This research, path planning optimization of the deep Q-network (DQN) algorithm is enhanced through integration with the enhanced deep Q-network (EDQN) for mobile robot (MR) navigation in specific scenarios. This approach involves multiple objectives, such as minimizing path distance, energy consumption, and obstacle avoidance. The proposed algorithm has been adapted to operate MRs in both 10 × 10 and 15 × 15 grid-mapped environments, accommodating both static and dynamic settings. The main objective of the algorithm is to determine the most efficient, optimized path to the target destination. A learning-based MR was utilized to experimentally validate the EDQN methodology, confirming its effectiveness. For robot trajectory tasks, this research demonstrates that the EDQN approach enables collision avoidance, optimizes path efficiency, and achieves practical applicability. Training episodes were implemented over 3000 iterations. In comparison to traditional algorithms such as A*, GA

Arumugam, Vengatesan, Alagumalai, Vasudevan, Rajendran, Sundarakannan

Assessing Road Load Predictions: A Comprehensive Review and Comparative Analysis of Real-World versus Numerical Simulation

2024-36-0157

12/20/2024

Road loads, encompassing aerodynamic drag, rolling resistance, and gravitational effects, significantly impact vehicle design and performance by influencing factors such as fuel efficiency, handling, and overall driving experience. While traditional coastdown tests are commonly used to measure road loads, they can be influenced by environmental variations and are costly. Consequently, numerical simulations play a pivotal role in predicting and optimizing vehicle performance in a cost-effective manner. This article aims to conduct a literature review on road loads and their effects on vehicle performance, leveraging experimental data from past studies from other researchers to establish correlations between measured road loads and existing mathematical models. By validating these correlations using real-world measurements, this study contributes to refining predictive models used in automotive design and analysis. The simulations in this study, utilizing five distinct empirical

Pereira, Leonardo Pedreira, Braga, Sérgio Leal

Optimizing Side Impact with Metaheuristics coupled with Penalty Methods

2024-36-0036

12/20/2024

In the automotive industry, a good vehicle is one that not only provides comfort and adequate on-road performance but also ensures safety for its users. Therefore, various standards have been created to qualify and ensure that cars meet minimum requirements. Assays include frontal and side impact tests. However, physical tests end up being costly if performed frequently, and thus, increasing the correlation between these and computational simulations has been explored in recent years. Within the computational scope, given the nonlinear nature of the functions involved in such studies, the use of metaheuristics (MH) with constraint handling techniques (CHT) has been employed to obtain better results for such scenarios. In this work, three MH algorithms are used: Archimedean Optimization (AOA), Sine-Cosine Algorithm (SCA), and Dung Beetle Optimization (DBO). They are coupled with CHTs of the penalty methods (PM) type in their most basic character, such as Static Penalty Method (SPM

Souza Silva, Paulo, Dezan, Daniel Jonas, Ferreira, Wallace Gusmão

DOE Tool Applied on a Skid Plate: A Case Study

2024-36-0090

12/20/2024

In recent years, the automotive industry has been undergoing constant evolution, and to keep up with market trends, it’s necessary to seek better performance in the shortest time possible. Therefore, CAE (Computer Aided Engineering) becomes one of the most efficient tools for this purpose, as it can predict failures and/or improvements virtually before the start of tooling manufacturing. Thus, optimization, a process in which the best value of a parameter is obtained, becomes essential in the CAE field. In this work, Design of Experiments (DOE) will be applied, a methodology that, using applied statistics, plans, conducts, analyzes, and interprets controlled tests, evaluating predefined parameters from different areas. A light vehicle skid plate will be the case study, impacting disciplines such as durability, NVH (Noise, Vibration and Harshness), and aerodynamics, in virtual analyses such as stiffness, vibration modes, and water fording. Using the resources provided by Renault, this

dos Santos Magalhães, Daniella Fernanda, Moura, Vitor Loic, Braga Junior, Francisco Estevanato, Andrade Barbosa, Samuel França Moura, Theulen Mueller, André Marcelo

Optimization of a 2-D Multi-Element Rear Wing on a Formula 1 Car

2024-36-0103

12/20/2024

The aerodynamic force produced by external flows over two-dimensional bodies is typically decomposed into two components: lift and drag. In race cars, the lift is known as downforce and it is responsible for increasing tire grip, thereby enhancing traction and cornering ability. Drag acts in the direction opposite to the car’s motion, reducing its acceleration and top speed. The primary challenge for aerodynamicists is to design a vehicle capable of producing high downforce with low drag. This study aims to optimize the shape of a multi-element rear wing profile of a Formula 1 car, achieving an optimal configuration under specific prescribed conditions. The scope of this work was limited to a 2-D model of a rear wing composed of two 4-digit NACA airfoils. Ten control parameters were used in the optimization process: three to describe each isolated profile, two to describe their relative position, and two to describe the angles of attack of each profile. An optimization cycle by finite

