Browse Topic: Neural networks

Items (1,424)
This study develops a personalized driver model for expressway merging, embedding individual driving characteristics into automated longitudinal and lateral control via Long Short-Term Memory (LSTM) networks. Uniform assistance (Advanced Driver Assist System, ADAS) can feel uncomfortable when it does not match a driver’s style; we therefore target the merge maneuver—a safety-critical task requiring anticipation and timing—and test whether merging-related context improves model fidelity. Driving data were collected in a high-fidelity motion-base simulator across two merging scenarios (13 licensed drivers in total). Inputs comprised ego speed, Headway distance and relative speed to the lead vehicle, and geometric context variables (distance to the end of the acceleration lane and to the hard/soft nose); outputs were longitudinal and, in the cross-scenario study, lateral accelerations. Models were trained per driver and evaluated by root mean square error (RMSE). Including merging context
Shen, ShuncongHirose, Toshiya
This paper presents a hybrid optimization framework that integrates Multi-Physics Topology Optimization (MPTO) with a Neural Network–surrogated Design of Experiments (NN-DOE) to enable lightweight structural design while satisfying crashworthiness, durability, and noise, vibration, and harshness (NVH) requirements under practical casting and packaging constraints. In the proposed MPTO formulation, crash and durability performances are incorporated through equivalent static compliance measures, while NVH performance is assessed using a frequency-domain dynamic stiffness metric, allowing consistent evaluation of trade-offs among competing design requirements. The framework is first demonstrated using a mass-produced passenger-car lower control arm (LCA) as a benchmark component. In this application, MPTO achieves weight reduction under multi-physics objectives by removing non-load-bearing material. Results show that single-discipline optimization produces unbalanced topologies, while
Kim, HyosigSenkowski, AndresGona, KiranSaroha, LalitBoraiah, Mahesh
The tire model is a crucial component in the design of the K-characteristic of FSAE racing car suspensions, and directly influences the achievement of maximum cornering lateral force. Not only do the slip angle, vertical load, tire pressure, and camber angle affect the mechanical characteristics of the tire, but temperature is also an important influencing factor when FSAE vehicle tires operate at high speeds. However, the modeling process of traditional tire models based on temperature characteristics is often very complex. The FSAE tire test code (FSAE TTC) already has a large amount of official sample data, which provides a basis for data-driven neural network models. This study implemented a hybrid modeling methodology, constructing two cascaded feedforward neural networks that combine the physical interpretability of the Magic Formula tire model with the nonlinear approximation capabilities of neural networks. The first network model uses slip angle, vertical load, tire pressure
Liu, XiyuanWang, ShenyaoLi, MingyuanHuang, Jiayu
The Formula SAE (FSAE) race track is characterized by a large number of corners, making cornering performance a key factor affecting lap time. Based on the proportional control strategy for rear-wheel steering angles, this paper proposes a steering angle optimization method using a Temporal Convolutional Network (TCN). The TCN model features a faster training speed than traditional sequential neural networks. In addition, dilated convolutions enable an exponential expansion of the receptive field without increasing computational costs, making it particularly suitable for capturing the temporal dependencies of vehicle states. By processing vehicle dynamic parameters including front-wheel steering angle, vehicle speed, yaw rate and sideslip angle, the model calculates the correction value of the rear-wheel steering angle. This correction value is then superimposed with the reference value of the rear-wheel steering angle derived from the proportional control strategy, which serves as the
Liu, Xiyuan
Accurately modeling and controlling vehicle exhaust emissions, particularly during highly transient events such as rapid acceleration, is crucial for meeting stringent environmental regulations and optimizing modern powertrain systems. While conventional data-driven modeling methods, such as Multilayer Perceptrons (MLPs) and Long Short-Term Memory (LSTM) networks, have improved upon earlier phenomenological or physics-based models, they often struggle to capture the complex nonlinear dynamics of emission formation. These monolithic architectures attempt to learn from all available data, which increases their sensitivity to dataset variability. They often require increasingly deep and complex architectures to improve performance, thereby limiting their practical utility. This paper introduces a novel approach that overcomes these limitations by modeling emission dynamics in a structured latent space. Using a rich dataset combining real-world driving data from a Portable Emission
Sundaram, GaneshGehra, TobiasUlmen, JonasHeubaum, MirjanGörges, DanielGünthner, Michael
The performance of chassis suspension mechanisms critically affects vehicle handling, ride comfort, and safety. Implementing real-time health monitoring for chassis systems contributes to preventing severe consequences such as increased body roll or loss of handling stability caused by shock absorber softening or spring stiffness degradation under deteriorating operating conditions, while circumventing the substantial costs associated with professional facility-based chassis inspections. With the rapid development of sensing and data analytics technologies, data-driven approaches are increasingly used in health monitoring. This study aims to achieve online monitoring of chassis suspension performance degradation using a deep neural network (DNN). First, a half-car model incorporating both vertical and pitch motions was established to simulate bumpy road conditions, with the aim of constructing a dataset that includes key vehicle suspension parameters and vehicle states related to their
