller overseeing both vehicles. The other utilizes a cascaded model predictive control (MPC) system framework that integrates a novel formulation based on vehicle kinematics to devise an optimal reference speed to maintain safe distance with both vehicles, which is fed to the lower level MPC that generates the corresponding throttle and brake values to track the reference speed while ensuring smooth speed transitions. Priority is given to the front vehicle in conflicting situations. Finally, the efficacy of the control strategies is validated using industry-standard simulation software Prescan by assessing the comparative performances of both the control strategies. The results of this study will provide valuable insights into the enhancement of ACC systems by improving the distance safety margin of the ACC-equipped vehicle with respect to the rear vehicle along with the front, ultimately contributing to better throughput of traffic and safer road mobilization.

Sharma, Vishrut, Sengupta, Somnath, Ghosh, Susenjit

Multi-Objective Welding Optimization for AA5052 Using Taguchi-Fuzzy Approach

05-18-03-0018

1/24/2025

This study investigates the influence of tungsten inert gas (TIG) welding parameters on the dilution and hardness of AA5052 aluminum alloy. Employing Taguchi’s L27 orthogonal array, the research systematically explores the effects of current, voltage, and welding speed. Analysis of the experimental data utilizes signal-to-noise ratio, analysis of variance (ANOVA), and regression techniques. The study compares a traditional regression model with a fuzzy logic approach for result validation, finding that the latter exhibits marginally better predictive accuracy. Optimal welding parameters are identified as 150 A current, 20 V voltage, and 45 mm/s welding speed, yielding a maximum dilution of 52.81% and hardness of 145.3 HV 0.5. Current emerges as the most significant factor influencing both dilution and hardness. Microstructural examination, hardness profiling, and tensile testing of specimens welded under optimized conditions reveal a characteristic hardness distribution across the weld zones and ductile fracture behavior.

Omprakasam, S., Raghu, R., Balaji Ayyanar, C.

PDCA-Guided Development of Fuzzy Logic Controller for Autonomous Vehicle Cruise Control and Collision Avoidance

2024-36-0188

12/20/2024

The advancement of the automotive industry towards automation has fostered a growing integration between this field and automation. Future projects aim for the complete automation of the act of driving, enabling the vehicle to operate independently after the driver inputs the desired destination. In this context, the use of simulation systems becomes essential for the development and testing of control systems. This work proposes the control of an autonomous vehicle through fuzzy logic. Fuzzy logic allows for the development of sophisticated control systems in simple, easily maintainable, and low-cost controllers, proving particularly useful when the mathematical model is subject to uncertainties. To achieve this goal, the PDCA method was adopted to guide the stages of defining the problem, implementation, and evaluation of the proposed model. The code implementation was done in Python and validated using different looping scenarios. Three linguistic variables were used, one with three fuzzy sets. As a result, nine rules were implemented in order to evaluate the vehicle’s response. An iterative loop was proposed to model different acceleration, deceleration or speed maintenance scenarios. The implementation of a system controlled by fuzzy logic was performed using the Python programming language. The simulations validated the speed adjustment, proving to be efficient for applications in autonomous vehicles as a simple and low computational cost approach.

Branco, César Tadeu Nasser Medeiros, Santos, Rafael Celestino

A Driving Behavior Decision Method Based on Gradient Boosting Tree Algorithm

2024-01-7030

12/13/2024

In order to reduce the incidence of traffic accidents and improve passengers’ driving experience, intelligent driving technology has attracted more and more attention. The core content of intelligent driving technology includes environment perception, behavior decision-making and control follow-up. Simulating driver’s behavior decision-making based on multi-source heterogeneous environment information is the key to liberate drivers and become the focus and difficulty of intelligent driving technology. Aiming at this key problem, this paper presents a design method of driving behavior decision maker based on machine learning after fuzzy classification of historical data. Firstly, 1000 sets of driving environment-decision results database are generated randomly according to driving rules and driving state. A fuzzy classification rule is established to classify driving environment information such as speed and relative distance. Then, a driving behavior decision maker is designed based on gradient lifting tree algorithm of machine learning. Finally, the driving behavior decision accuracy of the proposed method is 100% after running the simulation software, while the decision accuracy of the behavior decision maker based on the traditional BP neural network method is only 70.4%. Through the above research, it can be concluded that the driving behavior decision maker based on machine learning has obvious advantages, and its high accuracy and fast operation can also meet the requirements of real-time, fast and accurate intelligent driving, which provides a technical basis for the realization of unmanned driving technology.

