Browse Topic: Artificial intelligence (AI)

Items (2,572)
Find
Application of Deterministic and AI-Based Methods to Accelerate the Component-Level Development Process in Electric Vehicles2026-01-0766To be published on 07/01/2026
The global automotive landscape is undergoing a significant paradigm shift driven by the rapid development cycles of emerging competitors, leaving traditional European OEMs with a critical time-to-market gap. To bridge this gap, automotive engineering must pivot from traditional hardware-based processes toward agile, digital data-driven methodologies. This paper presents a comprehensive feasibility study on the implementation of data-centric approaches, using both Artificial Intelligence and deterministic methodologies, with focus on accelerating component development. It provides a detailed assessment of various AI-based and deterministic methodologies at specific stages of the product development process, targeting both: 1. Product design 2. Product development process The aim is to enhance component-level performance, quality, and functionality, while simultaneously optimizing workflows, increasing process and development efficiency, and facilitating knowledge reuse throughout the
Bode, Jana Pascal, Kröll, Sarah, Vohwinkel, Nikolaus, Paetzold-Byhain, Kristin
Generating Machine-Processable Specifications from Natural Language Using Large Language Models in Automotive Commissioning and Testing2026-01-0768To be published on 07/01/2026
The commissioning of electric and electronic components contributes significantly to adding value in vehicle production. Moreover, testing these components and digital vehicle functions secures this value and ensures high-quality products. The emergence of software-defined vehicles, however, leads to an increased scope and complexity of commissioning and testing processes as software functions depend on electric and electronic components that take on perception, execution, and processing tasks. Nevertheless, assembly planning must still meet the requirement of providing thorough, error-free, yet cost-effective processes. In this context, this paper tackles a common challenge: Software that is deployed in vehicle production to implement commissioning and testing processes is developed upon specifications that define prerequisites, procedures, and target end results in unstructured natural language. Therefore, extensive manual translation into executable code is needed, being susceptible
Köhler, Katja, El Asad, Aiman, Hahn, Michael, Reuss, Hans-Christian
Who’s Riding? Machine Learning-Powered Rider Identification from E-Bike CAN Data2026-01-0778To be published on 07/01/2026
This study investigates the feasibility of identifying individual e-bike riders based on Controller Area Network (CAN) data using machine learning techniques. Datasets from 12 test riders performing various predefined cycling tasks on a dynamometer test bench are collected and used to ensure controlled and reproducible conditions. The recorded CAN data includes various sensor signals, such as power output, cadence, torque, and the used support mode. After pre-processing, two different methods of feature extraction are tested and compared, one based on snapshots of the data and one based on driving events such as braking and accelerating, measured by calculating statistics of the riding data over sliding windows. A range of machine learning models is employed to classify riders based on their distinct riding patterns using the extracted features. The evaluated models comprise k-Nearest Neighbors (KNN), Random Forest and Naive Bayes. The findings demonstrate the efficacy of machine
Simmann, Gabriel, Rauch, Yannick, Beißert, Florian, Kriesten, Reiner
Interpretable Tire Force Modeling for Formula Student Vehicle Dynamics and Lap Time Applications2026-01-0762To be published on 07/01/2026
Accurate tire models are a key enabler for vehicle dynamics simulation, control design, and lap time optimization, particularly in the context of Formula Student race cars, where vehicle setups and tire characteristics differ significantly from production vehicles. State-of-the-art tire models, such as Pacejka’s Magic Formula, provide high accuracy but rely on predefined functional structures and a large number of parameters, which limits interpretability and adaptability to new tire compounds. This paper presents a data-driven approach for deriving compact and physically interpretable tire force models using symbolic regression. The proposed method employs an intelligent tree search to systematically explore the space of mathematical expressions and identify models that optimally balance prediction accuracy and structural simplicity. In contrast to black-box machine learning approaches, the resulting models consist of explicit mathematical expressions that enable physical
Anselment, Marcel, Borowski, Julian, Rudolph, Stephan
Multi-Agent LLM Architecture for Systems Engineering Automation2026-01-0777To be published on 07/01/2026
The increasing complexity of modern software-intensive systems, particularly in the automotive domain, demands new approaches to bridge the gap between high-level engineering specifications and executable, safety-compliant code. This need is amplified by the rapid transition toward software-defined vehicles (SDVs), where highly dynamic, updateable software functions significantly enlarge the scope and frequency of engineering activities and require scalable, transparent, and adaptive development processes. While recent advances in Large Language Models (LLMs) have demonstrated strong capabilities in automating tasks such as requirements analysis, code generation, and documentation, their deployment in safety-critical engineering workflows remains challenging due to the need for transparency, traceability, and controlled decision-making. This paper presents a modular multi-agent LLM pipeline that automates key steps of the systems engineering lifecycle - from requirement structuring and