Liao, YinshengLei, YisongSu, AilinWang, ZhenfengShi, ShuaiZhang, LeiZhang, JunzhiMa, Changye
Drivers often interact with partial automation (SAE Level 2) systems, initiating transfer of control (TOC) either by handing control over to the automation or by taking it back. Accurately predicting these interactions may inform the design of future automation systems that adapt proactively to the operating context, enhance comfort, and ultimately may improve safety. We present a context-aware framework that generates a unified driver–vehicle–environment representation by fusing data from in-cabin video of the driver and of the forward roadway with vehicle kinematics, driver glance, and hands-on-wheel behaviors. This representation was encoded in a hierarchical Graph Neural Network that classified driver-initiated TOCs to: (i) Manual-to-automation and (ii) Automation-to-manual transitions and predicted time-to-TOC. Shapley-based explainable AI was used to quantify how the importance of behavioral, contextual, and kinematic cues evolved in the seconds preceding a TOC. Analysis of a
Zhao, ZhouqiaoGershon, Pnina
This paper explores the application of an Improved Enhanced-Boost Quasi-Z-Source Inverter in AC-connected extreme fast charging (XFC) stations for electric vehicles (EVs), aiming to reduce conversion stages and enhance system efficiency. AC-connected XFCs offer superior reliability compared to DC-connected systems due to better fault tolerance and reduced sensitivity to power fluctuations but traditionally suffer from increased complexity and reduced efficiency due to multiple conversion stages. The proposed inverter addresses this by combining DC-DC and DC-AC conversion into a single stage, simplifying the system, decreasing losses, and improving efficiency. Furthermore, this research investigates the use of Spiking Neural Networks (SNNs) for generating the precise pulse width modulation (PWM) signals required for the Quasi-Z-Source Inverter. SNNs offer potential advantages in terms of dynamic response and adaptability compared to traditional PWM techniques, allowing for optimized
Saliesh, DileepSanaboyina, PrudhviChhagar, RohnitsinghSatyanarayan, Swapna
The development of renewable and eco-friendly bio-lubricants can address the environmental challenges posed by petroleum-based lubricants. At the same time, it is possible to improve the tribological properties of lubricants through alternative sources. To overcome these problems, castor oil is a potential basis for bio-lubricants due to its high viscosity, natural lubricity, and biodegradability. In the current work, castor oil was chemically modified by the epoxidation process. This process has improved the tribological properties of castor oil through the epoxidation method. In this method, the presence of hydrogen peroxide acts as an oxidizing agent while sulfuric acid serves as a catalyst, converting the unsaturated double bonds present in the oil into oxirane rings. At the same time, this modification enhanced the thermal stability and tribological applications in harsh operating conditions. The tribological performance of the epoxidized castor oil, further reinforced with copper
Prabhakaran, JPali, Harveer SinghSingh, Nishant Kumar
This study presents a comparative assessment of two machine learning approaches for predicting aerodynamic drag coefficients (Cd) in automotive vehicle designs using data derived from computational fluid dynamics (CFD) simulations. The first approach employs traditional regression models trained on structured parametric data generated through controlled geometric variations, while the second approach integrates unstructured point-cloud geometry with structured metadata using a multi-modal deep learning framework. Both methods are evaluated within their respective contexts to understand their strengths, limitations and potential roles in automotive aerodynamic workflows. Rather than identifying a single best approach, the study highlights how these methods address different design needs and resource constraints, providing insights for future hybrid strategies that combine interpretability with geometric sensitivity. The work aims to establish a foundation for data-driven aerodynamic
Kumar, GauravKhanna, Susheel
The push for vehicle development through virtual prototyping and testing in motorsports highlights the critical challenge of tire model selection and calibration, especially when vehicle dynamics must be accurately captured. The calibration process for tire models such as the Pacejka Magic Formula (MF) relies on parameter identification and experimental data fitting. While optimization algorithms have been implemented to calibrate tire models, few studies explore the effects of parameter selection on overall vehicle performance, complicating prioritization for the vehicle’s modeling and simulation strategy. To bridge this gap, this paper leverages optimal control methods to quantify how the variability of MF tire model parameters propagates to the overall vehicle model and impacts lap time prediction accuracy. To achieve this, a subset of parameters critical to combined slip of the MF tire model are varied through a Design of Experiments (DOE). These variations are executed on a flat
Zarate Villazon, Angel M.Brown, IanBalchanos, MichaelMavris, Dimitri
