Browse Topic: Data acquisition and handling

Items (6,101)
Find
Dynamic Stiffness Prediction in Cracked Cantilever Beams Using Enhanced ANN Techniques2026-28-0050To be published on 02/12/2026
This research paper presents an in-depth investigation into the application of Artificial Neural Networks (ANN) for predicting the dynamic stiffness characteristics of cantilever beams affected by cracks of varying depths and positions. Structural failure due to vibration remains a critical concern, and this study focuses on how crack-induced changes in modal stiffness compromise structural reliability. A significant research gap identified in previous studies is the limited consideration of crack location; this work addresses that gap by analyzing how both crack depth and position influence the natural frequency of the beam. Using modal analysis on cantilever beams with identical dimensions but different crack configurations, it was observed that deeper cracks and cracks near the fixed support led to a marked reduction in natural frequency, making the structure more vulnerable to resonance. Cracks located at the free end, however, showed negligible impact. To model and predict these
SB, Harshini, Rajkumar, Manjari, R, Krithika, K, Anusha, K, Divya, Bhaskara Rao, Lokavarapu
Achieving Reliability, Safety & Security in SDV OS Architecture2026-28-0122To be published on 02/12/2026
Software-Defined Vehicles (SDVs) are vehicles in which functionality and features are primarily governed by software, allowing for continuous updates, upgrades, and the introduction of new capabilities throughout the vehicle’s lifecycle. This transition from hardware-centric to software-driven architectures marks a significant shift in the automotive industry, transforming development processes, operational strategies, and business models. The SDV Operating System (SDV OS) is purpose-built for software-defined vehicles, serving as the foundational platform for managing vehicle software and enabling advanced functionalities. Unlike traditional embedded or general-purpose operating systems, SDV OS is tailored to meet the unique requirements of modern automotive architectures. Ensuring reliability, safety, and security is paramount in software-defined vehicles (SDVs), where even minor software faults can lead to serious consequences. The operating system (OS) plays a central role in
KHAN, Misbah Ullah, Gupta, Vishal
AI Smart Timer-Based Power Control and Energy Monitoring System for Home Appliances2026-28-0060To be published on 02/12/2026
This paper presents an intelligent home automation system that combines timer-based power control, real-time energy monitoring, and cloud-based AI analytics for individual appliances. The system is built using a Wi-Fi-enabled embedded controller connected to sensing circuits that measure voltage, current, and power consumption. Electromechanical relays are used to control appliance power based on user-defined timers. Users can configure either a fixed runtime or a scheduled cutoff, enabling automated energy-saving without manual input. Alongside local control, the system collects energy consumption data and transmits it to a cloud platform for storage and analysis. A dedicated mobile or web app provides live monitoring, device status, and remote control access. A major innovation is the integration of a cloud-based AI engine that processes historical and real-time data to offer predictive insights. The AI module forecasts energy use, detects anomalies, classifies appliances by behavior
D, Anitha, D, Suchitra, Jain, Utsav, MAITY, SOUVIK, Dinda, Atish
Automotive Ethernet Proxy-Based Security Architecture In Vehicle Computers2026-28-0121To be published on 02/12/2026
Modern vehicles require sophisticated, secure communication systems to handle the growing complexity of automotive technology. As in-vehicle networks become more integrated with external wireless services, they face increasing cybersecurity vulnerabilities. This paper introduces a specialized Proxy based security architecture designed specifically for IP-based communication within vehicles. The framework utilizes proxy servers as security gatekeepers that mediate data exchanges between Electronic Control Units (ECUs) and outside networks. At its foundation, this architecture implements comprehensive traffic management capabilities including filtering, validation, and encryption to ensure only legitimate data traverses the vehicle's internal systems. By embedding proxies within the automotive middleware layer, the framework enables advanced protective measures such as intrusion detection systems, granular access controls, and protected over-the-air (OTA) update channels. This strategy