Padubrin, Marcel, Kulzer, Andre Casal, Guerocak, Erol
Vision-Language Model Training for Code Generation from Requirements and Model-Based Artifacts2026-01-0770To be published on 07/01/2026
Recent advancements in Vision-Language Models (VLMs) have opened new possibilities for bridging the gap between Systems Engineering artifacts and automated code generation. Traditional Large Language Models (LLMs) are primarily trained on textual data and generic code repositories, which limits their ability to interpret graphical engineering artifacts such as Simulink block diagrams or system architecture models. In safety-critical domains like the automotive industry, these graphical models are central to development workflows and must remain closely aligned with textual requirements and implementation code to ensure traceability, compliance, and functional correctness. This paper proposes a VLM-centered multimodal training framework for code generation that integrates textual requirements, graphical model-based artifacts, and annotated source code into a unified learning process. By leveraging models which combine vision encoders with language backbones, the approach enables the
Padubrin, Marcel, Kulzer, Andre Casal, Guerocak, Erol
Kolmogorov-Arnold Networks in Industrial Application of Truck Development2026-01-0760To be published on 07/01/2026
Kolmogorov-Arnold Networks (KANs) are a novel mathematical method to generate data-driven AI surrogate models. Compared to neural networks based on the MLP standard (Multi-Layer Perceptron), these offer further mathematical interpretability and thus allow improved validation of AI for industrial applications. In this paper, we use KANs to generate an AI vehicle model of a truck as a mathematically precise AI surrogate model. To do this, we combine the KAN approach with the approach of Neural Ordinary Differential Equations (Neural ODEs) to generate predictions for the time-series of the truck’s velocity. Furthermore, we compare the results of the AI based on KANs with the traditional approach using MLP in terms of model size, accuracy, and computational time in order to evaluate advantages and disadvantages of the KAN approach. The best AI-KAN vehicle model identified in this way is then embedded in a co-simulation via the Functional Mockup Interface standard, thus opening up a wide
Vaudrevange, Patrick K.S., Halverson, James, Ruehle, Fabian, Fabcic, Tomaz, Dingler, Christian, Piskala Dilipkumar, Santhoshkumar, Ibrahim, Muhammed, Herrnberger, Michael, Kasper, Johanna, Türk, Lars, Keckeisen, Michael
Production-Ready Automated ECU Calibration using Residual Reinforcement Learning2026-01-0780To be published on 07/01/2026
Electronic Control Units (ECUs) have played a pivotal role in transforming motorcars of yore into the modern vehicles we see on our roads today. They actively regulate the actuation of individual components and thus determine the characteristics of the whole system. In this, the behavior of the control functions heavily depends on their calibration parameters which engineers traditionally design by hand. This is taking place in an environment of rising customer expectations and steadily shorter product development cycles. At the same time, legislative requirements are increasing while emission standards are getting stricter. Considering the number of vehicle variants on top of all that, the conventional method is losing its practical and financial viability. Prior work has already demonstrated that optimal control functions can be automatically developed with reinforcement learning (RL); since the resulting functions are represented by artificial neural networks, they lack
Kampmeier, Andreas, Badalian, Kevin, Koch, Lucas, Lee, Sung-Yong, Andert, Jakob
Development of a digital twin of an electrical powertrain in a testbench environment for efficiency estimations2026-01-0744To be published on 07/01/2026
The aim of this work is to develop a modular digital twin of an electric powertrain based on novel machine learning (ML)-based model structures and a systematic, component-oriented architecture. This results in a modular, real-time-capable digital twin that precisely maps the efficiency characteristics of the entire drivetrain and can be used in development and testing processes. The further goal here is to enable virtual testing, which can be used for frontloading and thus both prevent errors and increase the speed of product development. Based on a comprehensive set of measurement data from a test bench, a multi-stage procedure is implemented that integrates data acquisition, physically informed feature selection, modeling at the component and subsystem level, and hybrid coupling strategies. The digital twin captures inverter, electric machine, and mechanical transmission stages and generates physically consistent predictions of key variables such as torque, speed, power factors, and
Kopp, Lennart, Proksch, Daniel, Ockert, Niels, Karthaus PhD, Carsten, Kley, Markus
An Application-Oriented Process Model for Selecting Uncertainty Quantification Methods in Machine Learning2026-01-0773To be published on 07/01/2026
This paper presents an application-oriented process model for selecting uncertainty quantification methods in machine learning. The work is motivated by the increasing relevance of uncertainty quantification in product engineering applications, including the automotive domain, where reliable decision making under uncertainty is essential. In this context, machine learning is widely used in data mining to derive knowledge about systems and user behavior from data and to make this knowledge accessible to product developers. As these applications increasingly influence engineering decisions, the assessment and communication of uncertainty become critical requirements. Each data mining task is unique and no single algorithm is optimal for all tasks. This observation motivates the need for a structured process model to support the selection of appropriate uncertainty quantification methods in machine learning. The proposed process model builds on established problem-solving methods and