To effectively improve the performance of chassis control of distributed drive intelligent electric vehicles (EVs) under difference road conditions, especially in combing road information and chassis control for improving road handling and ride comfort, is a challenging task for the distributed drive intelligent EVs. Simultaneously, inaccurate chassis control and uncertainty with system input, are always existing, e.g., 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 control strategy of distributed drive intelligent EVs become a hot topic in both academia and industry. To issue the above mentioned, an adaptive torque vector hierarchical controller based on road level and adhesion is proposed, which optimizes the comprehensive. First, combined with the characteristic of the unbalance dynamic force caused by the air gap between the stator and the rotor of the in-wheel motor, a
Wang, ZhenfengZhao, GaomingZhang, ZhijieZhou, ZitaoHuang, TaishuoMa, Changye
Accurate prediction of equilibrium combustion products and thermodynamic properties is essential for optimizing engine performance, enhancing combustion efficiency, and reducing emissions in diesel-powered systems. Traditional methods for combustion modeling often involve solving complex chemical equilibrium equations or thermodynamic relations, which could be computationally expensive and time-consuming. In this study, we present a data-driven approach using a deep neural network (DNN) model to predict the equilibrium combustion products and key thermodynamic characteristics of diesel under varying thermodynamic conditions. The proposed DNN model is trained on a comprehensive dataset generated from equilibrium calculations. The inputs include pressure, temperature, and equivalence ratio, covering a relatively wide range to encompass diesel equilibrium combustion under various conditions. Outputs are equilibrium combustion products and thermodynamic properties, including enthalpy
Ji, HuangchangWang, KaiGuo, ZhefengHan, YangLee, Timothy
Traffic roundabouts, as complex and safety-critical road scenarios, present significant challenges for autonomous vehicles. In particular, predicting and managing dilemma zone (DZ) encounters at roundabout intersections remains a pivotal concern. This paper introduces an AI-driven system that leverages advanced trajectory forecasting to anticipate DZ events, specifically within traffic roundabouts. At the core of our framework is a modular, graph-structured recurrent architecture powered by graph neural networks (GNNs). By modeling agent interactions as a dynamic graph, our approach integrates heterogeneous data sources - including semantic maps - while capturing agent dynamics with high fidelity. This GNN-based forecasting model enables accurate prediction of DZ events and supports safer, data-driven traffic management decisions for both autonomous and human-driven vehicles. We validate our system on a real-world dataset of roundabout intersections, where it achieves high precision
Lu, DuoSatish, ManthanFarhadi, MohammadChakravarthi, BharateshYang, Yezhou
Hybrid mining trucks, as core equipment for mine transportation, face high energy consumption and significant fluctuations in power demand during cyclic operations due to prolonged exposure to demanding operating conditions characterized by heavy loads and variable working conditions. To address the issues of high energy consumption and significant fluctuations in power demand during the cyclic operation of mining trucks, this paper proposes a hybrid mining truck energy management strategy based on global SOC (State of Charge) planning and neural network optimization control. First, a powertrain model was developed for a typical operating cycle of a hybrid mining truck, and its accuracy was validated by comparing it with experimental data. Using dynamic programming algorithms to plan the SOC for single-cycle operations provides a rational reference for energy allocation across different operational phases of mining trucks during a single cycle. Next, using the powerful nonlinear
Yang, JianyuZhao, ZhiguoChen, HuiyongLi, TaoZhuang, WenyuShen, PeihongTang, Peng
Fused filament fabrication (FFF) has gained popularity in recent years because it can produce prototypes and functional components with complex geometry. Because of inherent process variability, the components often exhibit defects such as warping, layer delamination, voids, and poor surface finish, as well as issues related to variable material strength and anisotropy. In-situ monitoring (ISM) of the FFF process is a promising technique to predict part performance, which in turn can support accept or reject decisions for printed parts. This paper proposes a framework for incorporating ISM-generated information, with a particular focus on infrared (IR) image analysis for this purpose. IR camera images, in conjunction with numerical features such as infill pattern and extruder nozzle temperature, serve as an input to a multimodal deep learning (MDL) model that predicts the mechanical performance of printed parts. In the framework, convolutional neural nets process image inputs, while a
Mollan, CalahanKulkarni, SaurabhMalik, Ali AhmadPatterson, Albert E.Pandey, Vijitashwa
Predicting battery self-discharge across wide temperature ranges and extended durations remains a significant challenge due to the scarcity of physical test data, which is typically limited to a few temperature points and short observation windows. This limitation complicates generalization and increases the risk of inaccurate extrapolation. To address this, the paper introduces a machine learning–based framework designed to predict self-discharge behavior under diverse thermal conditions and longtime horizons. Multiple modeling strategies are examined, including feedforward neural networks, long short-term memory (LSTM) architectures, synthetic data generation, and physics-informed integration of governing equations. Particular emphasis is placed on hybrid and physics-regularized models that embed first-principles relationships to guide extrapolation beyond the observed data domain. This approach mitigates the inherent instability and potential errors associated with purely data