M, Arvind, Praneetha, Appana Durga, Remalli, Ravi Teja
MINER’S SAFETY BOT2026-28-0116To be published on 02/12/2026
Mining remains one of the most hazardous industries, with workers constantly exposed to life-threatening conditions such as toxic gases, high temperatures, and confined spaces. To address these concerns, we propose the design and development of an autonomous Miner’s Safety Bot aimed at enhancing underground safety through real-time environmental monitoring and intelligent navigation. The system is built around the ESP32 microcontroller, integrating critical sensors including the MQ7 gas sensor for detecting carbon monoxide and methane, the DHT11 sensor for measuring ambient temperature, and an ultrasonic sensor for obstacle detection. These components work to monitor hazardous parameters and assist the bot in navigating through narrow mine shafts. A servo motor connected to a remote-controlled chassis adjusts the bot's direction when obstacles are detected. The bot employs the ESP32-CAM module to transmit live visuals from the mining site to external observers. Furthermore, sensor data
D, SUCHITRA, D, ANITHA, MUTHUKUMARAN, BALASUBRAMANIAM, MOHANRAJ, SIDDHARTH, SUBASH CHANDRA BOSE, ROHAN
IoT-Enabled Cloud-Integrated Smart Parking System with Real-Time Monitoring and AI-Based Space Optimization for Next-Gen Mobility2026-28-0113To be published on 02/12/2026
This study presents the design and implementation of an advanced IoT-enabled, cloud-integrated smart parking system, engineered to address the critical challenges of urban parking management and next-generation mobility. The proposed architecture utilizes a distributed network of ultrasonic and infrared occupancy sensors, each interfaced with a NodeMCU ESP8266 microcontroller, to enable precise, real-time monitoring of individual parking spaces. Sensor data is transmitted via secure MQTT protocol to a centralized cloud platform (AWS IoT Core), where it is aggregated, timestamped, and stored in a NoSQL database for scalable, low-latency access. A key innovation of this system is the integration of artificial intelligence (AI)-based space optimization algorithms, leveraging historical occupancy patterns and predictive analytics (using LSTM neural networks) to dynamically allocate parking spaces and forecast demand. The cloud platform exposes RESTful APIs, facilitating seamless
Deepan Kumar, Sadhasivam, S, Balakrishnan, Dhayaneethi, Sivaji, Boobalan, Saravanan, Abdul Rahim, Mohamed Arshad, S, Manikandan, R, Jamuna, L, Rishi Kannan
Real time implementation of predictive maintenance for service center automation using Automobile Life Extender (ALE) based on Machine Learning2026-28-0124To be published on 02/12/2026
Automobile Life Extender (ALE) consists of an on-board function, machine learning model operating via cloud computing and a smart phone app. The on-board function will receive signals like engine rpm, throttle position, Brake pedal position, hydraulic pressure etc from vehicles Ecu’s. Based on this data onboard ALE module will calculate the engine load, brake circuit load etc . and sends it to the predictive maintenance model via on board IoT system. The predictive maintenance model will have historical data about the type of engine, brake system and their performance curve data acquired based on test done by its OEM. Here machine learning models play a crucial role in analyzing the vehicle data dynamically, identify drive patterns from it and predict the need for maintenance of a part or a system. A hybrid approach of training models based on Supervised and Unsupervised is incorporated, which will work with certain amount of labeled data along with a set of collected unlabeled data
sundaram, Rameshselvakumar, Kumar, Lokesh, Saint Peter Thomas, Edwin, Sureshkumar, Srihari, Muthukumaran, Chockalingam, Menon, Abhijith
Preliminary Design and Analysis of Dual Throat Fluidic Thrust Vectoring Nozzle for Supersonic Aerospace Application2026-28-0106To be published on 02/12/2026
The project investigates the performance characteristics of dual-throat nozzle used for fluidic thrust vectoring (FTV) in supersonic aircraft applications, offering a potential alternative to mechanical vectoring methods. Fluidic thrust vectoring provides benefits such as reduced weight, lower radar signature, and improved manoeuvrability and control. Computational methods are used to study the effects of geometric and operational parameters, including nozzle pressure ratios and secondary injection rate and injection angle, on thrust-vectoring efficiency and system dynamics. The study aims to develop optimized design configurations and validate using computational models.