Holderied, Niklas, Hörtling, Stefan, Bause, Katharina, Düser, Tobias
Harmonizing Generative AI and ISO 26262 for Safe and Intelligent ADAS Systems2026-01-0785To be published on 07/01/2026
The convergence of Generative AI (GenAI) and Functional Safety (FuSa) under ISO 26262 is reshaping Advanced Driver Assistance Systems (ADAS) by merging adaptive intelligence with stringent safety assurance. GenAI significantly improves perception, object classification, pedestrian intent prediction, and risk assessment, empowering vehicles to navigate highly dynamic, real-world environments. Furthermore, GenAI-driven synthetic data generation accelerates ADAS validation by enabling exhaustive testing of rare and safety-critical scenarios not covered by conventional datasets. However, the integration of GenAI into safety-critical automotive systems introduces major challenges. Its probabilistic nature, limited transparency, and vulnerability to adversarial inputs directly conflict with ISO 26262 principles that demand determinism, traceability, and fault isolation. This paper proposes a co-engineering framework that combines GenAI’s learning-based adaptability with deterministic safety
Jain, Yesha
Development of a Convolutional Autoencoder-Based Unsupervised Classification and Visualization Model for Extracting Feature Frequency in C-EPS Fault Diagnosis2026-01-0717To be published on 06/20/2026
In the automotive industry, deep learning models such as convolutional neural networks, autoencoders, and transformers have been actively studied to improve defect detection rates in End-of-Line (EOL) processes. However, applying these approaches to the field of Noise, Vibration, and Harshness (NVH) faces several practical challenges. ① Difficulty in securing sufficient training data and risk of overfitting due to longer evaluation times compared to other data types. ② Label imbalance caused by the relatively small amount of defective data. ③ Reduced labeling accuracy due to human error. ④ Decreased model robustness under domain shifts such as jig variations, evaluation environments, signal-to-noise ratio (SNR), and the occurrence of new abnormal noises. ⑤ Constraints in application due to compatibility issues with existing evaluation equipment. To address these issues, this study proposes an unsupervised learning-based method for classifying operating noise data of Column-type
Park, Jun-Seo, Jo, Hyeon-Choel, Cho, In-Je, Seo, Jae-Yong, Yoo, Seong-Sik
Active Learning Supported Metadata Extraction from NVH Simulations2026-01-0720To be published on 06/20/2026
Simulations can only be searched, reused and leveraged as trainings data for machine learning methods if they possess suitable metadata. Manually obtaining this metadata is time-consuming and requires expert knowledge. Consequently, there is often a lack of metadata, and this prohibits the reutilisation of simulation data. Therefore, automated frame works for metadata extraction are essential to quickly, effortlessly and cost-efficiently obtain this information. At present, there are no existing toolboxes for Finite-Element-Simulation data and current Large Language Models are not usable. Nevertheless, machine learning methods are a promising solution for this task. However, classical supervised machine learning methods cannot be used due to the high effort for labelling. Therefore, classical rule-based extraction algorithms are an alternative for fundamental metadata extraction. For more enhanced tasks, where more context is necessary, they are not usable. Active Learning is the
Luegmair, Marinus, Gröttrup, Sören
AI-Based Package Tray Design Method for Controlling Acoustic Modes in a Sedan2026-01-0716To be published on 06/20/2026
• In this study, we propose a methodology for predicting the acoustic modes and natural frequencies of a sedan using artificial intelligence and demonstrate the feasibility of controlling its acoustic characteristics by modifying the hole distribution of the package tray. In typical sedan structures, the cabin cavity and trunk cavity are acoustically coupled through holes in the package tray. The distribution of these holes significantly affects the natural acoustic modes and frequencies of the vehicle. However, once the exterior shape of the vehicle is finalized during the design phase, options for structural modifications to mitigate noise issues caused by these modes become extremely limited. To address this challenge efficiently, we develop a deep learning-based neural network model trained on data derived from a simplified acoustic analysis model of a sedan that includes a package tray. Finite element analysis is performed to generate acoustic modes and natural frequencies, which
Lee, Jin Woo, Cho, Jaeho, Nam, Younsic, Han, Yongha
Best-in-Class NVH Optimisation for Electric Powertrains, Holistic Front-Loading Approaches2026-01-0689To be published on 06/20/2026
Achieving best-in-class Noise, Vibration, and Harshness (NVH) in electric powertrains demands a paradigm shift in development methodology. This paper presents a holistic, front-loaded approach to NVH optimisation, leveraging simulation models, machine learning, and target cascading to deliver superior results. By attacking NVH at the source, and integrating data-driven techniques early in the design cycle, significant reductions in development time and reliance on traditional testbed loops are realised. Machine learning algorithms are utilised to accelerate root cause analysis and refine simulation accuracy, while target cascading ensures alignment of system-level performance objectives down to subsystem contributions. Combined, these strategies enable rapid and robust NVH optimisation, setting the benchmark for next-generation electric powertrain development. several application and real life exmaple are shown.