Li, Hongluo, Xia, Hongyang, Huang, Yongxian, Xu, You, Xu, Wei

Development of ANFIS Predictive Model for Wire Electrical Discharge Machining of Cupronickel Material

2024-28-0239

12/5/2024

Wire Electrical Discharge Machining (WEDM) is an essential manufacturing process used to shape complex geometries in conductive materials such as cupronickel, which is valued for its corrosion resistance and electrical conductivity. The aim of this explorative study is to enhance the efficiency and precision of machining by creating a specialized predictive model using an Adaptive Neuro-Fuzzy Inference System (ANFIS) for cupronickel material. The study examines the intricate correlation between process variables of the WEDM (Wire Electrical Discharge Machining) technique, such as pulse-on time (Ton), pulse-off time (Toff), and discharge current, and crucial machining responses, including surface roughness, material removal rate. Data is collected through systematic experimentation in order to train and validate the ANFIS predictive model. The ANFIS model utilizes the collective learning capabilities of neural networks and fuzzy logic systems to precisely forecast machining responses by considering input parameters. The ANFIS model captures the complex nonlinearities of the WEDM process, allowing for valuable insights into the best parameter settings to achieve desired machining results. The effectiveness of the developed ANFIS predictive model is assessed through statistical analysis and compared with empirical findings. The model showcases its proficiency in accurately predicting machining responses, providing manufacturers with a potent instrument for optimizing processes and making decisions in cupronickel material WEDM operations. This allows manufacturers to enhance productivity and quality while simultaneously reducing production costs. This research enhances the comprehension of WEDM processes and provides practical recommendations for achieving excellent machining results in diverse industrial applications.

Pasupuleti, Thejasree, Natarajan, Manikandan, Kiruthika, Jothi, Katta, Lakshmi Narasimhamu, Silambarasan, R.

Optimization and ANFIS Predictive Modeling of Wire Electrical Discharge Machining for Invar 36 Material

2024-28-0243

12/5/2024

Wire Electrical Discharge Machining (WEDM) is a highly accurate machining approach that is well-known for its capability to create intricate forms in materials with high levels of hardness and intricate geometries. Invar 36, a nickel-iron alloy, is extensively utilized in industries that demand exceptional dimensional stability across a wide temperature range. The objective of this exploration is for optimizing the WEDM parameters of Invar 36 material. Additionally, a predictive model called Adaptive Neuro-Fuzzy Inference System (ANFIS) will be developed to forecast the machining performance. The study involved conducting experimental trials to analyze the influence of crucial factors in WEDM. These parameters included pulse-on time (Ton), pulse-off time (Toff), and current. The objective was to examine their influence on key performance indicators such as material removal rate (MRR), surface roughness (Ra). The methodology of Design of Experiments (DOE) enabled a systematic exploration of parameters. A predictive model using ANFIS was created to forecast machining performance by utilizing input parameters. The model was trained using empirical data to accurately capture the intricate correlations between process variables and output responses. The outcomes clearly demonstrated that the ANFIS predictive model was highly effective in accurately predicting machining performance for WEDM of Invar 36 material. The model offers valuable insights on the ideal parameter configurations to maximize machining efficiency and surface quality. This study enhances the comprehension of WEDM for Invar 36 material and provides a useful tool for optimizing the process. Manufacturers can improve machining productivity and quality in precision engineering applications by utilizing the ANFIS predictive model, thereby promoting the wider use of WEDM technology.