Suresh, Vignesh, M, Akash, SENTHILKUMAR, NIKIL, Sundararaj, Senthilkumar, A, Garry Kiristen, Singh, Swaraj
TOPSIS-Based Multi-Criteria Optimization of WAAM Parameters for Automotive Component Fabrication2026-28-0026To be published on 02/12/2026
Wire Arc Additive Manufacturing (WAAM) can make huge, complicated metal parts quickly and cheaply, making it popular in the automobile sector. This study uses TOPSIS, a multi-criteria decision-making method, to improve WAAM process parameters such wire feed rate, travel speed, and current. Automotive applications need surface roughness, deposition rate, and dimensional precision, which WAAM-fabricated components must meet. TOPSIS normalizes and ranks experimental findings to find parameter combinations that perform best across many quality metrics. The results show that integrated optimization improves component quality and consistency, making WAAM a feasible and economical sustainable vehicle manufacturing option.
Pasupuleti, Thejasree
Parameter Optimization for Improved Surface Finish in WAAM-Fabricated Steel Structures2026-28-0023To be published on 02/12/2026
Wire Arc Additive Manufacturing (WAAM) is a cost-effective and scalable metal additive manufacturing technique widely used for fabricating large metallic components. However, surface finish remains a critical challenge, especially for structural applications where post-processing needs to be minimized. This study focuses on optimizing key process parameters to improve the surface finish of ER70S-6 steel structures fabricated using the WAAM process. Experiments were designed using a statistical approach to systematically vary parameters such as wire feed rate, travel speed, voltage, and inter-pass cooling time. Surface roughness was measured using standard metrology tools, and the results were analyzed to identify the most influential parameters. An optimized parameter set was proposed based on the experimental outcomes, leading to a significant reduction in surface roughness without compromising the structural integrity of the deposited material. The findings contribute to enhancing
PN, Vani
Experimental Investigation of Process Parameter Effects in WAAM of Nickel-Based Alloys2026-28-0027To be published on 02/12/2026
Wire Arc Additive Manufacturing (WAAM) is an evolving discipline in metal additive manufacturing characterized by rapid deposition, cost-effectiveness, and centrality to the near-net-shape fabrication of large-scale components. This study will concentrate on WAAM application to deposit nickel alloys, which find extensive use in aerospace, power generation, and marine industries, due to their good mechanical strength, corrosion resistance, and thermal stability. However, some drawbacks in WAAM processing of nickel alloys include thermal distortion, porosity, and residual stress. The research looks at how key WAAM process parameters, including wire feed rate, travel speed, current, and interpass temperature affect geometric accuracy, surface integrity, and mechanical performance of the fabricated components. Microstructural characterization was done using optical microscopy, and hardness distribution was measured as an indication of mechanical uniformity throughout the builds. It is
Natarajan, Manikandan
Effect of Minimum Quantity Lubrication during Machining of Incoloy 800H Using Vegetable Oil Enriched With Nano Particles2026-28-0038To be published on 02/12/2026
In this experimental work an effort has made to investigate the machining of difficult to machine Incoloy 800H super alloy. Cryogenically treated textured cutting inserts and vegetable oil enriched with nano particles were used for this study. The turning experiments were performed with different parameters such as Cutting speed, feed rate and depth of cut. Surface Roughness, Cutting Force, Tool-Tip Temperature and Power were the output responses considered. Grey Relational Analysis (GRA) and Analysis of Variance (ANOVA) analysis were used to optimize the machining parameters and to find the most influencing machining parameter on the output responses. The results showed that the optimal machining conditions considered were cutting speed at 35 m/min, feed rate at 0.06 mm/rev and depth of cut at 0.5 mm for the multiple-characteristic performances and it was improved by 3.86 % with this approached method. Also, Tool-tip temperature and Power were reduced during machining with cryo
Natarajan, Manikandan
Quantum Meets Agile: Crypto-Agility for a Post-Quantum World2026-28-0127To be published on 02/12/2026
As the automotive industry transitions toward software-defined vehicles and connected ecosystems, cybersecurity becomes a critical design pillar. A pressing challenge emerges with the advent of quantum computing, which threatens to render existing cryptographic standards such as RSA and ECC obsolete. This paper addresses the need for quantum-resilient security architectures in the automotive domain by introducing a combined approach using Post-Quantum Cryptography (PQC) and crypto-agility. Unlike traditional static cryptographic systems, our approach leverages agile architectures that enable seamless integration of new cryptographic algorithms as they emerge. Central to our work is the role of Hardware Security Modules (HSMs), which provide secure, tamper-resistant environments for cryptographic operations within vehicles. We explore how HSMs can evolve into crypto-agile and quantum-safe platforms capable of supporting hybrid and post-quantum algorithms, allowing secure transitions
Kuntegowda, Jyothi
Effect of Sebastiana rostrata Fiber Loading on the Tribological Behaviour of Polycaprolactone Biocomposite.2026-28-0021To be published on 02/12/2026
This study investigates the tribological performance of Sesbania rostrata fibers (SRFs) reinforced polycaprolactone (PCL) composites, focusing on the effects of fiber loading under varying normal loads. Composite samples with fiber contents of 10%, 20%, and 30% were tested at sliding velocities of 0.5 m/s and a fixed sliding distance of 500 m. Results show that the inclusion of SRFs significantly reduces the coefficient of friction (COF) and specific wear rate (SWR) compared to neat PCL, particularly at fiber loadings up to 20%. Beyond this threshold, fiber agglomeration leads to increased wear. The results highlight the potential of SRF/PCL composites for use in wear-critical automotive and orthopedic applications due to improved load-bearing capability and surface resistance.