Mehrgou, Mehdi, Garcia de Madinabeitia, Inigo, Graf, Bernhard, Gojo, Josef
A Self-Learning Framework for NVH CAE Analysis2026-01-0718To be published on 06/20/2026
The vibro-acoustic performance of a vehicle is a critical factor in customer perception of quality and comfort. Optimizing for Noise, Vibration, and Harshness (NVH), particularly road noise, presents a persistent challenge in the automotive development cycle. While modern FEM analysis is essential, the increasing complexity and sheer volume of CAE simulation data often overwhelm manual interpretation, potentially leading to prolonged development times or sacrifices in resulting comfort quality. To address these challenges, this paper introduces the application of CDH/ACE (Autonomous Computational Experiments), a framework that combines conventional CAE simulation workflows with machine learning in an iterative cyclic process. This creates a self-learning and self-correcting system that autonomously defines, performs, and learns from computational experiments. By building predictive models from simulation data, the framework intelligently guides the design exploration to achieve
Visser, Rene
NoiseSphere: An AI-Based Approach for Dynamic and Large-Scale Noise Mapping2026-01-0719To be published on 06/20/2026
Noise pollution is a major environmental and health challenge, yet its strong spatial and temporal variability makes comprehensive mapping highly complex. Current approaches under the European Noise Directive (END) provide only partial coverage and often lack temporal dynamics. The NoiseSphere project, fundet by the Austrian Research Promotion Agency FFG, develops an AI-based methodology for dynamic, large-scale noise prediction and mapping. A machine learning model is trained on heterogeneous data sources, including semantically enriched Sentinel-2 satellite imagery, OpenStreetMap road data, floating car data (traffic density and speed), and existing noise maps. The model is refined through integration of noise emission data and validated using targeted in-situ measurements. Two case studies, one located in an urban environment (Graz) and the other one in a rural region near Linz demonstrate the model’s applicability across contrasting settings. By combining remote sensing, traffic
Girstmair, Josef
Rapid Fuel Distribution Prediction in RCCI Marine Engines Using CFD-Informed, Active Learning Framework2026-37-0017To be published on 06/09/2026
Accurate prediction of in-cylinder fuel distribution (FD) is fundamental to reduced-order combustion modeling and emissions prediction, yet remains computationally prohibitive with high-fidelity CFD alone. This work develops a CFD-informed machine-learning surrogate for spatial FD in a large-bore diesel engine, based on a Wärtsilä W20 injector and representative engine conditions. A fully coupled injector–spray–engine CFD framework under engine-like RCCI inert conditions determines the needle-lift profile and resolves the combined effects of injector geometry, needle dynamics, and operating conditions on in-cylinder flow, capturing physical phenomena not reproducible by isolated free-spray simulations. A high-fidelity database is generated using Latin Hypercube Sampling, from which FD is extracted at 15 CAD before top dead center within an annular multi-zone (MZ) representation consistent with reduced-order combustion models. A multi-output Random Forest (RF) surrogate, augmented with
Moradi, Jamshid, Salahi, Mahdi, Heidarabadi, Shadab, Andwari, Amin, Konno, Juho, Wik, Christer, Mikulski, Maciej
Automated Design Sustainability Evaluation Framework: a CAD-Integrated Tool for Real-Time Costing and LCA in Automotive Engineering2026-37-0044To be published on 06/09/2026
As the automotive industry faces increasingly rigorous environmental regulations and an approaching obligation for Digital Product Passports (DPPs), incorporating sustainability metrics into the early design phase has become a necessity. Traditionally, Life Cycle Assessment (LCA) and manufacturing cost estimation are performed during or after the design phase using specific methods and tools, resulting in costly iterations and delayed decision-making. This paper introduces a preliminary computational tool that combines 3D CAD and spreadsheet software via VBA integration. The framework automates the generation of an “Extended Bill of Materials” by extracting geometric and manufacturing data directly from CAD models. This tool’s classification logic is a key innovation that intelligently processes CAD features to identify component categories, such as sheet metal, machined parts, or plastic injections. This automated recognition allows the framework to implement specific algorithmic
Guadagno, Maurizio, Cecconi, Leonardo, Berzi, Lorenzo, Delogu, Massimo
Automated Flight Maneuver Recognition for Intelligent Flight Simulator2026-26-0713To be published on 06/01/2026
The rapid growth in the number of aircrafts and pilots emphasizes the need for an AI-enabled training framework that can offer precise, automated examination of flight maneuvers, thereby optimizing the pilot’s training efficiency and minimizing iterations of the conduct of flight maneuvers thereby reducing the training time of the pilot for a flight. This paper introduces a novel hybrid methodology to intelligently detect manoeuvres performed during a flight using signal processing and machine learning techniques. A general framework is developed that can be used for all kinds of flight phases and aircraft types. The framework is implemented in a two-step approach. Firstly, Continuous Wavelet Transform (CWT) of the signals of interest for different manoeuvres are generated, to find the time at which a manoeuvre happens during a sortie. CWT looks at the energy levels in the transformed signal and uses smart thresholding technique to pick out only the parts with high energy, to extract
Sahu, Akash, C, Poornima, C, Aravindh, Kaliyari, Dushyant, TK, Khadeeja Nusrath