Chavare, SudeepZeng, YangbingMuppana, Sai SiddharthaMiao, YongXu, Simon
Crashworthiness assessment is a critical aspect of automotive design, traditionally relying on high-fidelity finite element (FE) simulations that are computationally expensive and time-consuming. This work presents an exploratory comparative study on developing machine learning-based surrogate models for efficient prediction of structural deformation in crash scenarios using the NVIDIA PhysicsNeMo framework. Given the limited prior work applying machine learning to structural crash dynamics, the primary contribution lies in demonstrating the feasibility and engineering utility of the various modeling approaches explored in this work. We investigate two state-of-the-art neural network architectures for modeling crash dynamics: MeshGraphNet, a graph neural network that is widely employed in physics-based simulations, and Transolver, a transformer-based architecture with a physics-aware attention mechanism designed to maintain linear computational complexity with respect to geometric
Nabian, Mohammad AminChavare, SudeepAkhare, DeepakRanade, RishikeshCherukuri, RamTadepalli, Srinivas
Calibration is a major resource bottleneck and source of risk in powertrain technology development. A promising alternative to the typical design-of-experiments (DoE) approach is the use of a ‘Non-Dominated Sorting Genetic Algorithm’ (NSGA) calibration method, where an iterative process is used to directly identify the Pareto Fronts between performance metrics, for example, net mean effective pressure (NMEP) and NOx emission. The goal of the present work was to develop and demonstrate a fully ‘online’ combustion system calibration method based on an NSGA, where the algorithm operates directly on experimental data rather than empirical models as is typical in the literature. This was completed by first designing an optimal NSGA for combustion system calibration and then demonstrating its use for an experimental combustion system calibration on a single cylinder gasoline engine at one operating condition. Results from the design process here indicate that ‘online’ NSGAs have a strong
Mansfield, Andrew
This study presents an image-derived multimodal AI framework for early-stage tire noise evaluation. The proposed model requires only multi-angle photographs captured by a standard smartphone and basic tire specifications. From these images, scaled three-dimensional (3D) meshes and fixed-view depth maps are reconstructed and combined with numerical parameters within a neural network architecture. Three input branches—a point-cloud–gradient branch, a depth-map convolutional neural network (CNN) branch, and a specification multi-layer perceptron (MLP) branch—are jointly trained using a composite loss that integrates frequency-weighted mean squared error (MSE), spectral cosine similarity, FFT-domain consistency, and A-weighted sound-level terms. A dataset of 28 tires, spanning passenger, SUV, and pickup applications for both battery electric vehicles (BEVs) and internal combustion engine (ICE) vehicles, was evaluated using leave-one-out (LOO) cross-validation. The model achieved a mean
Shao, GuangxinShopoff, ScottFranklin, Nicholas
Accurate torque-trace reproduction on regulatory drive cycles is central to heavy-duty diesel certification and development testing. Conventional controllers such as Proportional Integral Derivative (PID or PI) can be enhanced with gain scheduling and feedforward (FF) maps to satisfy requirements but require extensive calibration and are sensitive to nonlinearities and delay. This paper evaluates a data-driven control framework comprising a recurrent neural surrogate of engine torque (specifically an LSTM – long short-term memory) trained on engine/dynamometer data and a reinforcement learning (RL) policy trained using this surrogate (“world model”) to track requested torque while regularizing control effort. The RL policy (specifically TD3 – twin delayed deep deterministic) is benchmarked against tuned PID and PID+FF baselines on the Environmental Protection Agency’s Heavy Duty Federal Test Procedure (HD-FTP) segments using EPA regression criteria (slope, |intercept|, R2) and tracking
Cook, JamesPuzinauskas, PauliusBittle, JoshuaHall, Spencer
This paper addresses the changes in engine emissions due to in-use component changes through the synergistic application of predictive control, machine learning, and onboard adaptation. In particular, we consider an adaptive economic Model Predictive Control (eMPC) strategy to mitigate the effects of performance drift on Nitrogen Oxides (NOx) and Soot emissions from compression ignition (diesel) engines. A performance drift block, which applies a multiplier and offset to nominal emissions, is integrated with a high-fidelity Neural Network (NN) plant model to simulate these characteristic changes. To counteract variability, two online adaptation methods are integrated within the eMPC framework: One is based on Recursive Least Squares (RLS) and another on a continuously updated online NN. The proposed control architecture is validated through simulations over standard transient cycles. Results demonstrate that while the rate-based eMPC possesses inherent robustness to performance drift
Zhang, JiadiLi, XiaoKolmanovsky, IlyaTsutsumi, MunecikaNakada, Hayato