Natarajan, Manikandan, Pasupuleti, Thejasree, Kiruthika, Jothi, Katta, Lakshmi Narasimhamu, Silambarasan, R

Optimization and ANFIS Predictive Modeling of Additive Manufacturing (Fused Deposition Modeling) for PLA Material

2024-28-0240

12/5/2024

Additive Manufacturing (AM), specifically Fused Deposition Modeling (FDM), has become a revolutionary technology for creating intricate shapes using different materials. Polylactic Acid (PLA) is a biodegradable thermoplastic that is commonly used in additive manufacturing (AM) because of its environmentally friendly properties, affordability, and ease of use. The objective of this study is to optimize the FDM parameters for PLA material and create predictive models using the Adaptive Neuro-Fuzzy Inference System (ANFIS) to forecast printing performance. An investigation was carried out through experimental trials to examine the impact of important FDM parameters, such as layer thickness, infill density, printing speed, and nozzle temperature, on critical outcomes such as dimensional accuracy, surface finish, and mechanical properties. The utilization of design of experiments (DOE) methodology enabled a methodical exploration of parameters. A predictive model using ANFIS was created to forecast printing performance by utilizing input parameters. The results demonstrated the effectiveness of the ANFIS predictive models in accurately predicting printing performance for PLA material. The models offer valuable insights into the most effective parameter configurations for maximizing printing efficiency and ensuring high-quality parts. This study enhances the comprehension of Fused Deposition Modeling (FDM) for Polylactic Acid (PLA) material and provides a useful tool for optimizing the manufacturing process. Manufacturers can improve printing productivity and quality by utilizing ANFIS predictive models. This will help promote the wider use of FDM technology in different industries such as prototyping, manufacturing, and healthcare.

Pasupuleti, Thejasree, Natarajan, Manikandan, Kiruthika, Jothi, Ramesh Naik, Mude, Silambarasan, R

Development of ANFIS Predictive Model for Additive Manufacturing of TPU Material

2024-28-0025

10/17/2024

Additive Manufacturing (AM) techniques, particularly Fusion Deposition Modeling (FDM), have received considerable interest due to their capacity to create complex structures using a diverse array of materials. The objective of this study is to improve the process control and efficiency of Fused Deposition Modeling (FDM) for Thermoplastic Polyurethane (TPU) material by creating a predictive model using an Adaptive Neuro-Fuzzy Inference System (ANFIS). The study investigates the impact of FDM process parameters, including layer height, nozzle temperature, and printing speed, on key printing attributes such as tensile strength, flexibility, and surface quality. Several experimental trials are performed to gather data on these parameters and their corresponding printing attributes. The ANFIS predictive model is built using the collected dataset to forecast printing characteristics by analyzing input process parameters. The ANFIS model utilizes the learning capabilities of neural networks and fuzzy logic systems to analyze the intricate relationships within the FDM process. This model allows for precise predictions of printing outcomes. The model shows its ability to precisely forecast printing attributes, enabling the determination of ideal process parameter configurations for enhanced FDM performance with TPU material. The proposed Adaptive Neuro-Fuzzy Inference System (ANFIS) predictive model presents a methodical strategy for optimizing Fused Deposition Modeling (FDM) parameters. This model serves as a valuable tool for manufacturers to improve productivity and product quality in additive manufacturing operations using Thermoplastic Polyurethane (TPU) material. This research enhances the comprehension of FDM processes and provides practical recommendations for optimizing AM operations in diverse industrial applications.

Pasupuleti, Thejasree, Natarajan, Manikandan, D, Palanisamy, A, Gnanarathinam, Umapathi, D, Kiruthika, Jothi

Method for Modeling Automotive Manufacturing Equipment Preventive Maintenance Derived by Multi-Criteria Decision and Synthesized Weibull Distribution

2024-01-5096

10/8/2024

To avoid equipment failures in automotive manufacturing activities, particular attention is paid to the design of an effective preventive maintenance strategy model for automotive component processing equipment. The selection of appropriate maintenance intervals as well as the equilibrium between the benefits and costs should be the primary challenges in high-quality maintenance process. In this study, a reliable preventive maintenance strategy model is proposed and the aim is to suggest an appropriated approach for the selection of maintenance intervals from a comprehensive view of importance, hazard, and maintenance cost. First and foremost, a new Fermatean fuzzy entropy (FFE) measure method on the basis of analytic hierarchy process (AHP) is innovatively employed to access more objective weights of each indicator. Moreover, a more objective scoring of importance and hazard indicator is executed to aggregate the expert group judgments. Furthermore, this study emphasizes the introduction of a stable equipment reliability distribution, which is obtained using scientific regression on the basis of failure data. Thus, the maintenance cost of the equipment could be derived based on the equipment’s reliability. As a consequence, the prediction of the probability of failure occurring and preventive maintenance cycle are well validated. In conclusion, the preventive maintenance strategy established in the study not only reduces the inherent subjectivity in multi-criteria decision analysis, but also improves the accuracy of equipment failure probability prediction. Hence, it offers novel perspectives on optimized maintenance intervals and the balance between benefits and costs.