Automating Compliance Workflows in Aerospace Systems: A Scalable Framework for Specification Review and Requirement Mapping2026-26-0714To be published on 06/01/2026
Compliance verification in aerospace systems often relies on labor-intensive workflows that demand extensive manual effort to produce structured review documentation and requirement matrices. These processes can span dozens of hours per review, are vulnerable to inconsistencies due to non-standardized annotations, and depend heavily on individual interpretation of fragmented technical sources. With a growing backlog of review tasks and a steady influx of new requests, the need for scalable automation has become increasingly urgent. This study presents a modular automation framework designed to streamline compliance assessments through intelligent document parsing, requirement extraction, and matrix generation. The system integrates optical character recognition, computer vision, and natural language processing techniques to process both scanned and digital documents. By digitizing data across multiple hardware configurations and automating extraction from diverse technical records, the
Mirani, Harsh, Baviskar, Yash G.
Enabling Circularity in the Aerospace Maintenance Ecosystem through Generative-AI Driven Back-to-Birth Traceability of Life-Limited Engine Parts2026-26-0719To be published on 06/01/2026
Circular economy principles are increasingly central to aerospace sustainability strategies, aiming to extend asset life, improve asset valuations, and enhance benefits to stakeholders in the part ownership and maintenance lifecycle. In aircraft engines, achieving circularity hinges on the safe reuse, repair, and recirculation of high-value components. Life-Limited Parts (LLPs) are among the most critical in this context, but their reuse is strictly contingent on complete Back-to-Birth (BtB) traceability. Any gap in BtB records—often due to fragmented data across multiple airline operators, shop visits, document formats, and time expanse—renders otherwise serviceable LLPs unusable, leading to premature scrappage and lost circular value. This paper presents a Generative AI (GenAI)-driven methodology to reconstruct and validate complete LLP BtB histories from heterogeneous, unstructured, and legacy maintenance datasets. By combining aerospace domain-trained language models with embedded
Bhate, Ujwal, Jain, Dilip Kumar, Kulkarni, Ninad, Kalaiyarasan, Aravindh, Jha, Ashish, Shenoy, Karthik
Adaptive HVAC Strategies for Enhanced Cabin Thermal Comfort, Air Quality and Energy Efficiency2026-26-0791To be published on 06/01/2026
Passenger comfort within vehicle and aerospace cabins relies on finely tuned management of temperature, air quality, and energy use. This paper proposes an integrated HVAC framework that combines zonal climate control, intelligent airflow distribution, and real-time sensor data to maintain thermal balance across different cabin zones. Leveraging predictive thermal load modeling and machine learning, the system anticipates environmental changes—such as sudden shifts in external temperature or passenger load—and proactively adjusts heating and cooling outputs. Simultaneously, air quality is enhanced through a multistage filtration system, active air purification technologies, and dynamic CO₂ concentration monitoring. Comfort assessment integrates PMV (Predicted Mean Vote) and PPD (Predicted Percentage Dissatisfied) indices to adapt environmental conditions based on passenger feedback and physiological needs. Simulations and early-stage prototypes improve energy savings and improve
Mudavath, Lehitha Sai, Patil, Ashish, Saha, Sudipta
Data-Driven Air Traffic Management: Forecasting Demand, Modeling Delay Propagation, and Demand Capacity Balancing2026-26-0772To be published on 06/01/2026
Air traffic management (ATM) systems must accurately estimate flight demand, analyze network delays, and optimize capacity. This research uses a global airline dataset with passenger information, airport characteristics (including geographic markers and continental classifications), flight scheduling data (timing and destination details), crew information, operational status records, and OpenSky Network real-time states data to create an intelligent ATM decision-support framework. Advanced machine learning (ML) methods like gradient boosting and sequential modeling are used to build network models of flight routes between origins and destinations, develop temporal demand patterns for individual airports, analyze delay factors, and predict congestion periods. The research uses mixed-effects statistical models using crew data to measure operational variability and demographic and nationality-based analysis to identify demand trends for improving staffing and security processing during
Senthilkumar, N., S, Gopalakrishnan, Gopinath, S
Enabling Digital Transformation in Aerospace: Automated Model Based Engineering2026-26-0722To be published on 06/01/2026
Model-based development (MBD) and testing are critical for airborne software compliance with DO-178C and its supplement DO-331, which specifically addresses model-based approaches for software levels A through D. Traditional manual methods for MBD and testing are time-consuming and prone to variability, impacting consistency, accuracy, and certification timelines as avionics systems grow in complexity. This paper presents an automation framework designed to align with DO-331 objectives by leveraging fine-tuned large language models (LLMs) to automate the generation of high-level textual requirements and low-level model-based requirements. From these, comprehensive test cases are automatically derived, covering normal, edge, mutant, and dynamic scenarios to ensure thorough validation of model behavior. Utilizing Boeing AI, the framework extracts requirements and key parameters from documentation, enabling automated specification analysis and test script generation that simulate real
