Browse Topic: Data acquisition and handling

Items (4,617)

Post-EOL Cybersecurity Validation for Automotive Production ECUs

2026-26-0608To be published on 01/16/2026

ISO/SAE 21434 emphasizes comprehensive cybersecurity risk management throughout the automotive lifecycle. However, specific guidance on validating cybersecurity measures at the production level remains limited. This paper addresses the gap in production-stage validation, particularly after End-of-Line (EOL) flashing, which includes configurations of security hardware and software protection (e.g., UCB confirmation, JTAG, and P-flash password settings). Problem articulation: Current automotive cybersecurity validation methods, despite adherence to ISO/SAE 21434, lack specific procedures for the production stage. The existing system-level validation using the ASPICE V-model (e.g., SWE.6, SYS.5) does not ensure the integrity and functionality of cybersecurity features in the final manufactured unit post-EOL flashing. This gap poses a risk of vulnerabilities being introduced during the EOL process, compromising critical security measures. Proposed solution: To mitigate the cybersecurity

Chakraborty, Sucheta, Kulanthaisamy, Nagarajan, Sankar, Ganesh

Development of an Software Algorithm Based Semi-automated Data Acquisition System for Gasoline Vehicle Calibration on Chassis Dynamometer

2026-26-0535To be published on 01/16/2026

Vehicle level testing is one of the crucial part of the calibration development. In this, chassis dynamometer is used to collect the vehicle level data. Different engine and vehicle level parameters are logged at various speed and load points covering the entire engine operational zone. This data acquisition is a repetitive activity and covers over 30-40% of the total testing duration. This phase includes base calibration verification, transient development, and emissions-related calibrations, all of which follow a standardized and repetitive sequence. However, these tasks are predominantly performed manually, leading to potential human error and inefficiencies. This paper presents a novel and comprehensive algorithm developed using INCA FLOW software; the first of its kind for this application. Here, crucial vehicle data acquisition activities are identified, mapped into detailed steps. The algorithm introduces a semi-automated, stepwise process for data acquisition during chassis

Kavekar, Pratap Chandrashekhar, Tyagarajan, Sethuramalingam, Agarwal, Nishant Kumar, Shaikh, Wasim, Karadi, Subramanya

Accelerating Product Development Life Cycle through Digitalization of Fatigue Life for Structural Components

2026-26-0496To be published on 01/16/2026

In today’s competitive market, accelerating product development without compromising durability is critical. Durability is a key benchmark for assessing the quality and reliability of automotive products. To meet rising customer expectations and regulatory demands, the industry must develop vehicles that offer high performance and reduced weight while ensuring safety. A well-engineered vehicle must retain structural integrity and functionality under normal operating conditions and withstand extreme load events without critical failure. Achieving this requires effective Road Load Data Acquisition (RLDA), integrated with robust design practices and efficient validation processes. However, physical RLDA is time-consuming and costly, as it depends on prototype vehicles that are often available only in the later development stages. Failures identified during these late-stage tests can delay the product launch significantly. To address these challenges, this paper introduces a digital

Kokare, Sanjay, Dwivedi, Sushil, Siddiqui, Arshad, Iqbal, Shoaib

A Comprehensive Study of vehicle side door structure and window glass displacement during slam for refinement

2026-26-0549To be published on 01/16/2026

In the vehicle closures validation process, the displacements in its structure and window glass have significant impact on its service life. The objective of this paper is to develop a test case using instrumentation and data acquisition for measuring the vehicle door structure and its window glass displacement along the lateral direction. This measurement support for understanding the door and window glass displacement impact on its primary and secondary rubber seals, striker, check arm, hinges, and its structural rigidity. The door mechanisms also get affects by door displacement which results to significant deterioration in its performance. The test setup comprises of sensors with required range and accuracy connected with data acquisition system by selecting appropriate sampling rate. The sensors placed on window glass and on door structure top corner during the measurement. Different window glass positions like full close, half close and fully opened considered for the study

Arthanathan, Sankaranarayanan, SHASHIDHAR, S, B, VENKATASUBRAMANIAN

Optimisation of frontal impact force scheme to accelerate the target setting process for development of front-end structures in vehicles.

2026-26-0001To be published on 01/16/2026

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, Ishan, Bhatnagar, Abhinav, Kumar, Ayush

Real-time Intrusion Detection System (IDS) for Vehicle Networks Using Machine Learning for Predictive Threat Analysis

2026-26-0617To be published on 01/16/2026

The rapid adoption of connected vehicle technologies and advanced driver assistance systems (ADAS) necessitates robust security mechanisms capable of identifying and mitigating sophisticated cyber threats in real-time. Traditional signature-based intrusion detection systems (IDS) are often inadequate in addressing the dynamic and evolving nature of automotive cybersecurity threats, particularly in modern vehicle networks like Controller Area Network (CAN), CAN with Flexible Data-Rate (CAN-FD), and Automotive Ethernet. This research introduces a novel Real-time Intrusion Detection System utilizing advanced Machine Learning (ML) techniques designed specifically for automotive network environments. The proposed IDS framework employs supervised and unsupervised ML algorithms, including anomaly detection, behavioral analytics, and predictive threat modeling, to achieve high accuracy and rapid threat identification capabilities. Through extensive testing in simulated and actual vehicle

chaudhary lng, Vikash, Desai, Manoj, Chatterjee, Avik

A Novel Approach to Optimal Strain Gauge Placement for Structural Assessment: Integrating Close Looping Configuration with Calibration Techniques