Ma, Zexin, Pan, Zhesheng, Wang, Chengxiang, Wei, Mingxin, Yu, Wenbin, Li, Guoxiang, Zhao, Feiyang, Zhu, Sipeng

A Hardware-in-the-Loop Platform for Developing a Fuel Cell Hybrid Electric Microcar: Fuel Cell Stack Sizing Using a Real-Time Testing Approach

2024-24-0006

9/18/2024

Sustainable mobility is a pressing challenge for modern society. Electrification of transportation is a key step towards decarbonization, and hydrogen Fuel Cell Hybrid Electric Vehicles (FCHEVs) offer a promising alternative to Battery Electric Vehicles (BEVs), especially for long-range applications: they combine a battery system with a fuel cell, which provides onboard electric power through the conversion of hydrogen. Paramount importance is then given to the design and sizing of the hybrid powertrain for achieving a compromise between high performance, efficiency, and low cost. This work presents a Hardware-in-the-Loop (HIL) platform developed for designing and testing the powertrain layout of an FCHEV. The platform comprises two systems: a simulation model reproducing the dynamics of a microcar and a hardware system for the fuel cell hybrid electric powertrain. The former simulates the vehicle's behavior, while the latter is composed of a 2kW real fuel cell stack and a 100Ah Li-ion battery pack. This element is used for real-time testing of the hybrid powertrain, using a programmable power supply that emulates the vehicle and motor load request. Two fuel cell stack configurations have been analyzed by applying a linear scale-up approach (2kW and 4kW) and tested on an acceleration and deceleration driving cycle, representative of the microcar application; a simple fuzzy logic control strategy has been chosen for the test. The system's performances have been evaluated and deeply analyzed in terms of component behavior and energy efficiency. The results demonstrate that the 4kW stack configuration scores a nearly 5% higher efficiency than the 2kW stack, mainly operating in the lower current regions corresponding to higher efficiencies. The improvements can then be translated into an increase in the vehicle's estimated range, more than balancing the increased weight burden of nearly 10kg. By enabling the possibility to consider and test the real behavior of powertrain components, the HIL platform has proven to be an effective tool for design purposes.

Bartolucci, Lorenzo, Cennamo, Edoardo, Cordiner, Stefano, Donnini, Marco, Grattarola, Federico, Mulone, Vincenzo

Improved Monitoring and Classification of Engine Oil Condition through Two Machine Learning Techniques

04-18-01-0005

9/14/2024

This study explores the effectiveness of two machine learning models, namely multilayer perceptron neural networks (MLP-NN) and adaptive neuro-fuzzy inference systems (ANFIS), in advancing maintenance management based on engine oil analysis. Data obtained from a Mercedes Benz 2628 diesel engine were utilized to both train and assess the MLP-NN and ANFIS models. Six indices—Fe, Pb, Al, Cr, Si, and PQ—were employed as inputs to predict and classify engine conditions. Remarkably, both models exhibited high accuracy, achieving an average precision of 94%. While the radial basis function (RBF) model, as presented in a referenced article, surpassed ANFIS, this comparison underscored the transformative potential of artificial intelligence (AI) tools in the realm of maintenance management. Serving as a proof-of-concept for AI applications in maintenance management, this study encourages industry stakeholders to explore analogous methodologies. Highlights Two machine learning models, multilayer perceptron neural networks (MLP-NN) and adaptive neuro-fuzzy inference systems (ANFIS), were employed to predict and classify the performance condition of diesel engines. Among various training algorithms, Levenberg–Marquardt and the Bayesian regularization demonstrated superior classification accuracy, achieving a 95%–96% range. To assess the generalizability of MLP-NN and ANFIS, the training set size was varied from 90% to 10%. The ANFIS model exhibited greater stability than MLP-NN, with a 50% higher performance. Graphical Abstract

