Refine Your Search

Topic

Author

Affiliation

Search Results

Technical Paper

Comparative Analysis of GenAI Models for EV Battery Characterization Data Expansion and Validation

2024-10-17
2024-28-0032
Rapid advancement of electric vehicle (EV) technology has propelled the need for reliable and efficient methods for battery data expansion and validation. This has vital importance – to ensure safety aspects and efficient design of EV system. Traditional data collection methods for battery characterization are a large subject for the design of experiments and are often expert’s skill intensive, time-consuming, and lack scalability. This study proposes a Generative Artificial Intelligence (GenAI) based approach for two activities – First to assist the DOE of cell/battery characterization at different C rates and temperatures accounting for varied degradation rates. Secondly, manipulations of characterization data accounting for measurement and data recording errors. The study compares GenAI models like Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and transformer-based (Time-GPT) models in generating and validating EV battery characterization data.
Technical Paper

Enhancing Autonomous Vehicle Safety: A Statistical Approach to Real-Time Anomaly Detection in Autonomous Vehicles

2024-10-17
2024-28-0033
Enhancing Autonomous Vehicle Safety: A Statistical Approach to Real-Time Anomaly Detection in Autonomous Vehicles In 2022, Automakers reported approximately 400 crashes of vehicles with partially automated driver-assist systems to the NHTSA. Out of the 98 self-driving crashes with injuries, 11 resulted in serious injuries. Five incidents involving Tesla’s were fatal. According to Policy Advice, 43% of Americans are uncomfortable inside a driverless car, citing safety as their biggest concern. A survey by Advocates for Highway and Auto Safety indicated 75% of people would rather drive themselves than ride in an AV. The current limitations of training data for autonomous vehicles (AVs) can lead to performance deficiencies when encountering unexpected scenarios beyond their training scope. This can compromise passenger safety and hinder public trust in AV technology.
Technical Paper

Automotive security solution using Hardware Security Module (HSM)

2024-10-17
2024-28-0037
In today's world, Vehicles are no longer mechanically dominated, with increased complexity, features and autonomous driving capabilities, vehicles are getting connected to internal and external environment e.g., V2I(Vehicle-to-Infrastructure), V2V(Vehicle-to-Vehicle), V2C(Vehicle-to-Cloud) and V2X(Vehicle-to-Everything). This has pushed classical automotive system in background and vehicle components are now increasingly dominated by software’s. Now more focus is made on to increase self-decision-making capabilities of automobile and providing more advance, safe and secure solutions e.g., Autonomous driving, E-mobility, and software driven vehicles, due to which vehicle digitization and lots of sensors inside and outside the vehicle are being used, and automobile are becoming intelligent. i.e., intelligent vehicles with advance safe and secure features but all these advancements come with significant threat of cybersecurity risk.
Technical Paper

Wireless CAN adaptation for ZCU based using Zigbee protocol for efficient data transmission and data security

2024-10-17
2024-28-0036
This paper explores the integration of Wireless Controller Area Network (CAN) technology with the Zigbee protocol to enhance data transmission efficiency and security in Zonal Control Unit (ZCU) based systems. By combining Zigbee's wireless capabilities with CAN's established reliability, this integration aims to address these challenges while ensuring robust security measures. The integration of Wireless CAN with Zigbee protocol offers a promising solution to overcome the limitations of traditional wired communication architectures. Utilizing Zigbee's low-power, short-range wireless protocol facilitates seamless communication between ZCU modules, eliminating the need for physical connections and enhancing system flexibility. The adoption of Wireless CAN with Zigbee protocol presents an innovative solution for achieving efficient data transmission and robust data security in ZCU-based systems.
Technical Paper

Cyber Security challenges in V2X and in vehicle network

2024-10-17
2024-28-0035
Until recently, it was always assumed that only a computer network could be a potential Candidate for cyber-attacks. This perception changed sometime in the year 2007 when the EVITA project by the EU first considered the idea of protecting Automotive ECUs from cyber-attacks. The Automotive cybersecurity topic started gaining momentum when catastrophic repercussions of a cyber-attack using a Jeep Cherokee sometime around 2015. Out of multiple threats in various automotive inter and intra communication interfaces, V2X attacks are at their infancy, but are expected to become much more frequent in the coming years. Telematics, smart mobility, in-vehicle/mobility IoT, and other services require connected vehicles to share data with servers, apps, and various vehicle components. V2X involves V2I, V2V, V2N, V2C, V2P, V2D and V2G etc.
Technical Paper