2026-26-0551To be published on 01/16/2026

Addressing the challenge of optimal strain gauge placement on complex structural joints and pipes, this research introduces a novel methodology combining strategic gauge configurations with numerical optimization techniques. Traditional methods often struggle to accurately capture combined loading states and real-world complexities, leading to measurement errors and flawed structural assessments. For intricate joints, a looping strain gauge configuration is proposed to comprehensively capture both bending and torsional effects, preventing the bypassing of applied loads. A calibration technique is used to create strain distribution matrices and access structural behavior under different loading conditions. Optimization algorithms are then applied to identify gauge placements that yield well-conditioned matrices, minimizing measurement errors and enhancing data reliability. This approach offers a cost-effective solution by reducing the number of gauges required for accurate stress

shingate, Uttam, Yadav, Dnyaneshwar

Proactive AI-Enhanced Cybersecurity for Next-Gen Automotive Infotainment ECU

2026-26-0619To be published on 01/16/2026

Abstract With the rapid advancement of connected vehicle technologies, infotainment Electronic Control Units (ECUs) have become central to user interaction and connectivity within modern vehicles. However, this enhanced functionality has introduced new vulnerabilities to cyberattacks. This paper explores the application of Artificial Intelligence (AI) in enhancing the cybersecurity framework of infotainment ECUs. The study introduces AI-powered modules for threat detection and response, presents an integrated architecture, and validates performance through simulation using MATLAB, CANoe, and NS-3. This approach addresses real-time intrusion detection, anomaly analysis, and voice command security. Key benefits include zero-day exploit resistance, scalability, and continuous protection via OTA updates. The paper references real-world automotive cyberattack cases such as Tesla's OTA vulnerability patches, BMW ConnectedDrive exploits, and Jeep Cherokee's Uconnect hack, emphasizing the

More, Shweta, Kulkarni, Shraddha, Kumar, Priyanshu, GHANWAT, HEMANT, Joshi, Vivek

A Mathematical Modelling Approach Based on Artificial Neural Network for Estimation of Key Parameters in Internal Combustion Engine

2026-26-0659To be published on 01/16/2026

In a conventional powertrain driven by Internal combustion (IC) engines, there are many key sensors such as intake manifold temperature sensor, exhaust temperature sensor, Nitrogen oxide (NOx) sensors etc. to monitor engine performance and emissions. For enabling various diagnostics strategies and engine monitoring, virtual sensors or modelled values of such sensors play an important role. Conventional strategies incorporate the use of regression models, map-based models and physics-based models. There are a few drawbacks with conventional models 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, for example

Jagtap, Virendra Shashikant, Shejwal, Sanket, Mitra, Partha

Swarm-Inspired Cooperative Mapping for Urban Autonomous Navigation

2026-26-0635To be published on 01/16/2026

Urban autonomous vehicles today largely rely on individually built maps or centralized cloud services—both rigid under intermittent connectivity and rapid scene changes (construction, pop-up events). Inspired by how ant colonies collectively explore, we introduce a decentralized protocol: each vehicle broadcasts compressed “map particles” embedded with virtual pheromone values that highlight zones of high uncertainty or recent change. Neighboring vehicles incorporate these signals to prioritize sensing and route planning. A lightweight consensus algorithm merges local graphs into a shared dynamic map, resilient to network splits. The result, a bio-inspired SLAM that enables fleets to adapt on the fly to evolving cityscapes, boosting safety, efficiency, and robustness.

Bhargav, Anirudh S, Subbarao, Chitrashree

Driving behavior modelling with Graph Attention Networks using spatial data

2026-26-0661To be published on 01/16/2026

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, we construct a graph-based model that 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

Innovative Multi-Axial Testing approach for Enhanced Reliability of Cooling Modules in Commercial Vehicles

2026-26-0530To be published on 01/16/2026

This paper presents an innovative in-lab accelerated testing approach for chassis-mounted components, with a particular focus on the cooling module of commercial vehicles. The proposed method simulates real-time data acquired from field operations and replicates all critical chassis modes, including torsion. Additionally, real-time coolant circulation at specified pressure and temperature maintenance are feasible during durability testing, enhancing the realism of the test environment. The cooling modules, comprising the radiator, intercooler, and charge air cooler (CAC), often experience failures due to various multi-axial inputs and chassis modes. This paper introduces an innovative methodology for replicating field conditions in the lab, utilizing seven servo-hydraulic actuators to simulate multi-axial inputs. The accuracy of in-lab simulation for the acceleration levels at input and response locations of the cooling module exceeds 90%. This makes it a preferred choice for test

V Dhage, Yogesh, Satale, Sunil

A Frequency-Based correlation adjustment method for translating Proving Ground Test Tracks to 4-DOF Road Simulator Rig Testing of Electric Two wheelers

2026-26-0556To be published on 01/16/2026

Real-world usage subjects two-wheelers to complex and varying dynamic loads, necessitating early-stage durability validation to ensure robust product development. Conducting a full life-cycle durability testing on proving grounds is time-consuming, extremely difficult for the riders involved, and costly, which is why accelerated testing using rigs such as the road simulator system have become a preferred approach. The use of road simulators necessitates, accurately measured inputs and precise simulation to ensure proper actuation of the rig, thereby enabling realistic representation of road undulations. Road Load Data Acquisition (RLDA) is used to measure various inputs such as displacement, acceleration, strain, and predicted forces from the road which are then used to simulate real-world conditions in a road simulator. This paper covers two important aspects essential for achieving an accurate and clear representation of road simulation in a 4-DOF road simulator, encompassing both

Ganju, Shubham, V, Vijayamirtharaj, Prasad, Sathish, R S, Mahenthran

Reverse Gear Duty Cycle Generation Using Virtual RLD Simulation

2026-26-0405To be published on 01/16/2026

Keywords: RLD (Road Load Data), AVL VSM, AVL Route Studio, Duty Cycle, Transmission, Reverse Gear, Durability The development of transmission systems involves creating duty cycles for bench-level durability evaluations for both forward and reverse gears. For forward gear, vehicles are driven under various real-world conditions over thousands of kilometers, equipped with numerous sensors and components tailored for data collection. In contrast, duty cycles for reverse gear are often based on prior experience or rough estimations due to the lack of clear definition of real world use case. Reverse gear RLD is particularly scarce, especially for heavy-duty vehicles operating in off-road or mining environments, where specific reverse driving paths are not typically followed. This paper presents a detailed methodology highlighting the importance of reverse gear duty cycles by leveraging virtual RLD simulations on various gradients using tools such as AVL Route Studio and AVL VSM. By