Lalchandani, Tushar, Purushothaman, Kalaivani, Jeppu, Yogananda, Vijaya Kumar, Shree Harsha, Natarajan, Akilandeswari
Agentic Digital thread for self-healing non-conformities in aerospace product manufacturing lifecycle2026-26-0763To be published on 06/01/2026
Aircraft manufacturing involves a complex ecosystem where quality, traceability and compliance are paramount. Managing non-conformities both before and after manufacturing requires a digitally connected data framework that ensures seamless data flow, decision-making and corrective actions across different functions like sourcing, materials, engineering and production. The advent of agentic AI brings more autonomous solutions through drastically reduced human prompts. This paper presents a comprehensive Agentic Digital thread framework for managing pre and post manufacturing non-conformities, enabling real-time visibility and control from design to delivery. The Agentic digital thread transforms from being passive connectivity layer into living intelligence ecosystem that continuously learns, adapts, and improves in real time Pre-manufacturing nonconformity management focuses on early detection of issues through Agentic AI in sourcing, materials and design through integration of PLM
Veluri, Sastry, Gopala Krishnan, Kannan
Electric Health-Monitoring Wiring (E-Wiring) for Aircraft2026-26-0785To be published on 06/01/2026
Modern aircraft depend on extensive electrical wiring networks for power distribution, avionics, and control systems; however, these wiring systems are vulnerable to wear, insulation degradation, and arcing over time, leading to safety risks and costly unscheduled maintenance. The proposed Electric Health-Monitoring Wiring (E-Wiring) system integrates temperature, current, insulation, vibration, and environmental sensors directly into aircraft wiring harnesses to enable continuous monitoring and intelligent fault detection. Data from these embedded sensors are processed through a distributed edge AI network, forming an Electrical Health Monitoring System (EHMS) capable of real-time diagnostics, predictive maintenance, and fault localization. The architecture comprises smart cable segments with sensor nodes, local harness gateways for edge processing, aircraft-level EHMS integration via AFDX/Ethernet, and cockpit or maintenance displays linked to ground-based cloud analytics for fleet
Tammana, Bala Sai Sri Rohit, Murthy, Harsha, Mendu, HarikaSivaniSunandha
Integrating Human Factors and Predictive Modeling for Enhanced Aviation Safety: A Data-Driven Approach to Risk Mitigation and System Design2026-26-0795To be published on 06/01/2026
The evolution of the aviation industry from manual control to highly automated and autonomous systems has brought human factors to the forefront of safety, design, and operational efficiency. This paper presents an integrated analysis combining machine learning techniques with statistical modeling to assess the impact of human-system interaction on aviation incident outcomes. The first phase of this research involved a longitudinal dataset covering aircraft design evolution, training programs, and incident records. Using classification algorithms, including XGBoost, the study achieved an accuracy of 81.82% in predicting incident likelihood. Performance metrics such as F1-scores (0.85 for “Incident” and 0.78 for “No Incident”) highlighted the model’s robustness in identifying risk patterns associated with human factors and system complexity. In the second phase, 50 plus detailed aviation incident reports were analyzed using logistic regression, t-tests, and Cook’s Distance to identify
Valiyaparambil, Praveen
AI Based Energy Sustained Series Hybrid Aircraft2026-26-0776To be published on 06/01/2026
This paper investigates the energy consumption characteristics of series hybrid aircraft with a focus on comparing conventional energy management approaches against an AI-powered optimization framework. The study comprehensively models the energy demands of a series hybrid aircraft across all major flight phases, including Idle & Ground Operations, Taxi, Takeoff, Climb, Cruise, Descent, Approach, Landing, and Rollout & Taxi. For each phase, detailed mathematical formulations are developed to capture power requirements and energy flow, incorporating real-time operational parameters to enhance the accuracy of the energy consumption estimations measured in kilowatt-hours (kWh). The AI-based optimization leverages advanced control strategies, specifically Model Predictive Control (MPC) and Reinforcement Learning (RL) algorithms, to dynamically manage the aircraft's energy systems. MPC is employed to predict and optimize future energy usage by solving constrained optimization problems over
Kanchagar, Amogha
Drilling Studies on Sustainable Lightweight Hybrid Polymer Matrix High Performance Nanocomposites2026-26-0732To be published on 06/01/2026
Worldwide, engineers are exploring the possibility of using polymer composites in their quest for lightweight materials. In an effort to create polymer composites that are less harmful to the environment, the use of biodegradable polymers has been investigated in recent years. Injection molding was used to create a biodegradable polymer composite containing 20 wt.% vetiver fibers (VFs) and 2 wt.% nano-silica (nSiO2) obtained from pearl millet. Parts for unmanned aerial vehicles, interior cabin panels, seating structures, and secondary structural components were made of this composite. Desirability analysis was used to examine and optimize machining (drilling) studies that were designed according to Taguchi's design (L9 orthogonal array). Surface roughness (Ra) and delamination factor (DF) were taken as outputs, while spindle speed (SS) ranging from 1000 to 3000 rpm, feed rate (FR) from 15 to 45 mm/min, and drill diameter (DD) from 6 to 10 mm were used as inputs. The developed
Senthilkumar, N.