Revolutionizing Mechanical Engineering: Harnessing the Power of Machine Learning and AI

2024-10-17
2024-28-0034
In the contemporary landscape, the convergence of Artificial Intelligence (AI) and Machine Learning (ML) technologies plays a pivotal role in reshaping the mechanical manufacturing sector. This work illuminates the multifaceted applications of AI and ML in mechanical engineering, specifically focusing on defect detection, quality inspection, and the advancement of workplace safety protocols. Beyond industrial realms, this integration extends into everyday life through the widespread adoption of AI-driven smart appliances like dishwashers and sweepers, symbolizing a harmonious fusion of technology and mechanical manufacturing. As AI and ML technologies permeate daily existence, their role goes beyond ensuring production precision; they significantly elevate job productivity and enhance workplace safety standards.
Technical Paper

Modular and Cost Effective Compact HiL Test Platform for Functional ECU Software Validation

2024-10-17
2024-28-0041
Hardware In Loop (HIL) testing is an important step in software development lifecycle. HiL setup incurs high development costs, extended deployment time and elevated commissioning efforts. These highly complex HiL systems also consume considerable maintenance costs in the long run and due to these factors only limited number of HiL systems are generally deployed for validations. So, increase in number of users can cause a crunch in HiL availability leading to delay in testing and impacting the software release timeline in general. To meet the forementioned shortcomings, a custom-made Test box with sufficient IO’s along with a dedicated and independent processor to run the plant model will serve as a compact HiL. Compact HiL comprises of a rapid prototyping ECU, plant model and a customized test box (with control modules to serve specific purposes – analog, digital, resistance, CAN etc.).
Technical Paper

Contextual Study of Security and Privacy in V2X Communication for Architecture & Networking products

2024-10-17
2024-28-0038
In recent times there has been an upward trend in "Connected Vehicles", which has significantly improved not only the driving experience but also the "ownership of the car". The use of state-of-the-art wireless technologies, such as vehicle-to-everything (V2X) connectivity, is crucial for its dependability and safety. V2X also effectively extends the information flow between the transportation ecosystem pedestrians, public infrastructure (traffic management system) and parking infrastructure, charging and fuel stations, Etc. V2X has a lot of potential to enhance traffic flow, boost traffic safety, and provide drivers and operators with new services. One of the fundamental issues is maintaining trustworthy and quick communication between cars and infrastructure. While establishing stable connectivity, reducing interference, and controlling the fluctuating quality of wireless transmissions, we have to ensure the Security and Privacy of V2I.
Technical Paper

Contextual Study of Security and Privacy in Key As A Service (KAAS) for Architecture & Networking products

2024-10-17
2024-28-0039
One of the mega trends in the automotive industry, to integrate the car with the smartphone, has opened the adoption of Key-as-a-Service (KaaS). Traditionally, car keys or key fobs have been physical devices that provide entry and ignition capabilities. However, KaaS offers a digital alternative to traditional keys, which allow users to access and operate their vehicles using their smartphones or other digital devices. This innovative approach brings numerous benefits, including user personalization, enhanced security, remote access, and integration along with other digital services and ecosystems. KaaS also opens new possibilities for vehicle sharing and temporary access arrangements. Users can grant access to family members, friends, or service providers for a specific time-period without the need for physical key handovers. While KaaS offers convenience and flexibility, it also introduces potential security risks that must be carefully considered and addressed.
Technical Paper