Kansagara, Smit, Patel, Hiral, kira, Lucas, Sutar, Suresh, Soor, Debasis

Quantifying the Energy Consumption of HVAC Operation and Its Impact on the Range of Electric Buses Across Diverse Climatic Conditions

2026-26-0204To be published on 01/16/2026

Electric buses (e-buses) are essential to sustainable public transport, but their real-world efficiency and range are heavily affected by auxiliary systems, particularly the Heating, Ventilation, and Air Conditioning (HVAC) system. This study investigates how ambient temperature variations and HVAC loads influence energy consumption, range, and efficiency in e-buses operating under diverse climatic conditions. The methodology combines field data collection from urban e-buses across seasons—including extreme summer and winter—with controlled lab testing. Field measurements included ambient temperature, HVAC demand, vehicle speed, state of charge (SOC) variation, and energy consumption. These inputs were used to develop real-world duty cycles, replicating actual thermal loads, passenger profiles, idling periods, and driving patterns. In the lab, these cycles were simulated using a chassis dynamometer and environmental chamber, with HVAC systems tested at controlled ambient temperatures

Vishe, Prashant, Dalela, Saurabh, Joshi, Madhusudan, Saraswat, Shubham

A Performance-driven Numerical Approach for Optimizing the Plenum Opening Area of Cowl Box

2026-26-0461To be published on 01/16/2026

There is a scarcity of research in literature regarding the determination of Plenum Opening Area of cowl box. The area of the plenum opening in the cowl box significantly affects the airflow rate in fresh airflow modes, such as face and defrost modes, as well as issues related to water ingress. Primarily, the size of the plenum opening is determined by the necessary HVAC airflow rate. This study aims to investigate how the plenum opening area impacts both airflow discharge and the water ingress issue in the HVAC module. A novel approach is introduced in this research to determine the optimal plenum opening area of the cowl box, taking into account both airflow rate and water ingress concerns. The ANSYS FLUENT software is utilized to analyze airflow discharge in both face and defrost modes, while the SPH (Smooth Particle Hydrodynamics) based Preonlab tool is employed for water ingress analysis. Airflow discharge is evaluated for various plenum opening sizes in both modes, and the area

Baskar, Subramaniyan, A Sr, Mahesh, Gopinathan, Nagarajan

Assessing Brake Emission Performance Across New, Upgraded, and Retrofitted Test Bed Infrastructures

2026-26-0232To be published on 01/16/2026

Brake wear particle emissions are a significant source of traffic-related particulate matter, prompting increasing regulatory attention through frameworks such as UN GTR No. 24 and the forthcoming Euro 7 standard. To address the demand for accurate and reproducible measurement solutions, a comparative study was conducted using an identical ventilated cast-iron disc brake across different test bed infrastructures. Three AVL solution configurations were assessed: (1) a newly built brake emission test bed, (2) an engine test bed upgraded with brake emission measurement equipment, and (3) a simulated third-party brake test bed (e.g., originally used for performance or NVH testing) retrofitted with brake emission measurement equipment. In the third configuration, the UN GTR No. 24 test sequence was automated and executed by the AVL System Control in coordination with the existing test bed infrastructure. The testing infrastructure included a CFD-optimized brake enclosure and sampling tunnel

Martikainen, Sampsa, Weidinger, Christoph, Huber, Michael Peter

Integrating V2V and V2I Communications for Enhanced Traffic Safety and Efficiency in Connected Vehicular Networks

2026-26-0271To be published on 01/16/2026

This paper presents a new approach to improve road safety and traffic flow by combining vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. Our study focuses on a system that connects vehicles with each other and with traffic signals to share real-time data about speed, position, and road conditions. Using both analytical models and experimental simulations built in MATLAB/Simulink, we developed a system that predicts and advises the optimal speed for vehicles approaching an intersection. In our design, a Green Light Optimized Speed Advisory (GLOSA) feature suggests an ideal speed for drivers so that they can pass through green lights without unnecessary stopping. This not only improves traffic flow but also reduces fuel consumption and lowers the risk of accidents. We validated our system through a series of simulations and real-time traffic scenarios. The results show that our approach can adapt dynamically to changes in vehicle behavior and traffic density

PINTO, COLIN AUBREY, Shah, Ravindra, Karle, Ujjwala

Resilient Design Strategies for Wireless Charger ECUs: A Proactive Threat Analysis and Risk Assessment Framework for Ensuring Cybersecurity in EV Charging Ecosystems

2026-26-0173To be published on 01/16/2026

The goal of Automotive cybersecurity is safety, reliability, confidentiality and authenticity. As the automotive industry grows smarter, so too do the cybersecurity protocols used to protect vehicles from malicious actors. Automotive cybersecurity secures communication networks, electronic systems, software and data collected by the new wave of intelligent cars The paper describes the cyber security threats its analysis ion wireless charging

Uthaman, Sreekumar, Mulay, Abhijit B, Gadekar, Pundlik

Optimizing Suspension Joint Reliability: Overcoming Bolt Loosening and Torque Variability in Automotive Production

2026-26-0492To be published on 01/16/2026

In modern automotive manufacturing, ensuring the integrity of suspension joints under real-world driving conditions is a critical aspect of vehicle safety and performance. These joints endure substantial transverse loads and large vibrations due to irregular road surfaces, dynamic manoeuvres, and varying environmental factors. As a result, bolt loosening becomes a significant concern, compromising joint integrity and overall vehicle reliability. This paper delves into the challenges associated with maintaining joint integrity, specifically focusing on pre-load determination, torque application, and production-related issues. The pre-load generated during torquing is the primary factor that ensures a suspension joint remains securely fastened under dynamic road conditions. This pre-load is derived using road load data acquisition (RLDA) inputs, which capture the forces acting on the joint during actual driving scenarios. RLDA inputs provide critical insights into the forces experienced