Hybrid Digital Twin for Aero-Engine Bearing Prognostics: A Physics-Informed Machine Learning Approach to RUL Prediction2026-26-0718To be published on 06/01/2026
Unscheduled maintenance due to the failure of critical components, such as aero-engine rolling element bearings, is a leading cause of costly Aircraft-on-Ground (AOG) events; consequently, current time-based maintenance practices are inefficient and prone to risk. This paper develops a resource-efficient Hybrid Digital Twin (HDT) model for an engine bearing, focusing on the dynamic prediction of spall growth due to Rolling Contact Fatigue (RCF), thereby enabling a condition-based maintenance paradigm. The HDT architecture integrates two core models: (1) a physics-informed model that uses established life and fatigue theory to define initial degradation thresholds and constrain the failure envelope, and (2) a data-driven Recurrent Neural Network (RNN) (specifically, an LSTM) for dynamic degradation rate modeling. The methodology utilizes a Monte Carlo simulation coupled with RCF progression equations to generate a large, synthetic run-to-failure dataset under varying operational loads
Mohamed, Abbas
Aircraft cabin Diagnosis - Inspection of the Aircraft cabins and seats using AI2026-26-0789To be published on 06/01/2026
Operational challenges related to aircraft interiors particularly damaged seats, compromised seat cushions, and liquid or food spillages have a direct impact on airline operations and passenger satisfaction. Allowing passengers to use defective seating not only degrades the travel experience but also risks damaging the airline’s reputation. Moreover, addressing these issues often results in increased aircraft ground time, contributing to significant financial implications for airline operators. To mitigate these challenges, a predictive maintenance approach leveraging artificial intelligence (AI) is proposed. This system utilizes radar scans and high-definition camera images captured when the aircraft is unoccupied to detect interior issues. The collected data is then compared against a baseline “master scan” taken under ideal, clean, and properly maintained conditions. Advanced AI algorithms analyze these comparisons to accurately identify problem areas, down to specific seat
Nagoal, Chandrasekhar Reddy, Prathipati, Krishna Chaitanya, Kandukuri, Ravindra
A GenAI-Based Approach for Real-Time Multilingual In-Flight Communication Systems.2026-26-0784To be published on 06/01/2026
In today’s global aviation industry, passenger experience is strongly influenced by effective communication. In-flight announcements, often limited to English and a single local language, can create confusion and stress for international travelers who may not be fluent in either. This communication gap not only impacts passenger comfort but also poses potential risks in conveying time-sensitive or safety-critical information. Recent advances in Generative Artificial Intelligence (GenAI), particularly in speech recognition, neural machine translation, and naturalistic text-to-speech, provide a pathway to overcome these challenges. This paper explores the concept of real-time multilingual in-flight announcements, delivered in each passenger’s preferred language through connected headphones or personal devices. The proposed system architecture integrates speech-to-text conversion, language translation, and speech synthesis with aircraft infotainment platforms. Potential applications range
Mishra, Ashwini, Kature, Kartik, Patil, Ashish
Energy Saving and Personalized Thermal Comfort Control Based on Reinforcement Learning and Decision Tree2026-99-1714To be published on 05/22/2026
Indoor thermal comfort is closely related to people’s health and work efficiency. Control systems typically consume a large amount of energy to maintain a comfortable thermal environment. Currently, reinforcement learning is widely applied to optimize thermal comfort control systems. However, existing research mainly adopts universal thermal comfort evaluation models that aim to satisfy the majority of people, which makes it difficult to quickly and accurately reflect the specific thermal comfort needs of individuals. As a result, the hot environment is neither comfortable nor energy-efficient in practical use. Therefore, this paper proposes an energy-saving personalized thermal comfort control method based on decision trees and reinforcement learning. First, decision tree learning is used to obtain an individual thermal comfort evaluation model from a small amount of historical data. Then, this individual comfort model is combined with energy consumption to form a reward function
Li, Xianying
Semantic-Driven Mathematical Modeling and Adaptive Refactoring for Logistics Optimization: A Language-Model Orchestrated Optimization Pipeline2026-99-07505/15/2026