Automatic mode identification for TBIW / Powertrain

2024-10-17
2024-28-0011
This paper addresses the critical task of global mode identification in the NVH domain, particularly focusing on the escalating complexity from subsystem to TBIW levels. Accurate identification of global modes for a full vehicle system demands substantial expertise and is integral to NVH post-processing. Our study introduces a novel tool/methodology developed by the IDIADA team for efficient Global/Local mode identification in subsystems or TBIW level models. Leveraging data extracted from .op2 files, including strain energy and displacement, the tool employs AI methodologies to generate easily interpretable graphs and pie charts. Compatible with major post processors like Hyper View/Meta post viewer, the Python-based tool operates efficiently via cloud technology, significantly reducing prediction time. The output not only predicts global mode numbers but also provides crucial insights into subsystem contributions, aiding in mode shape and continuity improvements.
Technical Paper

Automotive HVAC performance study using parametric DoE approach for Geometric variation with Mesh-morphing method in Ansys Fluent.

2024-10-17
2024-28-0008
The parametric variation study will be very useful for understanding the design performance of any product based on the input parameters. This type of case study will be done using Design of experiments and generate number of design points. Conventionally DoE solver will be working with geometry variation with CAD interface, meshing with appropriate tool then solver, finally with post processing. If a solver itself having workflow of change the geometry variation with mesh deflection method and automated post processing, then no need of geometry variation and meshing will lead to lot of time reduction in doing parametric study. Here HVAC parametric study used to show the performance of solver and accuracy of results generated. This approach can be used to optimize the design using parametric variation. This paper will show how to move Horizontal and vertical vanes using mesh morphing and what is the reduction in timeline in new product development.
Technical Paper

Predicting Full Vehicle Drag Coefficient using a Convoluted Neural Network Approach

2024-10-17
2024-28-0007
Artificial Intelligence (AI) and Machine Learning (ML) technologies have emerged as transformative forces across various domains, revolutionizing industries, and reshaping societal paradigms. In this work, we show how a CNN model was used in the field of CFD to predict drag coefficient of a full vehicle profile. A brief description is also provided of the data set used for training and fitting the prediction model. This was done using the integrated AI/ ML technology in the DEP MeshWorks tool focusing on quick design iterations and results generation. The design advisor function within MeshWorks is an intelligent system that comprehends the real-time prediction of the responses such as model stiffness, frequency and others related to durability, NVH or CFD domain, on a model building phase without needing to run the post-processing for every design iteration.
Technical Paper

Numerical Investigation on Performance Based Methodology for Developing the Vane design of AC Duct

2024-10-17
2024-28-0004
To ensure proper airflow distribution inside the cabin, the AC duct vanes' ability to direct airflow must be evaluated. Objective of this work is to propose a methodology for developing the vane design of AC system duct. CFD based factorial analysis was conducted using three components at three levels. The impact of number of horizontal vanes, number of vertical vanes and distance between them on the pressure drop and face level velocity are investigated. It was observed that when the number of vertical vanes are increased, the vane's ability to direct airflow rises. In this situation, the pressure drop increases as well. When the number of horizontal vanes exceeds a specific threshold, the vane's capacity to steer airflow declines. In literature, it can be noted that a greater number of research are available that focus on the relationship between human thermal comfort and vent position.
Technical Paper

Development of ANFIS Predictive Model for Additive Manufacturing (Fusion Deposition Modeling) of TPU Material

2024-10-17
2024-28-0025
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.
Technical Paper

Towards automation of reference data generation for ADAS/AD functions development – ALiVA framework

2024-10-17
2024-28-0022
The advancements towards autonomous driving have propelled the need for reference/ground truth data for development & validation of various functionalities. Traditional data labelling methodologies are time consuming, skills intensive & have many drawbacks. These challenges are addressed through ALiVA (automatic lidar, image & video annotator), a semi-automated framework assisting for event detection & reference data generation through annotation/labelling of video & point-cloud data. ALiVA is capable of processing large volumes of camera & lidar sensor data. Main pillars of framework are object detection-classification models, object tracking algorithms, cognitive algorithms & annotation results review functionality. Automatic object detection functionality generates precise bounding box around the area of interest & assigns class labels to annotated objects.
Technical Paper

Unlocking radar sensor integration in vehicle: Accelerated product development harnessing electromagnetic simulation