Kumar, Sabeesh, Vasant Kumar, Jesse Daniel, Mishra, Harshit, Senthil Raja, T, NAYAK, Bhargav, M, Sudhan, NAMANI, Prasad, Vibhute, Shekhar

A Physics-Guided Neural Network Approach for EGR Cooler Temperature Estimation: Addressing ECU Model Discrepancies

2026-26-0435To be published on 01/16/2026

As the automotive industry explores alternative powertrain options to curb emissions, it is pertinent to refine existing technologies to improve efficiency. The Exhaust Gas Recirculation (EGR) system is a pivotal component in emission control strategies for Internal Combustion Engines (ICE). The EGR cooler is crucial in thermal management strategies, as it lowers the temperature of recirculated exhaust gases before feeding it along with fresh air, thereby reducing nitrogen oxides (NOx) emissions. Precise estimation of the EGR cooler outlet temperature is crucial for effective emission control. However, conventional Engine Control Unit (ECU) models fall short, as they often show discrepancies when compared to real-world test data. These models rely on empirical relationships that struggle to capture, transient effect, and real time variation in operating conditions. Consequently, ECU-based estimations of EGR Cooler outlet temperature frequently deviate from actual values, leading to

Kumar, Amit, Kumar, Raman, Manojdharan, Arjungopal, Challa, Krishna, Kramer, Markus

Enhancing Factory Modelling: Integrating Drone Technology and Automated Post Processing Systems

2026-26-0307To be published on 01/16/2026

The growing environmental, economic, and social challenges have spurred a demand for cleaner mobility solutions. In response to the transformative changes in the automotive sector, manufacturers must prioritize digital validation of products, manufacturing processes, and tools prior to mass production. This ensures efficiency, accuracy, and cost-effectiveness. By utilizing 3D modeling of factory layouts, factory planners can digitally validate production line changes, substantially reducing costs when introducing new products. One key innovation involves creating 3D models using point cloud data from factory scans. Traditional factory scanning processes face limitations like blind spots and periodic scanning intervals. This research proposes using drones equipped with LiDAR (Light Detection and Ranging) technology for 3D scanning, enabling real-time mapping, autonomous operation, and efficient data collection. Drones can navigate complex areas, access small spaces, and optimize factory

Narad, Akshay Maruti, C H, Ajheyasimha, Vijayasekaran, Vinothkumar, FASGE, ABHISHEK

Automotive Cybersecurity Incident Response (CSIR) Framework and Its Integration into OEM Processes

2026-26-0613To be published on 01/16/2026

The exponential growth of connected and autonomous vehicles has significantly escalated cybersecurity threats, compelling automotive Original Equipment Manufacturers (OEMs) to adopt robust and structured Cybersecurity Incident Response (CSIR) capabilities. Current automotive cybersecurity regulations, such as AIS 189 in India and UNECE WP.29 globally, mandate precise frameworks for proactive threat detection, timely response, and comprehensive incident documentation. This research presents an innovative, comprehensive CSIR framework specifically tailored to integrate seamlessly into OEM cybersecurity management processes. Leveraging a combination of real-time monitoring systems, structured threat categorization methodologies, and integrated escalation and communication protocols, the proposed CSIR framework ensures efficient incident handling aligned with stringent regulatory compliance. The framework encompasses advanced methodologies including Vehicle Security Operations Center (VSOC

chaudhary lng, VIKASH, Desai, Manoj, Chatterjee, Avik, Chatterjee lng, Avik

GTSRB-Shield: A Novel Machine Learning Framework for Intrusion Detection in Autonomous Vehicles Leveraging the German Traffic Sign Recognition Benchmark

2026-26-0611To be published on 01/16/2026

The escalating dependence of Autonomous Vehicles on Intelligent Transportation Systems (ITS) has highlighted the imperative for comprehensive security protocols to safeguard such vehicles against cyber threats. Intrusion Detection Systems (IDS’s) are pivotal in ensuring the protection of these systems by detecting and alleviating unauthorized access and nefarious activities. The German Traffic Sign Recognition Benchmark (GTSRB) database, which encompasses an extensive compilation of traffic sign imagery, functions as a vital asset for the advancement of machine learning-based IDS. This research elucidates an intrusion detection system (IDS) that employs machine learning algorithms to scrutinize the GTSRB database. The proposed IDS emphasize the preprocessing of the GTSRB dataset to extricate pertinent features that can be employed for the training of machine learning models. Research also focuses on model development with machine learning algorithms to classify traffic signs and

Patil, Kamalesh, Akbar Badusha, A., Jadhav, Savitri, Gunale, Kishanprasad

Automotive Cybersecurity: Safeguarding Connected and Autonomous Mobility

2026-26-0629To be published on 01/16/2026

As vehicles transform into complex cyber-physical systems within Intelligent Transportation Systems (ITS), automotive cybersecurity has become a foundational pillar in securing safe, reliable, and trustworthy transportation. This paper examines cybersecurity challenges in connected and autonomous vehicles (CAVs), focusing on Vehicle-to-Everything (V2X) communications technologies, including Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I), and Vehicle-to-Pedestrian (V2P) and critical systems like electronic control units (ECUs), battery management units (BMUs), and sensor fusion modules. Key vulnerabilities, such as remote hacking, denial-of-service (DoS) attacks, malware injection, and data breaches, threaten vehicle functionality, passenger safety, and privacy. Key protection mechanisms, including encryption, intrusion detection systems (IDS), cryptographic protocols, secure over-the-air (OTA) updates, and Advanced Artificial Intelligence (AI) and Machine Learning (ML