Raja, K., Senthil Kumar, M.S.
Evolution of a Novel Hybrid Stab-Link for a Born Electric Sports Utility Vehicle2026-28-0001To be published on 02/12/2026
The present study details the design evolution and failure analysis of a novel hybrid stabilizer bar link (stab link) developed for the front suspension of a born electric sports utility vehicle (SUV) platform characterized by higher gross vehicle weight (GVW), increased wheel travel, and constrained packaging space. To address these challenges, a unique hybrid stab link was designed featuring dual plastic housings at both the metal ball joint ends, connected by a steel tube, and achieving a 30% weight reduction while offering enhanced articulation angles for extremely lower turning circle diameter (TCD) of the vehicle, compared to the conventional stab link. The unique hybrid stab failed under complex loading conditions during accelerated durability testing (ADT), prompting a comprehensive investigation. The failure analysis included road load data acquisition across various stab bar diameter configurations evolved during suspension tuning, different stabilizer link designs evolved
SELVENDIRAN, P, J, Ramkumar, NAYAK, Bhargav, M, Sudhan, Patnala, Avinash
Multi-Objective Optimization of WAAM for Sustainable Production of Automotive-Grade Components2026-28-0030To be published on 02/12/2026
Wire Arc Additive Manufacturing (WAAM) has emerged as a promising technology for fabricating large-scale metal components with reduced material waste and lead time, aligning with the goals of sustainable manufacturing. This study presents a multi-objective optimization approach for WAAM to enhance both the manufacturing efficiency and sustainability of automotive-grade components. Key process parameters such as travel speed, wire feed rate, and current were systematically varied to evaluate their impact on dimensional accuracy, mechanical performance, and energy consumption. A statistical design of experiments framework was employed, and multiple performance objectives were optimized simultaneously using suitable decision-making techniques. The results demonstrate that optimized WAAM settings not only meet structural and functional requirements for automotive applications but also contribute to material and energy savings. This approach supports the integration of sustainability into
Pasupuleti, Thejasree
Statistical Optimization of Wire Arc Additive Manufacturing Parameters Using Taguchi Methodology2026-28-0035To be published on 02/12/2026
Wire Arc Additive Manufacturing (WAAM) is an emerging metal additive manufacturing process known for its high deposition rates and cost-effectiveness in fabricating large-scale components. However, the quality of the final build is highly sensitive to process parameters such as wire feed rate, travel speed, voltage, and current. In this study, the Taguchi method is employed to statistically optimize key WAAM process parameters with the aim of improving surface finish and mechanical integrity of the deposited parts. An L9 orthogonal array was used to design experiments, and signal-to-noise (S/N) ratios were analyzed to identify optimal parameter settings. Analysis of variance (ANOVA) was performed to determine the significance of each factor on the selected output responses. The results demonstrated that specific combinations of process parameters can significantly reduce surface roughness and enhance bead geometry. The optimized settings obtained through the Taguchi approach provide a
PN, Vani
Parameter Selection Strategies for High-Performance WAAM Structures in Automotive Engineering2026-28-0033To be published on 02/12/2026
Wire Arc Additive Manufacturing (WAAM) has gained traction as an advanced fabrication technique for producing large, structurally demanding components in the automotive industry. Achieving high-performance WAAM structures requires precise control and selection of key process parameters, which directly influence mechanical strength, dimensional accuracy, and surface quality. This study investigates the effect of critical process variables—including wire feed rate, travel speed, current, voltage, and inter-layer cooling time—on the structural integrity of WAAM-fabricated components designed for automotive use. A systematic experimental approach, supported by statistical modeling and optimization tools, was employed to identify parameter combinations that yield optimal results. The outcomes demonstrate improved microstructural uniformity, reduced residual stresses, and enhanced tensile properties in the fabricated parts. The findings serve as a foundation for developing robust parameter
V, Aravind
Statistical Modeling of Wire Arc Additive Manufacturing Parameters Using Regression Analysis2026-28-0024To be published on 02/12/2026