Autonomous vehicle navigation requires accurate prediction of driving path curvature to ensure smooth and safe trajectory planning. This paper presents a novel approach to curvature prediction using deep neural networks trained on GPS-derived ground truth data, rather than model predictions, providing a more accurate training signal that reflects actual vehicle motion. We develop a multi-modal neural network architecture with temporal GRU encoders that processes vision features, driver intent signals, historical curvature, and vehicle state parameters to predict curvature. A key innovation is the use of GPS-based actual curvature measurements computed from vehicle motion data (κ = ωz/v) as training supervision, enabling the model to learn from real-world driving patterns. The model is trained on 5,322 samples from real-world driving data collected on The University of Oklahoma’s Norman Campus using a Comma 3X device and a 2025 Nissan Leaf electric vehicle. Experimental results
Hajnorouzali, YasamanWang, HanchenLi, TaozheBurch, CollinLee, VictoriaTan, LinArjmandzadeh, ZibaXu, Bin
High thermal loads on brake systems during extended descents followed by vehicle soak pose significant safety and durability risks. Excessive rotor or fluid temperatures can cause loss of braking efficacy, fluid degradation or evaporation, thermal fade, and accelerated component wear. This study uses time-history data of brake-disc and fluid temperatures which were collected during controlled hill-descent events with subsequent soak periods, where the vehicle is parked in a wind protected area. Besides the rotor and brake fluid temperatures, environmental conditions were recorded (ambient temperature, humidity, wind speed and direction) and the vehicle and brake specifications are known (rotor/caliper geometry, pad material, vehicle aerodynamic configuration and mass). 126 test runs from a dedicated vehicle program are used, each providing time-history records that form the basis of our analysis. From these records we extract phase-specific samples (descent and soak phase) and engineer
Poojari, Uday KumarWestphalen, JanVenugopal, Narayana
Accurate and rapid remaining useful life (RUL) prediction of batteries under various extreme conditions is crucial for battery management systems. However, existing methods often face challenges such as limited datasets under extreme conditions, high model complexity, and weak interpretability. Therefore, this paper proposes a hybrid framework based on pruning domain-adaptive convolutional neural networks (CNN) and long short-term memory (LSTM) to study RUL prediction under different fast-charging conditions using the MIT dataset. First, four voltage-related feature matrices are extracted. Using maximum mean discrepancy (MMD) constraints, the CNN-LSTM is trained with source domain and limited target domain data to align distributions. Neuron pruning is then applied to the fully connected layer to compress the model. Results demonstrate that under sparse target domain data, the domain adaptation approach achieves significantly lower prediction errors than fine-tuning. The pruned model
Huang, MingyueChen, HongxuLuan, Weiling
For the safe and reliable deployment of lithium-ion batteries, accurate state of health (SOH) estimation is paramount. However, most existing data-driven methodologies depend exclusively on single-modal data, such as voltage-capacity or incremental capacity (IC) curves. Such limited data frequently fails to offer a holistic understanding of the complex battery degradation process. To address this limitation, this paper proposes a novel multi-modal feature fusion network. This network can effectively combine three different but complementary data modalities: historical point features, voltage-capacity and IC sequence features, as well as degraded image features. To this end, the framework incorporates a one-dimensional convolutional neural network (1D-CNN) for analyzing point features, leverages a Transformer encoder to process sequence features, and employs ResNet for identifying spatio-temporal patterns in degraded images. These heterogeneous features are then collaboratively
Li, XiaobinHe, NingYang, Fangfang
With the rapid expansion of global electric vehicles (EVs) deployment, the echelon utilization of retired lithium-ion batteries (LIBs) has emerged as a critical issue. Although these batteries typically retain over 70% of their initial capacity and remain suitable for stationary energy storage systems, the substantial variability in aging states poses safety risks. Conventional capacity estimation methods are often time-intensive and costly, while data-driven approaches face challenges from complex degradation mechanisms and limited historical usage data. This study uses the electrochemical impedance spectroscopy (EIS) method to create a model that estimates the capacity of retired batteries. EIS offers fast measurement, requires no historical cycling data, and provides rich state-of-health (SOH) information. An EIS dataset was acquired from 18650-type LFP and NCM cells aged under multiple cycling conditions. The real part and magnitude of the impedance spectra were extracted as input
Hou, ZhengyuLuan, WeilingSun, ChangzhengChen, Ying
The State of Charge (SOC) is a key parameter for measuring the remaining capacity of new energy vehicle batteries. It not only directly reflects the driving range of the vehicle but also plays an indispensable role in ensuring operational safety and extending battery lifespan. Accurate estimation of SOC provides strong support for the safe and reliable operation of electric vehicles. During the charging and discharging process of lithium iron phosphate batteries, the intercalation and deintercalation of lithium ions cause deformation of the electrode's lattice structure, leading to the expansion and contraction of the electrode volume. This, in turn, exerts stress on the limited internal space of the battery, which is mainly manifested as changes in battery pressure monitored by sensors. To address the issues of insufficient information and low estimation accuracy associated with the use of electrical signals in traditional data-driven methods, this study introduces pressure