Kumar, Om, Kumar, Rajiv, Sankar M, Gopi, Haregaonkar, Rushikesh Sambhaji

Security monitoring for High Performance Vehicle Computers

2026-26-0627To be published on 01/16/2026

With the increasing connectivity of modern vehicles, cybersecurity threats have become a critical concern. Intrusion Detection Systems (IDS) play a vital role in securing in-vehicle networks and embedded vehicle computers from malicious attacks. This presentation shares about an IDS framework designed specifically for POSIX-based operating systems used in vehicle computers, leveraging system-level monitoring, anomaly detection, and signature-based methods to identify potential security breaches. The proposed IDS integrates lightweight behavioral analysis to ensure minimal computational overhead while effectively detecting unauthorized access, privilege escalation, communication interface monitoring etc. By employing a combination of rules and systems datapoints, the system enhances threat detection accuracy without compromising real-time performance. Practical series deployments demonstrate the effectiveness of this approach in mitigating cyber threats in automotive environments

Shukla, Siddharth, Chatterjee lng, Avik

Data-Driven Prediction of Damper durability Cycles Using AIML Techniques

2026-26-0550To be published on 01/16/2026

The suspension dampers play a pivotal role in controlling suspension dynamics, especially during rapid suspension movements such as pothole impacts, speed bumps, and off-road conditions. The dampers directly influence the ride comfort, vehicle stability. Ensuring the durability of these valves is essential to maintain consistent performance throughout the vehicle's lifecycle. To validate the valve configuration at high speed, in current development practices, durability cycles are typically derived through physical data collection on actual vehicle driven on proven ground tracks. While this method provides accurate real world validation, it is highly time consuming and resource intensive. The dependency on full vehicle testing also limits early phase of validation, creating bottlenecks in the product development cycle. An AIML based methodology is presented in this paper to predict the HSVD cycles for damper validation. The AIML algorithm was trained using the historical test data and

Kabbin, Chetan D., Suryawanshi, Vishal, Daphal, Pratap, Kulkarni, Prasad

Software-Defined Vehicles: Architecting the Future of Intelligent and Connected Mobility

2026-26-0691To be published on 01/16/2026

The rise of Software-Defined Vehicles (SDVs) marks a fundamental shift in automotive design, where software, rather than hardware, defines vehicle capabilities. This review explores the SDV paradigm within Intelligent Transportation Systems (ITS), emphasizing centralized computing, over-the-air (OTA) updates, and service-oriented architectures (SOA). Key enablers such as high-performance computing units, middleware platforms (e.g., AUTOSAR Adaptive), and digital twins support scalable, flexible software deployment and real-time functionality. Artificial Intelligence (AI) and Machine Learning (ML) enhance features like predictive maintenance, driver personalization, and autonomous decision-making. However, SDVs also introduce complex challenges, including software validation, real-time performance, and system interoperability. Cybersecurity becomes critical, especially as vehicles interface with cloud platforms, edge computing, and Vehicle-to-Everything (V2X) networks. The paper also

Ahmad, Aqueel, Hemanth, Khimavath, Kumar, Om, Kumar, Rajiv, Haregaonkar, Rushikesh Sambhaji

Generative AI based methodology for Road Profile Mix Creation

2026-26-0674To be published on 01/16/2026

The acquisition of road profile data is crucial for various automotive testing applications, including vehicle dynamics analysis, chassis endurance tests, and simulation of vehicle-road interactions. This is necessary for conducting virtual tests to accelerate research and development processes and can significantly reduce testing costs. However, most of the on-road measurements lack comprehensive and relevant road profile data. Conducting on-road trials to acquire this data is a laborious and time-consuming process, often impeded by logistical and environmental challenges. This research proposes a generative AI-based methodology for creating diverse and realistic road profile mixes from the existing on-road dataset of front axle displacement and road profile measured with a laser sensor. By leveraging advanced machine learning techniques, the proposed approach seeks to generate synthetic road profiles that accurately reflect real-world conditions, thereby reducing the dependency on

Rajappan, Dinesh Kumar, Venkatesh, Anirudh Anand, R, Suresh, N, Gopi Kannan

Feasibility and Performance of Post-Quantum Cryptography on Embedded Systems for Two-Wheeler Security

2026-26-0622To be published on 01/16/2026

The proliferation of connectivity features (V2X, OTA updates, diagnostics) in modern two-wheelers significantly expands the attack surface, demanding robust security measures. However, the anticipated arrival of quantum computers threatens to break widely deployed public-key cryptography (RSA, ECC), rendering current security protocols obsolete. This paper addresses the critical need for quantum-resistant security in the automotive domain, specifically focusing on the unique challenges of two-wheeler embedded systems. This work presents an original analytical and experimental evaluation of implementing selected Post-Quantum Cryptography (PQC) algorithms, primarily focusing on NIST PQC standardization candidates (e.g., lattice-based KEMs/signatures like Kyber/Dilithium), on microcontroller platforms representative of those used in two-wheeler Electronic Control Units (ECUs) – typically ARM Cortex-M series devices characterized by limited computational power, memory (RAM/ROM), and strict

Mishra, Abhigyan

Integrating Road Load Data Acquisition and Signal Processing Techniques to Generate Reliable Drive Files for Electrodynamic Shakers in Testing the Exhaust Systems of Off-Highway Applications

2026-26-0552To be published on 01/16/2026

Generating a reliable drive file for an electrodynamic (ED) shaker from Road Load Data Acquisition (RLDA) and validating its correlation with real-world conditions through damage and fatigue analysis is crucial for accurate component testing, particularly in complex systems like off-highway exhaust systems. This paper presents a methodology for creating such a drive file and establishing its validity, highlighting the necessity of ED shakers for simulating the intricate dynamic loads experienced by these systems. The process begins with acquiring comprehensive RLDA under representative operational conditions of the off-highway vehicle. Drive files are generated using this data, which records accelerations at important exhaust system mounting locations. Advanced signal processing techniques are employed to condense the raw RLDA into a format suitable for shaker control. To establish proper correlation, the generated drive file is used to excite the exhaust system on an ED shaker