Wire Arc Additive Manufacturing (WAAM) is gaining prominence for fabricating large metal components due to its high deposition rate and cost-effectiveness. However, the quality and performance of WAAM-fabricated parts are strongly influenced by process parameters such as wire feed rate, travel speed, arc voltage, and current. This study presents a statistical modeling approach using regression analysis to predict the effects of these key parameters on critical output responses, including bead geometry, surface roughness, and material deposition rate. Experiments were designed using a structured methodology, and the collected data were analyzed to develop linear and multiple regression models. The accuracy and reliability of the models were evaluated using statistical metrics such as R² and p-values. The results demonstrate that regression-based models can effectively predict WAAM outcomes, enabling process optimization and quality control. This approach provides a valuable tool for
Pasupuleti, Thejasree
Quantifying the Energy Consumption of HVAC Operation and Its Impact on the Range of Electric Buses Across Diverse Climatic Conditions2026-26-0204To 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, Saraswat, Shubham, Joshi, Madhusudan
Swarm-Inspired Cooperative Mapping for Urban Autonomous Navigation2026-26-0635To 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
Extreme Learning Machines (ELM) for Fast Instantaneous Prediction of Emission Level of an Automobile2026-26-0226To 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 Factory Modelling: Integrating Drone Technology and Automated Post Processing Systems2026-26-0307To 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
A Data-Centric Approach to Identify Optimal NVH simulation Tools and Solvers2026-26-0356To 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
Integrating V2V and V2I Communications for Enhanced Traffic Safety and Efficiency in Connected Vehicular Networks2026-26-0271To 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
Software-Defined Vehicles: Architecting the Future of Intelligent and Connected Mobility2026-26-0691To 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
Security monitoring for High Performance Vehicle Computers2026-26-0627To 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
Feasibility and Performance of Post-Quantum Cryptography on Embedded Systems for Two-Wheeler Security2026-26-0622To 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
Automotive Cybersecurity: Safeguarding Connected and Autonomous Mobility2026-26-0629To 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
Proactive AI-Enhanced Cybersecurity for Next-Gen Automotive Infotainment ECU2026-26-0619To 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
GTSRB-Shield: A Novel Machine Learning Framework for Intrusion Detection in Autonomous Vehicles Leveraging the German Traffic Sign Recognition Benchmark2026-26-0611To 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
Driving behavior modelling with Graph Attention Networks using spatial data2026-26-0661To 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
A Mathematical Modelling Approach Based on Artificial Neural Network for Estimation of Key Parameters in Internal Combustion Engine2026-26-0659To be published on 01/16/2026
In a conventional powertrain driven by Internal combustion (IC) engines, various sensors are used to monitor engine performance and emissions. Along with physical sensors, virtual sensors or modelled values of key parameters play an important role for enabling various diagnostics strategies and engine monitoring. Conventional strategies for modelling incorporate the use of regression models, map-based models and physics-based models which have few drawbacks in terms of accuracy and model calibrations efforts. Data driven models or neural networks have fairly better accuracy and reliability for estimating complex parameters. Representing the neural network with a mathematics-based model would help to eliminate drawbacks associated with conventional modelling approach. The proposed methodology uses artificial intelligence technique called artificial neural network (ANN) for estimation of temperature at turbine inlet (TTI) in typical diesel engine. The data driven model is built in Python
Jagtap, Virendra Shashikant, Shejwal, Sanket, Mitra, Partha
A Digital Twin Framework for Real-Time Optimization of Solar-Integrated Energy Systems2026-26-0418To 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
Automotive Cybersecurity Incident Response (CSIR) Framework and Its Integration into OEM Processes2026-26-0613To 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