Souza Dourado, Guilherme, Hayashi, Marcelo Tanaka

Multi Criteria Analysis Selection of Cylindrical Spur Gears

2024-36-0117

12/20/2024

Organizations need to maintain their processes at high levels of efficiency to be competitive, asset management and industrial maintenance are extremely important to obtain positive results in optimizing operating costs, saving energy resources, reduction of environmental impacts among other characteristics that are considered differential for organizations. In this scenario, methods are increasingly being sought to assist managers in decision-making processes that contain several alternatives and selection criteria involved. The AHP and TOPSIS methods have been widely associated with prioritization studies, cost evaluation, resource selection, suppliers, among others. Thus, the selection of equipment and industrial elements can be evaluated by means of multicriteria decision methods where the criteria considered important by specialists in the area are inserted into the model. The objective of this article was to present a selection process for spur gears based on stress analysis and

de Oliveira, Geraldo Cesar Rosario, de Oliveira, Vania Aparecida Rosario, Silva, Carlos Alexis Alvarado, Guidi, Erick Siqueira, Salomon, Valério Antonio Pamplona, Rosado, Victor Orlando Gamarra, de Azevedo Silva, Fernando

SAE TOMORROW TODAY: Scaling Connected Vehicles with Over-The-Air Updates

1349212/18/2024

As the automotive world shifts toward fully software-defined vehicles (SDVs), many OEMs are hesitant to embrace a consumer-driven model for over-the-air (OTA) updates. Enter Sibros, a company offering holistic OTA software that enables automakers to achieve scalable, software-defined mobility. By providing AI-powered insights that deliver continuous product and service enhancements, OEMs can harness Sibros' single no-code platform to monitor, control and optimize SDVs, thus accelerating time-to-market, reducing code defects and enabling hundreds of connected vehicle use cases at global scale. This presents unique value for consumers, OEMs, commercial fleet operators, and even off-road sectors like agriculture and mining. To learn more, we sat down with Hemant Sikaria, CEO & Co-Founder, Sibros, to discuss the impact of his company's groundbreaking technology, how insurance and regulation come into play, and the importance of robust security measures to ensure the responsible growth of

Hineman, Marcie

Modeling and Optimization of Regenerative MacPherson Strut

10-09-01-0005

12/16/2024

Throughout the vehicles industry and electrification, vehicle ride comfort, road holding, and fuel/charge economy have always been important considerations for the design and development of shock absorbers. Vehicle suspension is one of the oscillating power dissipation sources in which the undesired mechanical energy is dissipated into heat waste. Therefore, in this study a regenerative MacPherson strut is modeled and validated to investigate the vehicle vertical dynamics performance as well as the harvestable power that can be used to charge batteries or power vehicle electrical loads. The optimal design parameters of the regenerative MacPherson strut (RE.M.S) is obtained by using multi-object genetic algorithm (MOGA) optimization for a better trade-off between regenerated power, ride comfort, and road holding. The results showed that RE.M.S can function as a semi-active shock absorber as change of duty cycle of charging circuit. Furthermore, the optimal selection of the design

Hegazy, Ahmed H.A., Kaldas, Mina M., Soliman, Aref M.A., Huzayyin, A.S.

MFFormer3D: A Multi-frame Fusion Transformer Utilizing Object Queries for Enhanced 3D Detection

2024-01-7043

12/13/2024

3D object detection based on the point cloud is a critical technology for environmental perception in autonomous driving systems. However, it has long faced dual challenges of accuracy and efficiency due to the sparsity and irregularity of point cloud data and the complicated driving scenarios. This paper proposes a novel multi-frame fusion 3D object detection algorithm, MFFormer3D, embedding object queries. The method first removes ground points from the raw point cloud to reduce subsequent computational load. It then employs Spatially Grouped Sparse Convolution Feature Extraction Layer (SGSC-FEL) to optimize the backbone network for feature extraction. Subsequently, we introduce a Cross-frame Object Query Filter (COQF) mechanism for efficient multi-frame fusion and a Motion Correction Module (MCM) to compensate for ego-motion effects. Experiments on the nuScenes dataset demonstrate that MFFormer3D outperforms the baseline method by 2.25% in NDS and 7.73% in mAP while maintaining an