Khaire, Santosh Ramdas, Khaire, Rushikesh, Yadav, Dnyaneshwar

A Quality-Driven Approach to Engineering Sign-Off for Software and Robust Product Development

2026-26-0581To be published on 01/16/2026

This abstract outline a paper detailing the development and implementation of a comprehensive framework designed to enhance the quality and governance of the product development process in the automotive industry. As the sector undergoes significant transformation—driven by electrification, autonomous systems, and increasing regulatory and customer expectations—the need for structured development approach and robust oversight has become critical to success. The paper introduces a newly developed framework for Final Data Judgment (FDJ) and Engineering Sign-Off (ESO), representing a next-generation strategy to defect free design, robust engineering quality management and product maturity assurance. This methodology emphasizes customer-centric deliverables, risk-based assessments, and technical rigor to minimize post-SOP issues and ensure alignment with end-user expectations. The approach prioritizes end-user impact by embedding rigorous quality checkpoints that align engineering outputs

Digikar, Ashish, PATHAK, ISHA, Kothari, Bhushan

A Digital Twin Framework for Real-Time Optimization of Solar-Integrated Energy Systems

2026-26-0418To be published on 01/16/2026

In the context of increasing global energy demand and climate change concerns, the integration of renewable energy sources with advanced modelling technologies has become essential for achieving sustainable and efficient energy systems. Solar energy, despite its potential, continues to face challenges related to performance variability, limited real-time insights, and reactive maintenance. To overcome these barriers, this work presents a Digital Twin framework aimed at optimizing solar-integrated energy systems through real-time monitoring, predictive analytics, and adaptive control. This work presents a Digital Twin framework designed to address the challenges of designing, operating, maintaining, and estimating renewable energy systems, specifically solar power, based on dynamic load demand. The framework enables the real-time forecasting and prediction of energy outputs, ensuring systems operate efficiently and maintain peak performance across diverse conditions. The proposed

R, Akash, Burud, Priti Raju, Gumma, Muralidhar

A Data-Centric Approach to Identify Optimal NVH simulation Tools and Solvers

2026-26-0356To be published on 01/16/2026

The world is rapidly evolving towards a data-driven paradigm, with widespread adoption of tools and techniques such as Artificial Intelligence, Machine Learning, Digital Twins, and Cloud Computing. In the automotive sector, vast amounts of data are being generated through both physical and digital test evaluations. Among these, Computer-Aided Engineering (CAE) stands out as one of the largest contributors to data generation, as physical testing is often cost-prohibitive due to the need for prototypes and complex test setups. The field of Automotive Noise, Vibration, and Harshness (NVH) is advancing exponentially, driven by stringent regulatory norms and growing customer demand for comfort. Digitally advanced techniques are playing a pivotal role in revolutionizing NVH processes. Data generation via CAE tools has become an integral part of engineers' daily operations, with the selection of appropriate CAE software and solvers being critical. This choice impacts factors such as user

Hipparge, Vinod, masurkar, Nikita, Arabale, Vinand, Billade, Dayanand

Extreme Learning Machines (ELM) for Fast Instantaneous Prediction of Emission Level of an Automobile

2026-26-0226To be published on 01/16/2026

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 nitrogen oxides and other pollutants thus damaging the ecosystem. In line with this objective, 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 features such as vehicle type, fuel type, driving conditions, road type etc.. as well as the target variable representing the emission band of the vehicle. In addition to the big data available as mentioned above, there is a marked progress in the machine learning

Sridhar, Sriram, Aswani, Shelendra

Enhancing Engine Reliability Testing with IoT, AI and ML: Real-Time ML-based Limit Monitoring and Predictive Maintenance with IoT sensor

2026-26-0647To be published on 01/16/2026

The integration of Internet of Things (IoT), Artificial Intelligence (AI), and Machine Learning (ML) has transformed various industries, offering substantial benefits. The application of these technologies in engine reliability testing has immense potential as they offer real-time monitoring and analysis of engine performance parameters. Engine reliability testing is vital for ensuring the safety, efficiency, and longevity of engines. Traditional methods are time consuming, expensive, and rely heavily on manual inspection and data analysis. This paper shows how IoT, AI and ML technologies can greatly enhance the efficiency of engine reliability testing. The paper includes the following case studies: 1. ML-based Limit Monitoring for test data: With the help of machine learning models, we monitor the Engine health by comparing predicted and measured values during real-time testing. Intelligent algorithms predict and compare values, detect anomalies, and identify root causes in real-time

Yadav, Sanjay Kumar, kumar, prabhakar, R, Dinesh, Joon, Sushant, Rai, Ayush, Tripathi, Vinay Mani

Durability Validation of Full Vehicle Structures Using Strain Correlation and RLDA-Based Simulations

2026-26-0523To be published on 01/16/2026

Durability validation of full vehicle structures is crucial to ensure long-term performance and structural integrity under real-world loading conditions. Accurate strain correlation between physical testing and finite element (FE) simulations plays a key role in the validation, ensuring reliable predictions of vehicle durability. In this paper, a comprehensive methodology for strain correlation on a full vehicle subjected to torture track testing is implemented. Strategic placement of strain gauges is determined through a combination of static analysis, modal analysis, and identification of critical stress regions in the FE model. Strain gauges were installed on key structural locations of a prototype to capture strain responses under severe loading environments. Simultaneously, vehicle wheel loads were recorded on the torture track to build a detailed Road Load Data Acquisition (RLDA) dataset at critical hard points, Loads measured in terms of wheel loads (WFT) are fed to MBD model to