Pourramezan, Mohammad-Reza, Rohani, Abbas

Personalized Design of Variable Transmission Ratio and Selection Switching Strategies Considering Drivers’ Steering Characteristics

10-08-04-0028

9/14/2024

In order to meet the driving characteristics and needs of different types of drivers and to improve driving comfort and safety, this article designs personalized variable transmission ratio schemes based on the classification results of drivers’ steering characteristics and proposes a switching strategy for selecting variable transmission ratio schemes in response to changes in driver types. First, data collected from driving simulator experiments are used to classify drivers into three categories using the fuzzy C-means clustering algorithm, and the steering characteristics of each category are analyzed. Subsequently, based on the steering characteristics of each type of driver, suitable speed ranges, steering wheel travel, and yaw rate gain values are selected to design the variable transmission ratio, forming personalized variable transmission ratio schemes. Then, a switching strategy for variable transmission ratio schemes is designed, using a support vector machine to build a driver classification and identification model, and a transition scheme for variable transmission ratios is proposed. Finally, simulations are conducted to validate the personalized variable transmission ratio schemes and the transition schemes. The results show that the personalized variable transmission ratio schemes reduce driver burden and improve vehicle handling stability while meeting the driving characteristics and needs of different types of drivers. The switching strategy for selecting variable transmission ratio schemes can smoothly transition between different schemes for different types of drivers, ensuring that the variable transmission ratio schemes better match the driving characteristics and needs of the driver without affecting normal driving.

Chen, Chen, Zheng, Hongyu, Zong, Changfu

Modelling and Simulation of Electronic Brake Booster with Fuzzy Logic Control

2024-01-3052

9/8/2024

On one hand, simulation tools are widely used to study and examine new technologies before building prototypes. It is a cost and time saver if it is mathematically modeled with and simulated in real time with sufficient fidelity. On the other hand, the expansion of electric and hybrid vehicle development requested advancing the Electronic Brake Booster (EBB) technologies. In this paper, a simulation tool for the EBB is developed to simulate the performance in real time with a very quick response compared to the previous models with a novel fuzzy logic control (FLC) for the position tracking control. The configuration of the EBB is established, and the system model, including the permanent magnet synchronous motor (PMSM), a double reduction transmission (gears and a ball screw), a servo body, a reaction disc, and the hydraulic load, is modeled. The load-dependent friction has been compensated by using the Karnopp-friction model. FLC has been used for the control algorithm. The control concept focused on transforming the pressure control of the EBB into position tracking control to overcome the nonlinearity and achieve the control process with the required precision and dynamics. The EBB simulation model has been developed using MATLAB/Simulink, and an ode4 Runge-Kutta solver with a step size of 10 milliseconds is used to solve the differential equations of the model. In order to present the reliability of the developed simulation model, a comparison was made with a widely referenced and validated EBB model that was developed to simulate the performance. The simulation results showed a very good correlation between the developed model and the widely referenced model. In addition to that, the developed model is able to simulate the performance of the EBB faster than the widely referenced model and has real-time behavior.

Soliman, Amr M.E., Kaldas, Mina M., Soliman, Aref M.A., Huzayyin, Ahmed

Research on Network Security Situation Prediction Algorithm Combining Intuitionistic Fuzzy Sets and Deep Neural Networks

12-07-03-0022

4/17/2024

The expansion of the internet has made everyone’s personal and professional lives more transparent. There are network security issues because people like sharing resources under the right conditions. Academics have demonstrated significant interest in situation awareness, which includes situation prediction, situation appraisal, and event detection, rather than focusing on the security of a single device in the network. Multi-stage attack forecasting and security situation awareness are two significant issues for network supervisors because the future usually is unknown. Hence, this study suggests combined intuitionistic fuzzy sets and deep neural network (CIFS-DNN) for network security situation prediction. The goal is to provide network administrators with a resource they can use as a point of reference while they formulate and carry out preventive actions in the event of a network assault. The job requires differentiating between the event of an assault and a typical instance, as well as differentiating between the various sorts of attacks and a typical case. In this article, we present a model that can more accurately and effectively forecast network security scenarios, and our experiments bear this out. The results show that the proposed technique is successful and exact in predicting network security issues. The suggested CIFS-DNN approach has a low delay rate of 10%, a low latency rate of 20%, a low error rate of 25%, a high prediction ratio of 98.6%, a high security rate of 98.3%, a high accuracy ratio of 99.6%, and a high efficiency ratio of 93.9%