Cheng, Shuai, Zhang, Yin, Gao, Di, Li, Jingyao, Wang, Luyang, Ning, Zuotao

Path Planning with Rear-Wheel Steering for Enhanced Parking Efficiency in Narrow Parking Spaces

2024-01-7051

12/13/2024

Path planning in parking scenarios for vehicles with Ackermann steering characteristics is a well studied problem in the literature. However, the recent emergence of four-wheel steering (4WS) chassis has brought new opportunities to the field of motion planning. Compared with front-wheel steering (2WS), 4WS vehicles offer higher flexibility and new maneuver modes such as CrabWalk. To utilize such new potential to further improve parking efficiency, this paper proposes a four-wheel steering oriented planning algorithm for parking scenarios. First, Hybrid A*-4WS is proposed to search for a coarse trajectory from the starting pose to the parking slot, with improved node expansion mechanism to incorporate four-wheel steering characteristics. Then a nonlinear programming (NLP) problem is formulated with four-wheel steering kinematic model to fully utilize the maneuver capability of 4WS vehicles, with OBCA used for collision avoidance constraints. Finally, the two algorithms are sequentially

Song, Yufei, Liu, Yuanzhi, Xiong, Lu, Tang, Chen

Human-like Behavior Strategy for Autonomous Vehicles Considering Driving Styles

2024-01-7046

12/13/2024

Autonomous driving technology plays a crucial role in enhancing driving safety and efficiency, with the decision-making module being at its core. To achieve more human-like decision-making and accommodate drivers with diverse styles, we propose a method based on deep reinforcement learning. A driving simulator is utilized to collect driver data, which is then classified into three driving styles—aggressive, moderate, and conservative—using the K-means algorithm. A driving style recognition model is developed using the labeled data. We then design distinct reward functions for the Deep Q-Network (DQN), Proximal Policy Optimization (PPO), and Soft Actor-Critic (SAC) algorithms based on the driving data of the three styles. Through comparative analysis, the SAC algorithm is selected for its superior performance in balancing comfort and driving efficiency. The decision-making models for different styles are trained and evaluated in the SUMO simulation environment. The results indicate that

Shen, Chuanliang, Zhang, Longxu, Shi, Bowen, Ma, Xiaoyuan, Li, Yi, Hu, Hongyu

Empirical Modelling of Machinability during Drilling of Aluminium Oxide/Glass Fiber Reinforced Resin/Epoxy Composites

2024-01-5219

12/10/2024

This study describes the Taguchi optimization process applied to optimize drilling parameters for glass fiber reinforced composite (GFRC) material. The machining process is analyzed in relation to process parameters using analysis of variance (ANOVA). The characteristics assessed for both the drilling and the specimen include speed, feed rate, drill size, and specimen thickness. The commercial software program MINITAB14 was used to collect and analyze the measured results. Cutting force and torque during drilling are examined in relation to these parameters using an orthogonal array and a signal-to-noise ratio. The primary goal is to identify the critical elements and combinations of elements that impact the machining process to achieve minimal cutting thrust and torque, based on the evaluation of the Taguchi technique

Raja, Rosari, Jannet, Sabitha, Kandavalli, Sumanth Ratna

AI-Based Smart Vehicle Parking System

2024-01-5242

12/10/2024

This project presents the development of an advanced Autonomous Mobile Robot (AMR) designed to autonomously lift and maneuver four-wheel drive vehicles into parking spaces without human intervention. By leveraging cutting-edge camera and sensor technologies, the AMR integrates LIDAR for precise distance measurements and obstacle detection, high-resolution cameras for capturing detailed images of the parking environment, and object recognition algorithms for accurately identifying and selecting available parking spaces. These integrated technologies enable the AMR to navigate complex parking lots, optimize space utilization, and provide seamless automated parking. The AMR autonomously detects free parking spaces, lifts the vehicle, and parks it with high precision, making the entire parking process autonomous and highly efficient. This project pushes the boundaries of autonomous vehicle technology, aiming to contribute significantly to smarter and more efficient urban mobility systems

Atheef, M. Syed, Sundar, K. Sham, Kumar, P. P. Prem, Karthika, J.

Thermal Conductivity Optimization of Nanodiamond Nanofluids for High-Performance Automotive Engines

2024-01-5212

12/10/2024

In this study, we investigate the thermal conductivity optimization of nanodiamond nanofluids for application in high-performance automotive engines. Nanodiamond particles, known for their superior thermal properties and stability, are dispersed in a base fluid composed of ethylene glycol and water. Various concentrations of nanodiamonds are prepared to evaluate their impact on thermal conductivity and viscosity. The experimental setup includes precise measurements of thermal conductivity using the transient hot-wire method and viscosity using a rotational viscometer over a temperature range of 25°C to 100°C. The results demonstrate significant enhancements in thermal conductivity with acceptable increases in viscosity, suggesting the potential of nanodiamond nanofluids in improving engine cooling efficiency. The study concludes with recommendations for future research to explore the long-term stability and performance of these nanofluids in real-world automotive applications

Jeyanthi, P., Gulothungan, G.