JAJU, MAYUR, Dokhale, Sandeep, Gadre, Nilesh, Patil, Sanjay

Considerations for Vulnerability Management in the Automotive Industry

2026-26-0626To be published on 01/16/2026

With the emergence of Software-Defined Vehicles (SDVs), more complex software and connectivity technologies are introduced to support new advanced use cases. These use cases include, e.g., phone as a key, smart parking, summon vehicle, remote diagnostics and vehicle management. However, complex software functionality and external connectivity also increase the attack surface of vehicles and its ecosystem. As such we have seen various cybersecurity attacks targeting vehicles and OEM backends in the past few years. In this paper, we first perform a classification of recent automotive cybersecurity attacks. We further perform an analysis of these attacks and associated vulnerabilities considering the application of best practices of vulnerability management approaches including Common Vulnerability Scoring System (CVSS), Exploit Prediction Scoring System (EPSS), and Stakeholder-Specific Vulnerability Categorization (SSVC). CVSS is a standardized framework used to assign severity scores to

Oka, Dennis Kengo, Vadamalu, Raja Sangili

A Large Concept Model Approach for Summarizing Automotive Documents and Enhancing Vehicle Data Query

2026-26-0676To be published on 01/16/2026

Technological advancement in automobile production, regulations, sales, and services leads to extensive technical documents and manuals. However, lengthy documentation, language barriers make it challenging to find quickly, highlighting the importance of summarization to bridge this knowledge gap. The Large Language Models (LLMs) have demonstrated impressive capabilities in tasks like Q&A, coding, drafting, and scientific acumen, and are commonly used to condense many complex documents. Despite LLMs being widely used in various sectors like research and journalism, LLMs face challenges in reliably summarizing content. Their word-by-word tokenization can sometimes fail to capture the true meaning and context, especially for abstractive summaries. This paper explores Large Concept Models (LCMs), which operate on principles of semantic reasoning, cross-modality integration, and hierarchical structuring at a higher conceptual level. This makes LCMs language and modality agnostic

Singh, Samagra, Ravi, Utkarsh, Vikram, Prateek, Shenoy, Lakshmi, Awasthi PhD, Anshuman

Machine Learning Approach to ISO Road Class Prediction Using Multiple Linear Regression

2026-26-0667To be published on 01/16/2026

The inertial profiler methodology is traditionally employed in RLDA (Road Load Data Acquisition) to measure road profiles and classify test routes into ISO road classes. However, this approach demands significant time and effort during instrumentation. Also, during data acquisition, laser height sensor data is affected especially during adverse conditions such as rainy seasons or on surfaces with improper reflectivity. Additionally, substantial resources are required for data processing to convert raw measurements into road classifications. To address these challenges, an initial attempt was made to establish a relationship between axle acceleration responses and road profiles, enabling axle acceleration measurements during RLDA to predict ISO road classes. However, this approach relied on a simple linear model that considered only axle acceleration responses, rendering the predictions susceptible to inaccuracies due to varying parameters such as vehicle speed. To overcome these

P, Praveen Kumar, P, Dayalan, Sriramulu, Yoganandam

Unlocking Edge AI in Software-Defined Vehicles: Balancing model complexity, compute resources, and data access

2026-26-0686To be published on 01/16/2026

The potential of Edge AI in automotive goes beyond ADAS and automated driving. AI-driven optimizations in driving efficiency, in-cabin personalization, predictive maintenance, and enhanced safety require intelligent processing at the vehicle edge. However, integrating AI into current vehicle electrical/electronic architectures (EEAs) presents significant challenges. This paper examines how AI models can run on general-purpose ECUs, gateways, and domain controllers while balancing model complexity, compute resources, and data availability. We explore trade-offs, architectural choices, and the need for software configurability to ensure AI models evolve with new data and vehicle parameters. We conclude by providing a glimpse into Sonatus’ latest AI product that encapsulates a holistic approach optimized for vehicle platforms—spanning cloud-based model development, optimization, and validation to in-vehicle inference—that unlocks the potential of Edge AI and SDVs for the automotive

Sah, Mohamadali, Khatri, Sanjay

Addressing Seat Belt Discomfort Among Indian Female Driving Population Through Anthropometric Data Collection and Simulation

2026-26-0016To be published on 01/16/2026

The rate of female drivers in India is increasing alongside the rapid growth of the Indian automotive industry. A driving comfort survey conducted among female drivers revealed that many experiences dis-comfort when wearing seat belts—whether while driving or as front-seat passengers. This discomfort is primarily due to a phenomenon referred to as “neck cutting.” The root cause of neck cutting is likely related to vehicle design, which is traditionally based on Anthropometric Test Devices (ATD’s) representing the 50th percentile of the global population. However, a literature review indicated that the anthropometric dimensions of the Indian populations are generally smaller than those of the global for the respective candidate. This highlighted the need to collect region-specific anthropometric data for India. During this research work, Indian anthropometric data was collected through the Size India 2.0 project, covering a wide demographic region across India. This study was in

Kulkarni, Nachiket, Chitodkar, Vivek V, Eknath Chopade, Santosh, Yamgar, Babasaheb S, Mahajan, Rahul

Artificial Intelligence in Passenger Cars: Unlocking Intelligent Mobility and Human-Centric Vehicle Innovation

2026-26-0672To be published on 01/16/2026

Artificial Intelligence (AI) is fundamentally reshaping the landscape of automotive engineering, particularly in passenger vehicles where comfort, safety, and customization are paramount. This paper presents a comprehensive review of current and emerging AI-driven applications in passenger cars, including intelligent vehicle insurance, real-time traffic optimization, personalized driving experiences, emotion recognition, and advanced EV battery management. The integration of AI technologies—ranging from machine learning and computer vision to natural language processing and deep neural networks—enables predictive maintenance, adaptive driver-assist systems, and next-generation human-machine interfaces. AI’s role in vehicle insurance is also explored through behaviour-based risk scoring and claims automation. Furthermore, emotion-aware cabin systems are discussed, which aim to detect driver fatigue, stress, or distraction to improve road safety and mental wellness. The paper also

Hazra, Sandip, Tangadpalliwar, Sonali, Khan, Arkadip

Transforming Gear Manufacturing_ A Deep Learning Approach to Quality Prediction

2026-26-0646To be published on 01/16/2026

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 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 the activity. This paper discusses methodologies to meet these requirements and achieve desired results. The research aims to develop a deep learning