Gao, Hui, Guo, Liang

Enhancing Lateral Stability in Adaptive Cruise Control: A Takagi-Sugeno Fuzzy Model-Based Strategy

2024-01-1962

4/9/2024

Adaptive cruise control is one of the key technologies in advanced driver assistance systems. However, improving the performance of autonomous driving systems requires addressing various challenges, such as maintaining the dynamic stability of the vehicle during the cruise process, accurately controlling the distance between the ego vehicle and the preceding vehicle, resisting the effects of nonlinear changes in longitudinal speed on system performance. To overcome these challenges, an adaptive cruise control strategy based on the Takagi-Sugeno fuzzy model with a focus on ensuring vehicle lateral stability is proposed. Firstly, a collaborative control model of adaptive cruise and lateral stability is established with desired acceleration and additional yaw moment as control inputs. Then, considering the effect of the nonlinear change of the longitudinal speed on the performance of the vehicle system. And the input penalty factor of the adaptive cruise control system is designed as a variable parameter for the collaborative control model. On this basis, the longitudinal speed, reciprocal of speed and penalty factor are used as advance variables to design fuzzy rules of the system. And the nonlinear Takagi-Sugeno fuzzy model is established by fuzzifying the local linear model. Then, the vehicle following cruise controller considering the lateral stability is designed by parallel distribution compensation method. Finally, the TruckSim/Simulink co-simulation model was built for testing. The test results show that the proposed controller can improve the lateral stability of the vehicle during the following process, reduce the risk of instability of the vehicle, and improve the overall safety of the automatic driving system.

Yan, Yang, Xin, Yafei, Zheng, Hongyu

Fuzzy Control of Regenerative Braking on Pure Electric Garbage Truck Based on Particle Swarm Optimization

2024-01-2145

4/9/2024

To improve the braking energy recovery rate of pure electric garbage removal vehicles and ensure the braking effect of garbage removal vehicles, a strategy using particle swarm algorithm to optimize the regenerative braking fuzzy control of garbage removal vehicles is proposed. A multi-section front and rear wheel braking force distribution curve is designed considering the braking effect and braking energy recovery. A hierarchical regenerative braking fuzzy control strategy is established based on the braking force and braking intensity required by the vehicle. The first layer is based on the braking force required by the vehicle, based on the front and rear axle braking force distribution plan, and uses fuzzy controllers. Achieve one-time distribution of the front axle braking force; the second layer, according to the magnitude of the braking intensity, divides the braking conditions into light braking, moderate braking and emergency braking, and realizes braking under the three working conditions respectively. Secondary distribution of front axle braking force. Using the driving mileage contribution as the evaluation index and NEDC as the simulation working condition, it is verified that the regenerative braking control strategy can achieve energy recovery. To further improve the braking energy recovery and ensure the vehicle braking effect, the braking effect and braking energy recovery are used as the optimization objective function, the particle swarm algorithm is used to optimize the fuzzy rules, and the optimized fuzzy controller is reloaded into the regenerative braking control Simulation is carried out in the strategy to verify that the designed multi-section front and rear wheel braking force distribution curves and fuzzy rules optimized by particle swarm algorithm can effectively improve regenerative braking energy recovery and improve vehicle driving range, while ensuring braking safety.