Tian, JieDu, JinqiaoRao, BoLai, TiandeDong, BoyiJiang, Jiuchun
This research paper provides a comprehensive study on how Artificial Neural Networks (ANNs) can be deployed to predict the stiffness characteristics of a cantilever beam with a crack of various depths and positions. The most destructive source of failure is considered to be vibration, so the major focus of this paper will be on how the cracks affect the modal stiffness. This study has various applications, such as airplane wings, bridges, stadiums, and arenas. A common research gap was noticed amongst the existing studies; the position of the cracks in the cantilever wasn’t considered, but this paper discusses how the location of cracks severely affects the dynamic behaviour of the cantilever. This study was done by carrying out modal analysis on a cantilever of the same dimensions with different crack configurations. Various crack dimensions and orientations were analysed to understand the effects of the crack on the dynamic behaviour of the cantilever. From the modal analysis results
SB, HarshiniRajkumar, ManjariR, KrithikaK, AnushaK, DivyaBhaskara Rao, Lokavarapu
This study presents the design and implementation of an advanced IoT-enabled, cloud-integrated smart parking system, engineered to address the critical challenges of urban parking management and next-generation mobility. The proposed architecture utilizes a distributed network of ultrasonic and infrared occupancy sensors, each interfaced with a NodeMCU ESP8266 microcontroller, to enable precise, real-time monitoring of individual parking spaces. Sensor data is transmitted via secure MQTT protocol to a centralized cloud platform (AWS IoT Core), where it is aggregated, timestamped, and stored in a NoSQL database for scalable, low-latency access. A key innovation of this system is the integration of artificial intelligence (AI)-based space optimization algorithms, leveraging historical occupancy patterns and predictive analytics (using LSTM neural networks) to dynamically allocate parking spaces and forecast demand. The cloud platform exposes RESTful APIs, facilitating seamless
Deepan Kumar, SadhasivamS, BalakrishnanDhayaneethi, SivajiBoobalan, SaravananAbdul Rahim, Mohamed ArshadS, ManikandanR, JamunaL, Rishi Kannan
The landing gear, as a crucial component of an aircraft, is pivotal for maintaining the safety and reliability of air travel. This study introduces a data-driven structural optimization method aimed at mitigating the peak strain on the landing gear’s rocker arm. The initial phase involves selecting nine design variables for parametric modeling to generate an initial dataset. Subsequently, the Maximum Information Coefficient (MIC) technique is used to conduct a parameter sensitivity analysis, enabling the identification and elimination of variables with minimal influence. A comparative analysis between the Genetic Algorithm–Backpropagation Neural Network (GA-BPNN) and BPNN reveals that GA-BPNN has a superior fitting capability on the enhanced dataset. By applying Particle Swarm Optimization (PSO), the optimal solution for GA-BPNN is identified. The implementation of this optimized method results in a 38.16% reduction in peak strain, validating its feasibility and reliability in
Chen, HuShi, ShiWang, MengFang, XingboWei, XiaohuiNie, Hong
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
Qi, ZhenliangLiu, PingDuan, HaotianZhou, ZilongHuang, Haibo
This paper presents the development and implementation of a digital twin (DT) for the suspension assembly of automotive vehicles—an essential subsystem for assessing vehicle performance, durability, ride comfort, and safety. The digital twin, a high-fidelity virtual replica of the physical suspension system, is constructed using advanced simulation methodologies, including Finite Element Analysis (FEA), and enriched through continuous integration of empirical test data. Leveraging machine learning techniques, particularly Artificial Neural Networks (ANNs), the DT evolves into a dynamic and predictive model capable of accurately simulating the behaviour of the physical system under diverse operational conditions. The primary aim of this study is to enhance the precision and efficiency of suspension testing by enabling predictive maintenance, real-time system monitoring, and intelligent optimization of test parameters. The digital twin facilitates early detection of potential failures
Sonavane, PravinkumarPatil, Amol
A passenger vehicle's front-end structure's structural integrity and crashworthiness are crucial to ensure compliance with various frontal impact safety standards (such as those set by Euro NCAP & IIHS). For a new front-end architecture, design targets must be defined at a component level for crush cans, longitudinal, bumper beam, subframe, suspension tower and backup structure. The traditional process of defining these targets involves multiple sensitivity studies in CAE. This paper explores the implementation of Physics-Informed Neural Networks (PINNs) in component-level target setting. PINNs integrate the governing equations into neural network training, enabling data-driven models to adhere to fundamental mechanical principles. The underlying physics in our model is based upon a force scheme of a full-frontal impact. A force scheme is a one-dimensional representation of the front-end structure components that simplifies a crash event's complex physics. It uses the dimensional and