Ramakrishnan, Gowtham Raj, Baheti, Palash, PR, Vaidyanathan, Durgude, Ranjit, Bathla, Archana, R, Greeshmita, V, Rangarajan

Leveraging Telematics Big Data Analytics for Real-Time Monitoring of Catalytic Converter Failures and Root Cause Identification for Emission Compliance

2026-26-0591To be published on 01/16/2026

The automotive industry is continuously evolving at high pace to meet rising customer expectations, reliability, reduced maintenance, and most relevant, compliance with stringent emission norms. Traditionally, the analysis of vehicle emissions relies heavily on periodic inspections and manual checks. These conventional methods are often time-consuming, prone to human error, and lack the ability to provide real-time insights. Also, identifying Catalytic converter failures due to non-manufacturing issues require meticulous physical inspections and historical data reviews, which are not always accurate or timely. Telematics or Connected cars technology being one of the major technological innovations in recent times revolutionizes these processes by enabling real-time data exchange between vehicles and external systems. The current study presents an innovative approach to utilizing telematics data for real-time monitoring of vehicle emissions and pinpointing Catalytic converter failures

DEV, Triyambak, Prasad, Kakaraparti Agam, Kalkur, Varun, Modak, Saikat, AGARWAL, Shashank, Chandra, Animesh, Paul, Varsha, Garg, Amit, Sundararaman, Venkataraman, Bose, Sushant

Regenerative braking control strategy for electric commercial bus under Indian road condition using artificial neural network

2026-26-0645To be published on 01/16/2026

The main objective of this research 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 the 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, road gradient, traffic condition, etc.) from real-world driving conditions and aims to train an Artificial Neural Network (ANN) using a large set of driving data collected under various conditions to predict the most efficient regenerative braking settings for different driving scenarios. While the results are

Saurabh, Saurabh, Bhardwaj, Rohit, Patil, Nikhil, Gadve, Dhananjay, Amancharla, Naga Chaithanya

A Dynamic Cybersecurity Benchmarking Framework for Automotive Cyber-Physical Systems

2026-26-0612To be published on 01/16/2026

As the automotive industry accelerates towards greater connectivity and automation, ensuring robust cybersecurity has become a critical priority, especially in emerging markets like India. This paper introduces a comprehensive framework designed to assess and enhance the cybersecurity of production-ready vehicles, with a particular focus on addressing the unique challenges posed by both domestic and international markets. The proposed system combines advanced threat modeling, vulnerability assessment, and dynamic evaluation techniques to continuously monitor and quantify a vehicle’s cybersecurity posture throughout its lifecycle. In the Indian context, where the automotive market is rapidly evolving and the adoption of connected and automated vehicles is on the rise, the need for tailored cybersecurity measures is particularly pressing. By evaluating the impact of cyber threats on safety, data privacy, financial risks, and vehicle functionality, the system generates a detailed

Shah, Ravindra, Awasthi, Vibhu Vaibhav, Karle, Ujjwala

Development of a High-Fidelity Vehicle Dynamics Model with Rear-Wheel Active Roll Control for Improved Stability

2026-26-0093To be published on 01/16/2026

This work introduces a unified vehicle dynamics framework that combines detailed modeling and active control to enhance ride comfort and handling stability. A full 12-degree-of-freedom vehicle model is developed to simulate dynamic responses across a range of driving conditions. Unlike conventional approaches, this model incorporates both linear and nonlinear tire behavior, enabling more accurate prediction of vehicle motion. To further improve performance, an active roll control mechanism is proposed, utilizing rear-wheel suspension actuators to counteract undesired body roll and yaw instabilities. A novel co-simulation environment is established by coupling MATLAB/Simulink-based control strategies with high-fidelity multibody dynamics from ADAMS Car. The model is calibrated and validated using experimental data from an instrumented test vehicle. Results show that the integrated control system significantly reduces critical parameters such as roll angle, yaw rate deviation, and

Duraikannu, Dinesh, DUMPALA, GANGI REDDY

Navigating the Field of Automotive Cybersecurity Relevant Regulations

2026-26-0623To be published on 01/16/2026

In recent years many automotive cybersecurity relevant regulations have been released and some have already started to come into effect. Moreover, some other regulations will come into effect in the next few years. These regulations provide requirements and guidance to automotive organizations with different degree of specifics. In this paper, we review a number of different cybersecurity relevant regulations such as UNR 155, UNR 156, AIS 189, AIS 190, GB 44495, GB 44496, EU Cyber Resilience Act, 15 CFR Part 791. We break down and categorize these regulations based on their scope and highlight key areas relevant to different teams within the organizations. These key areas include cybersecurity management system (CSMS), software update management system (SUMS), secure software development and software supply chain security, continuous cybersecurity activities (monitoring, incident response), and vulnerability disclosure and management. We then map responsibilities from the regulations

Oka, Dennis Kengo, Vadamalu, Raja Sangili

Automotive Cybersecurity Regulatory Framework

2026-26-0625To be published on 01/16/2026

During the last few years, cybersecurity has become one of the key aspects in the automotive industry to ensure the safety and security of vehicles throughout their lifecycle. The implementation of new technologies and the goal of deploying fully automated vehicles in the not-so-distant future have created new needs regarding vehicle safety. As the automotive industry shifts toward automated and connected vehicles, the possibility of cyberattacks emerges as a significant concern. To address these challenges, different regulatory bodies and governments worldwide have developed or are developing a new set of regulations and standards with varying approaches to legislate or standardize the minimum criteria that manufacturers must follow to ensure security against potential attacks, adding requirements to ensure the cybersecurity of the vehicles at all levels. At the United Nations level, UN Regulation 155 was introduced in 2021, establishing requirements for manufacturers' cybersecurity

Flix, Oriol, Lujan Tutusaus, Carlos, Hidalgo, Justin

Items per page:

1 – 50 of 4617