Parametrized Twist Beam Suspension for Enhanced Ride and Handling: A Design Iteration Approach

2024-28-0181

12/05/2024

The parametrized twist beam suspension is a pivotal component in the automotive industry, profoundly influencing the ride comfort and handling characteristics of vehicles. This study presents a novel approach to optimizing twist beam suspension systems by leveraging parametric design principles. By introducing a parameter-driven framework, this research empowers engineers to systematically iterate and fine-tune twist beam designs, ultimately enhancing both ride quality and handling performance. The paper outlines the theoretical foundation of parametrized suspension design, emphasizing its significance in addressing the intricate balance between ride comfort and dynamic stability. Through a comprehensive examination of key suspension parameters, such as twist beam profile, material properties, and attachment points, the study demonstrates the versatility of the parametric approach in tailoring suspension characteristics to meet specific performance objectives. To validate the

Pakala, Pradeep Kumar, Ganesh, Lingadalu

An Innovative Method to Measure Tapered Roller Bearing Preload in Manual Transmission & Identification of Crucial Influencing Parameters

2024-28-0197

12/05/2024

In manual transmission, bearing preload is a vital factor for optimum durability and performance of tapered roller bearings (TRB). To achieve better optimization of bearing preload, a precise measurement method is a minimum requisite. This technical paper investigates multiple ideas and develops a novel methodology for accurate bearing preload measurement, overcoming the challenges produced by the complexity of transmission design. This paper provides a systematic approach to bearing preload measurement in manual transmission along with identification of key parameters responsible for influencing bearing preload, such as rigidity and fit of the components. A comprehensive experimental study at both part level and system level was conducted to quantify the effects of above-mentioned parameters on preload and transmission performance. Furthermore, the paper explores the effect of bearing preload optimization on the durability performance of the transmission unit

Gaurav, Kumar, Kumar, Arun, Singh, Maninder Pal, Dhawan, Soumil, Singh, Kulbir, Kumar, Krishan, Singh, Manvir

Smart Logistics Junction to Supervise the Material Handling Equipment Movements at the Intersection

2024-28-0260

12/05/2024

This paper presents a work undertaken to simulate the logistics processes in the digital environment using a discrete event simulation software which involves the movements of the Material Handling Equipment [MHE]. MHE movements to the line side involves traffic, where the parts are transported from the supermarket area to the line side based on the part requirement list ordered from the line side. The intersections are the bottleneck in the system due to the traffic and if the vehicle scheduling is not streamlined, then during any failure/stoppage of the vehicle, would result in the blocking of the preceding vehicles causing line stoppage. This work outlines to develop a junction block in the digital environment using a discrete event driven approach where an optimal flow of the vehicles is maintained at the intersections. The Junction block is created based on the succeeding track occupancy level, thus the preceding MHE’s can overtake in case of any blockages based on the priority

Surendranath, Sujith, Amasa, Sanjay, Kotegar, Shravan Raj, Venkataramana, Surendhar, Sathiyamoorthi, Gokul

Influence of Discrete Load Cases on Optimization of Chain Guide Design of Crawler Dozers under Various Ground Conditions

2024-28-0270

12/05/2024

The undercarriage is a critical component in machines such as crawlers, excavators, and compact track loaders. It includes vital elements such as the track frame, chain guides, rollers, track chains, idlers, carrier rollers, final drive, and sprockets. Among all these machines, crawler dozers encounter harsh environments with various ground conditions. During operations, the chains are subjected to traverse and side loads, which cause the chains to tend to slip out of the bottom rollers. The chain guide plays a crucial role in assisting and maintaining the chain in the correct position. The forces acting on chain guides are influenced by factors such as track chain tension, roller wear, chain link wear, and counter-rotation (where one track moves forward while the other moves in reverse). Among all the load cases, there are two critical load cases which are vital to be studied in order to determine the required number of chain guides along with other attributes like profile or section

Masane, Nishant, Bhosale, Dhanaji, Sarma, Neelam K

Comparative Analysis of BIW Subassembly Simulation Techniques AutoForm vs LS-DYNA