Accelerating Product Development Life Cycle through Digitalization of Fatigue Life for Structural Components2026-26-0496To 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
Development of an Software Algorithm Based Semi-automated Data Acquisition System for Gasoline Vehicle Calibration on Chassis Dynamometer2026-26-0535To 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
Generative AI based methodology for Road Profile Mix Creation2026-26-0674To 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
Real-time Intrusion Detection System (IDS) for Vehicle Networks Using Machine Learning for Predictive Threat Analysis2026-26-0617To 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
Optimizing Suspension Joint Reliability: Overcoming Bolt Loosening and Torque Variability in Automotive Production2026-26-0492To 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 Performance-driven Numerical Approach for Optimizing the Plenum Opening Area of Cowl Box2026-26-0461To 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, Mahesh, A, Gopinathan, Nagarajan
Innovative Multi-Axial Testing approach for Enhanced Reliability of Cooling Modules in Commercial Vehicles2026-26-0530To 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 Quality-Driven Approach to Engineering Sign-Off for Software and Robust Product Development2026-26-0581To 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
Multi-Band Frequency Approach to Correlate Proving Ground and Road Simulator for an Electric Two-Wheeler2026-26-0556To 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
Navigating the Field of Automotive Cybersecurity Relevant Regulations2026-26-0623To 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, and BIS Final Rule. 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
Oka, Dennis Kengo, Vadamalu, Raja Sangili
MOSAIC-TARA: A Comprehensive TARA Methodology for Automotive Cybersecurity2026-26-0609To be published on 01/16/2026
Threat Analysis and Risk Assessment (TARA) is a continuous activity, acting as a foundation of cybersecurity analysis for electrical and electronics automotive products. Existing TARA methodologies in the automotive domain exhibits challenges due to redundant and manual processes, particularly in handling recurring common assets across Electronic Control Units (ECUs) and functional domains. Two primary approaches observed for performing TARA are Manual-Asset-Centric TARA and Catalogue-Driven TARA. Manual-Asset Centric TARA is constructed from scratch by manually identifying the assets, calculating risks by likelihood, and impact determination. Catalogue-Driven TARA utilizes the precompiled likelihood and impact against identified assets. Both approaches lack standardized and modular mechanisms for abstraction and reuse. This results in poor scalability, increased efforts, and difficulty in maintaining consistency across vehicle platforms. The proposed method in this research overcomes
Goyal, Yogendra, Sinha, Swati, Sutar, Swapnil, Jaisingh, Sanjay
Transforming Gear Manufacturing_ A Deep Learning Approach to Quality Prediction2026-26-0646To 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
Artificial Intelligence in Passenger Cars: Unlocking Intelligent Mobility and Human-Centric Vehicle Innovation2026-26-0672To 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
Enhancing Engine Reliability Testing with IoT, AI and ML: Real-Time ML-based Limit Monitoring and Predictive Maintenance with IoT sensor2026-26-0647To 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
Comprehensive Durability Assessment of Planet Carrier in Heavy-Duty Tipper Gearboxes Using RLDA Torque Data2026-26-0443To be published on 01/16/2026
In heavy-duty tippers, where challenging conditions demand high torque, planet carriers play a crucial role by enabling efficient load distribution and torque transmission while supporting gear ratio and speed variation in space-constrained systems such as automatic transmissions, hybrid drivetrains, and electric vehicles. This paper focuses on the comprehensive durability performance assessment of planet carriers using duty cycles derived from RLDA measurements for a heavy-duty tipper gearbox development program. The existing Design Validation Plan (DVP) for the planet carrier considers first gear utilization of 10-15% at 40% vehicle overload, in line with historical data. However, recent trends in mining applications revealed vehicle overloads of 55-65%, leading to an increase in first gear utilization (25-35%). This shift presents challenges for OEMs to enhance design durability while incorporating additional safety margins to meet the demands of a competitive, cost-driven market
Bagane, Shivraj, Pendse, Ameya
Items per page:
1 – 50 of 6101