Gupta, IshanBhatnagar, AbhinavKumar, Ayush
In automotive engineering, understanding driving behavior is crucial for decision on specifications of future system designs. This study introduces an innovative approach to modeling driving behavior using Graph Attention Networks (GATs). By leveraging spatial relationships encoded in H3 indices, a graph-based model constructed, which captures dependencies between various vehicle operational parameters and their operational regions using H3 indices. The model utilizes CAN signal features such as speed, fuel efficiency, engine temperature, and categorical identifiers of vehicle type and sub-type. Additionally, regional indices are incorporated to enrich the contextual information. The GAT model processes these heterogeneous features, learning to identify patterns indicative of driving behavior. This approach offers several significant advantages. Firstly, it enhances the accuracy of driving behavior modeling by effectively capturing the complex spatial and operational dependencies
Salunke, Omkar
Functional Mock-up Units (FMUs) have become a standard for enabling co-simulation and model exchange in vehicle development. However, traditional FMUs derived from physics-based models can be computationally intensive, especially in scenarios requiring real-time performance. This paper presents a Python-based approach for developing a Neural Network (NN) based FMU using deep learning techniques, aimed at accelerating vehicle simulation while ensuring high fidelity. The neural network was trained on vehicle simulation data and trained using Python frameworks such as TensorFlow. The trained model was then exported into FMU, enabling seamless integration with FMI-compliant platforms. The NN FMU replicates the thermal behavior of a vehicle with high accuracy while offering a significant reduction in computational load. Benchmark comparisons with a physical thermal model demonstrate that the proposed solution provides both efficiency and reliability across various driving conditions. The
Srinivasan, RangarajanAshok Bharde, PoojaMhetras, MayurChehire, Marc
O-rings play a critical role in ensuring leak-proof seals in a wide range of engineering systems. Accurate prediction of their compression and relaxation behavior under various material and geometric configurations is essential for optimal design and reliability. This study presents an analysis of machine learning techniques to predict two key performance outputs, compression force and relaxation force (after 10 minutes) trained on computer-aided engineering (CAE) simulation data. The experimental setup was represented in CAE simulation and the results were compared with experimental data conducted at ZF test facilities. Simulation results correlated well with the experimental data (deviation was less than the 5%). To create a dataset for training machine learning (ML) models, realistic ranges for the input parameters such as hardness and geometrical parameters were determined, and simulation data were generated using design of experiments (DOE). Multiple ML models were developed and
Kosgi, DurgaprasadAlva, P PanchamDangeti, VenkataKrishna Pavan
Addressing climate issues is a key aspect of good global governance today. A key aspect of managing the threats caused to the environment around is to ensure a sustainable transportation system so that humans exist in peace with nature. According to sources, in 2020 alone, cars accounted for approximately 23% of global CO2 emissions. In addition, they also emit dangerous pollutants thus damaging the ecosystem. To keep pollutants in check there are emission level testing strategies in place in each country. However, we can do better for a sustainable future. On one hand, the huge volume of vehicles around the world makes it an excellent choice and source for a vast emission level dataset comprising of input features as well as the target variable representing the emission band of the vehicle. In addition to the big data available as mentioned above, major advancements in the machine learning algorithms are done today. The advent of algorithms such as Artificial Neural Networks (ANN) has
Sridhar, SriramAswani, Shelendra
In a conventional powertrain driven by Internal combustion (IC) engines, various sensors are used to monitor engine performance and emissions. Along with physical sensors, virtual sensors or modelled values of key parameters play an important role for enabling various diagnostics strategies and engine monitoring. Conventional strategies for modelling incorporate the use of regression models, map-based models and physics-based models which have few drawbacks in terms of accuracy and model calibrations efforts. Data driven models or neural networks have fairly better accuracy and reliability for estimating complex parameters. Representing the neural network with a mathematics-based model would help to eliminate drawbacks associated with conventional modelling approach. The proposed methodology uses artificial intelligence technique called artificial neural network (ANN) for estimation of temperature at turbine inlet (TTI) in typical diesel engine. The data driven model is built in Python
Jagtap, Virendra ShashikantShejwal, SanketMitra, Partha