2024-10-17
2024-28-0019
Automotive radar plays a crucial role in object detection and tracking. While an standalone radar possesses ideal characteristics, integrating it within a vehicle introduces challenges. The presence of vehicle body, bumper, chassis, and cables in proximity influences the electromagnetic waves emitted by the radar, thereby impacting its performance. To address these challenges, electromagnetic simulations can guide early-stage design modifications. However, operating at very high frequencies around 77GHz and dealing with the large electrical size of complex structures demand specialized simulation techniques to optimize radar integration scenarios. Thus, the primary challenge lies in achieving an optimal balance between accuracy and computational resources/simulation time. This paper outlines the process of radar vehicle integration from an electromagnetic perspective and demonstrates the derivation of optimal solutions through RF simulation.
Technical Paper

Parametric Solid Meshing of Tires

2024-10-17
2024-28-0017
CAE has been a critical tool for efficient tire development with the use of simulation to evaluate durability, drag and other performance metrics. A significant challenge in the process can be the significant amount of time consumed in setting up a tire model. Of late tire suppliers in Japan have been successfully using innovative ideas and tools to reduce this time by as much as 80 percent. The time savings translates to substantial reduction in turnaround time for evaluating new tire designs. They have been using custom CAE software that has inbuilt tools offering many useful features for any tire CAE team. There is a Hex meshing tool that gives the ability for the CAE engineer to generate a ‘pure’ quad mesh pattern across the tire cross-section along with the ability to automatically create a REBAR (internal reinforcement) layer within the tire. Hex meshes are desired for simulation as they offer better quality of results when compared to tetra meshes.
Technical Paper

Design, Modeling and Analysis of Roll Cage for SAE BAJA Vehicle

2024-10-17
2024-28-0012
This paper studies design parameters, selection of materials and structural analysis for an All-Terrain Vehicle (ATV) BAJA roll cage at the event site in any possible situation. SolidWorks 2022 was used for creating the prototype of the roll cage and then both static structural as well as dynamic crash analysis for the roll cage was done using Altair HyperWorks 2023 for various collisions like front, rear, side, rollover, torsional, front bump, rear bump, front roll over, side roll over and rear roll over. In addition to their corresponding deformation, Von Mises stresses were observed and a safety factor was calculated for these load cases which was found to be in the range of 1.5 to 3. Without reducing the roll cage’s strength, the roll cage designed for a four-wheel drive configuration is developed with driver comfort and safety in mind. Finding the optimal safety factor is the core objective of the analysis, as it ensures in any situation, the ATV’s roll cage will stay secure.
Technical Paper

Study of effect on structural strength of locally strengthened rotor lamination stack through virtual validation.

2024-10-17
2024-28-0006
Rotor and Stator are the key constituents of an electric motor that are made of several laminates punched from a sheet metal and stacked together. The rotor stack is inserted with magnets at the punched-out pockets and is assembled with a shaft via press fitting. Rotor assembly being the rotating part of an E-Motor is subjected to centrifugal loads due to masses of magnets, lamination stack and shaft rotating at high speeds, temperatures and assembling loads because of which rotor laminates experience failures as the high strains develop in the regions on the laminate that support magnets. Typically, these high strain locations are the sections of the magnet pockets one on the outer diameter of the laminate and the other at the sections between the magnet pockets. Traditionally, these high strains are addressed by increasing the area of these sections, but this has a detrimental effect on the electromagnetic performance.
Technical Paper

Occupant reflex study during pre-crash and integrated safety restraint system

2024-10-17
2024-28-0002
The active safety feature's primary goal is to minimize the risk of a collision between the car and an obstacle. To enhance the safety of an occupant, it is required to install active safety features on all the new cars being manufactured, but unfortunately, all accidents are not avoidable. The number of accidents on the road has increased recently along with the number of cars, and thus it is very essential to study the crashworthiness of an automobile since human life is at the top of the priority list. In this study, the reflexes of an occupant prior to the crash event are studied, and research has been done on how occupant positioning affects injury metrics. Most of the available studies are related to the pre-crash event or the ideally seated position of the occupant. However, it is very much essential to know the reflex or behavior of an occupant during the pre-crash event, where generally the occupant will not be in an ideal seating position due to panic reflex.
X