2024-28-0169

12/05/2024

Assembly simulation plays a pivotal role in predicting and optimizing the distortion of an assembly, particularly in the automotive industry where precision and efficiency are paramount. In BIW parts assembly, factors such as clamping, mechanical & thermal joining, and loading direction are important. These factors affect the quality of the final assembly. Predicting and optimizing these parameters in the early design stage can help reduce development time, cost and improve the quality of the final product. Currently, LS-DYNA is used for closures like doors, hoods, and fenders. However, the pre-processing, computation and post-processing time is significantly high in LS-DYNA making it challenging to use for the Entire BIW. Employing a comprehensive approach, authors assess the distortion results, preprocessing, calculation, and post-processing time of both simulation techniques. Notably, the study reveals that AutoForm offers over 50%-time savings across all stages compared to LS-DYNA

Talawar, Vaishnavchandan, Nalam, Swaroop Raju, Dhanajkar, Narendra, Kumar, Ajay, Pasupathy, Vivekanand, Chava, Seshadri

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

2024-28-0240

12/05/2024

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

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

Optimization of Additive Manufacturing (Fused Deposition Modeling) of PLA Material Using TOPSIS Approach

2024-28-0233

12/05/2024

Additive Manufacturing (AM), specifically Fused Deposition Modeling (FDM), has transformed the manufacturing industry by allowing the creation of 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 nature, affordability, and ease of processing. This study aims to optimize the parameters of Fused Deposition Modeling (FDM) for PLA material using the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) approach. The researchers performed experimental trials to examine the impact of important FDM parameters, such as layer thickness, infill density, printing speed, and nozzle temperature, on critical outcomes, including dimensional accuracy, surface finish, and mechanical properties. The methodology of design of experiments (DOE) enabled a systematic exploration of parameters. The TOPSIS approach, a technique for making decisions

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

A Simulation Based Methodology for Optimizing Correlation of Brake Disc Temperature

2024-28-0183

12/05/2024

Brake disc temperature is a critical factor influencing the performance and wear characteristics of braking systems in automobiles. Hence it is very important to optimize the correlation of brake disc temperature prediction with test. In this study critical parameters of Brake Disc temperature evaluation are identified, and algorithm is used to optimize the critical parameters to achieve the correlation of prediction with experiment data. Through a series of controlled experiments and simulations, disc temperatures are monitored under different braking conditions and simultaneously input parameters for prediction are optimized to achieve the correlation. Statistical methods were applied to evaluate the observed correlations and to model the predictive behavior of brake disc temperatures. Finally, A front-loading tool is developed to optimize the brake disc keeping target thermal capacity via algorithm. The findings of this study are expected to contribute to the enhancement of brake

Negi, Ayush Singh, Kochhar, Raman

Optimization and Regression Modeling of Additive Manufacturing (Fused Deposition Modeling) of PETG Material for Automobile Applications

2024-28-0234

12/05/2024

Additive Manufacturing (AM), specifically Fused Deposition Modeling (FDM), has become a highly promising method for creating intricate shapes using different materials. Polyethylene Terephthalate Glycol (PETG) is a highly utilized thermoplastic that is recognized for its exceptional strength, resistance to chemicals, and effortless processing. This study aims to optimize the process parameters of the FDM technique for PETG material using Taguchi Grey Relational Analysis (GRA). An empirical study was carried out to examine the impact of various FDM process parameters, such as layer thickness, infill density, printing speed, and nozzle temperature, on important outcome variables like dimensional accuracy, surface quality, and mechanical properties. The Taguchi method was used to systematically design a series of experiments, while GRA was used to optimize the process parameters and performance characteristics. The results unveiled the most effective parameter combinations for attaining

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

Optimization of Console Armrest Design for Reduction of G-Values in Head Impact Testing

2024-28-0212

12/05/2024

Head injuries from interior impacts during vehicle accidents are a significant cause of fatalities in India. Data from the National Crime Records Bureau (NCRB) for 2023 reveals that approximately 15% of the total 150,000 road fatalities were due to head impacts on vehicle interiors, resulting in about 22,500 deaths. Thus, head impact protection in a car crash is key during the design of vehicle interiors. IS 15223 and ECE-R21 provide specific guidelines for head impact testing of instrument panels and consoles in vehicles to ensure compliance with safety standards and minimize the risk of head injury during collisions. By systematically addressing each aspect of IS 15223 and ECE- R21 in the design, testing, and documentation phases, manufacturers can ensure that console armrests are optimized for safety. This approach not only helps meet regulatory standards but also enhances overall occupant protection in vehicles during collisions. The objective of this paper is to design a console

Malhotra, Deepak, Vaishnav, Suresh, Sureshkumar Presannakumari, Rajasilpi, Mangal, Gautam, Keshri, Amit

Items per page:

1 – 50 of 6857