The automotive and off-road industries are heavily investing in R&D to improve both physical and virtual verification and validation techniques. Recent software and hardware advancements have extended these techniques from simple component evaluations to complex system assessments such as involving multi-physics scenarios. Despite the benefits of virtual validation tools like structural analysis and CFD, they often come with high development costs, particularly in CFD applications. Virtual verification methodology, especially when combined with data science, offer significant advantages over traditional physical methods by enhancing CAE efficiency and reducing resource consumption which can greatly improve product design and validation efficiency across many industries. The success of machine learning applications depends on effective data processing, adequate computational resources, and the right algorithm selection. Key machine learning techniques impacting the CFD field include
Jadhav, MitaliKumbhar, AppasoTirumala, BhaskarNisha, Kumari
The automotive industry is rapidly transitioning towards Industry 4.0, transforming vehicle manufacturing. To achieve a lower carbon footprint, it is crucial to minimize raw material wastage and energy consumption. Reducing component wastage, lead time, and automating gear manufacturing are key areas. Gear micro-geometry inspection is vital, as variations affect service life and NVH (Noise, Vibration, Harshness). Despite standards for permissible errors, manual evaluation of gear microgeometry inspection is often needed. This subjective evaluation approach will have a possibility that a gear with undesired variations gets assembled into the product. These issues can be detected during NVH testing, leading to replacement of part and re-assembly thus increasing lead time. This generates a need for an automated system which could reduce the human intervention and perform gear inspection. The research aims to develop a deep learning-based model to eliminate the ambiguity of manual
Ramakrishnan, Gowtham RajBaheti, PalashPR, VaidyanathanDurgude, RanjitBathla, ArchanaR, GreeshmitaV, Rangarajan
The main focus of this paper is to create a more efficient regenerative braking control strategy for electric commercial buses operating under Indian road conditions. The strategy uses Artificial Neural Networks (ANNs) to optimize regenerative braking process. Regenerative braking helps to recover energy that would otherwise be lost during braking and convert it back into usable power for the vehicle. The challenge is to design a system that works effectively on the diverse and often challenging road conditions found in India, such as varying gradients, traffic patterns, and road surface types. This study begins by collecting data (which includes vehicle speed, traffic condition, etc.) from real-world driving conditions and aims to train an Artificial Neural Network (ANN) using a large set of driving data which is collected under various conditions to predict the most efficient regenerative braking settings for different driving scenarios. This research brings a new approach to the
Saurabh, SaurabhBhardwaj, RohitPatil, NikhilGadve, DhananjayAmancharla, Naga Chaithanya
Artificial Intelligence (AI) is radically transforming the automotive industry, particularly in the domain of passenger vehicles where personalization, safety, diagnostics, and efficiency. This paper presents an exploration of AI/ML applications through quadrant of the key pillars: Customer Experience (CX), Vehicle Diagnostics, Lifecycle Management, and Connected Technologies. Through detailed use cases, including AI-powered active suspension systems, intelligent fault code prioritization, and eco-routing strategies, we demonstrate how AI models such as machine learning, deep learning, and computer vision are reshaping both the user experience and engineering workflow of modern electric vehicles (EVs). This paper combines simulations, pseudo-algorithms and data-centric examples of the combined depth of functionality and deployment readiness of these technologies. In addition to technical effectiveness, the paper also discusses the challenges at field level in adopting AI at scale i.e
Hazra, SandipTangadpalliwar, SonaliKhan, Arkadip
The article is devoted to a comprehensive analysis of the digital transformation of education using the example of a project to train engineering personnel for the innovative transport industry in Russia. Special attention is paid to the introduction of hybrid formats, digital platforms, inclusivity, issues of digital inequality, as well as the experience of the National Research Center of the Russian Federation FSUE NAMI and interaction with leading universities in the country. A comparative analysis with foreign initiatives, including modern AI solutions for inclusive education, is presented, as well as the impact of the project to create educational and methodological centers on the professional motivation of teachers.
Shishanov, SergeiKurmaev, RinatRevenok, Svetlana
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
Chen, YanboChen, JiaqiYu, HuilongXi, Junqiang
Distributed-drive electric vehicles (DDEVs) significantly enhance off-road maneuverability but suffer from compromised high-speed stability and robustness. This research introduces a front-centralized and rear-distributed (FCRD) architecture that synergistically leverages the advantages of each configuration. The electric-drive-wheel (EDW) on the rear suspension can provide three working modes: (a) Drive-connected mode, (b) Drive-disconnected mode, (c) Brake mode. It is the key actuator for vehicle mode-switching, which supports the vehicle with three driving modes: (a) DDEV, (b) front-wheel drive (FWD), (c) all-wheel drive (AWD). A hierarchical control architecture employs the upper-layer controller with Back Propagation Neural Network (BPNN) for mode identification and decision-making. The lower-layer controller enables the intelligent torque distribution and collaborative control of the motors. The control strategy is pre-trained in the VCU (vehicle control unit) with off-line data
Ding, XiaoyuChen, XinboWang, WeiZhang, JiantaoKong, Aijing
Items per page:
1 – 50 of 1424