Zhang, Yu

Vehicle Braking Performance Improvement via Electronic Brake Booster

10-08-01-0005

2/10/2024

Throughout the automobile industry, the electronic brake boost technologies have been widely applied to support the expansion of the using range of the driver assist technologies. The electronic brake booster (EBB) supports to precisely operate the brakes as necessary via building up the brake pressure faster than the vacuum brake booster. Therefore, in this article a novel control strategy for the EBB based on fuzzy logic control (FLC) is developed and studied. The configuration of the EBB is established and the system model including the permanent magnet synchronous motor (PMSM), a two-stage reduction transmission (gears and a ball screw), a servo body, reaction disk, and the hydraulic load are modeled by MATLAB/Simulink. The load-dependent friction has been compensated by using Karnopp friction model. Due to the strong nonlinearity on the EBB components and the load-dependent friction, FLC has been used for the control algorithm. The control concept focused on transforming the pressure control to position tracking control of the EBB, which enabled overcoming the nonlinearity in the hydraulic system and achieve the control process with the required precision and dynamics. The improvement on the vehicle braking performance was examined and demonstrated theoretically by comparing the EBB and the vacuum brake booster. The EBB model and its control strategy are integrated to a well-used verified seven degrees of freedom longitudinal–vertical vehicle model. The results showed that the position tracking control of the EBB perform well. The braking performance of the vehicle with EBB is better than the vacuum brake booster in terms of response time and stopping distance and time. Furthermore, the EBB has improved stability in its booster characteristics while maintaining consistency with vacuum brake booster.

Soliman, Amr M.E., Kaldas, Mina M., Soliman, Aref M.A., Huzayyin, A.S.

Hydrodynamic Flow Characteristics Prediction for Bluff Body Wake via Novel Adaptive Neuro-Fuzzy Controller Avoiding Fuzzy Rule Explosion

2023-01-5081

11/22/2023

This study analyses the effect of Reynolds number (Re) and bluff body shape (quantified by shape factor SF) variation on various hydrodynamic characteristics of unsteady bluff body flow, such as Strouhal number, maximum lift coefficient, and mean drag coefficient. The study initially examines a relationship among these characteristics and further utilizes artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS) controllers for their precise prediction. The results from real-time computational fluid dynamics (CFD) experimentations were gathered and considered to train ANN controllers. A novel ANFIS controller has been designed using only three membership functions thus solving the problem of fuzzy rule explosion. The results indicate that both the ANN and ANFIS controllers can precisely predict these hydrodynamic flow characteristics as validated through minimal values of root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). It is observed that ANFIS controller provides better results compared to the proposed feed-forward ANN controller. The RMSE, MAE, and MAPE obtained for ANFIS model for different shape factors for maximum lift coefficient were 0.0024, 0.002, and 0.85%, respectively.

Kharola, Ashwani, Dobriyal, Ritvik, Sharma, Rakesh Chandmal, Sharma, Neeraj, Sharma, Ashwini, Raturi, Anuj

Artificial Intelligence Model for Machinability Investigations on Drilling of AA6061 with Micro Textured Tool for Automobile Applications

2023-28-0082

11/10/2023

Considering the advancements in manufacturing industries, which are crucial for economic growth, there is a substantial demand for exploration and analysis of advanced materials, especially alloy materials, to enable efficient utilization of new technologies. Lightweight and high-strength materials, like aluminium alloys, are highly recommended for various applications that necessitate both strength and resistance to corrosion, such as automobile, marine and high-temperature applications. Therefore, there is a significant need to investigate and analyse these materials to facilitate their effective application in manufacturing sectors. This study investigates the machinability of drilling AA6061 using a micro-textured tool and proposes an Adaptive Neuro Fuzzy Inference System (ANFIS) model for investigating the machinability of drilling AA6061 aluminium alloy with a micro-textured uncoated tool. The ANFIS model considers various input parameters such as spindle speed, feed rate, and Coolant type to predict the machinability performance of the drilling process. The results indicate that the ANFIS model is an effective tool for predicting the machinability performance of AA6061 during the drilling process. The model can help optimize the drilling process by identifying the best combination of input parameters that yield the desired machinability performance. This study demonstrates the potential of ANFIS models in the field of machining, particularly in the development of predictive models for optimizing machining processes.

Katta, Lakshmi Narasimhamu, Natarajan, Manikandan, Pasupuleti, Thejasree, Siva Rami Reddy, Narapureddy, Sivaiah, Potta

Items per page:

1 – 50 of 333