While large language models (LLMs) offer a convenient natural language interface for logistics optimization problems, it remains challenging to directly generate reliable mathematical models and executable code from unstructured text requirements. LLMs tend to produce invalid constraints or syntactically incorrect code. In addition, traditional logistics optimization methods lack the flexibility to adjust warehouse rules or operational goals without manual expert intervention. To address these issues, we propose LOOP (a Language-Model Orchestrated Optimization Pipeline), which automatically translates natural-language requirements into optimization algorithm code while retaining the rigor of classical models and solvers. LOOP leverages task-specific agents to construct accurate mathematical models and adopts a difference-driven code generation approach. First, it synchronizes model changes into executable code via semantic mapping and ensemble difference analysis. Second, it
Ding, Ruiqing, Li, Qianying, Li, Xiaojian
Local LLM Based Knowledge Graph in Power Domain Using Graph-Schema Reasoning and Retrieval-Augmented Generation2026-99-07565/15/2026
In recent years, large language models (LLMs) have shown great potential in many domains. However, their application in professional domains is often limited by problems like erroneous outputs and hallucinatory responses. Therefore, we present a framework that combines knowledge graphs (KGs) with local LLMs. The framework utilizes the factual information in KGs to improve the initial output of the LLMs, thereby reducing the factual errors in inference. In this paper, a domain knowledge graph is automatically constructed using textual data from the power industry. The KG contains 149,732 entities and 139,280 relationships. The proposed method is tested on EleQA, a public Q&A dataset of electricity regulations. Compared with the LLM-only baseline, the knowledge-graph-enhanced model achieves an improvement of 32.42%. Moreover, the framework shows strong adaptability and performs well on various LLMs. Our framework improves the accuracy and utility of large language models in the power
Chen, Ruiduan, Lin, Shizhong, Shao, Zhan, Cui, Shicheng, Li, Xingyu, Luo, He
Time Series Causal Discovery Based on Data Augmentation and Causal Validation2026-99-07035/15/2026
Causal discovery within time series is crucial for revealing the actual causal mechanisms in dynamic systems, and it has major impacts in various fields like economics, healthcare, and climate science. Even though it’s important, accurately figuring out causal relationships from observational temporal data is still quite a difficult task. Traditional Granger causality based methods are often limited by noise sensitivity, large amount of data, and the inability to distinguish between real causality and false correlation caused by hidden factors. In order to solve these problems, this paper presents CausalAugVeri, which is a new algorithm that cleverly mixes data augmentation with causal verification to make causal discovery more solid and precise. This work has three main points: First, we carefully check that using convolutional data augmentation techniques can greatly improve how well time series predictions work, giving a steadier base for detecting Granger causality. Second, the
Yang, Jing, Chen, Xiaotao, Qin, Xuanli, Xu, Xianjun, Hu, Zhangxiang
Design of a Novel Intelligent Monitoring Platform for Low and Medium Altitudes2026-99-07395/15/2026
This paper presents the design of a novel intelligent monitoring platform for low and medium altitudes, aiming to offer a new solution for the development of intelligent equipment operating in this airspace. Current monitoring tasks are primarily performed by fixed-wing and multi-rotor UAVs, but these platforms face significant technical bottlenecks in flight endurance and monitoring precision. This research aims to address these deficiencies. The platform is based on a small-scale unmanned airship featuring a semi-rigid, hybrid lift-body structure. Improvements were made upon the traditional ellipsoidal hull; the hull profile was optimized using a geometric superposition method, introducing an aerodynamic camber line with a maximum camber (m) of 4% to enhance aerodynamic performance at small angles of attack. In terms of its energy system, the platform is powered by a purely electric energy system composed of solar panels and batteries; solar energy is used during the day, while
Song, Ziang, Gao, Wenxuan, Cao, Xiaochuan, Zheng, Xing, Zhao, Chong
CF-CoT: Enhancing Causal Reasoning in LLMs through Counterfactual Scenarios2026-99-07285/15/2026
Causal reasoning is the task to identify causal relations between a pair of events in a given context. However, causal reasoning in natural language remains a challenging task for large language models (LLMs), since they tend to mix correlation and causality and exhibit bias in their reasoning, especially by mistaking temporal proximity for causal relations. The problem is exacerbated by the models’ propensity to generate spurious justifications that confuses co-occurrence rather than actual causal relationships. Although CoT prompting has shown effectiveness in enhancing multi-step reasoning, it is prone to hallucination and spurious inferences, which generally dampens their capability to provide correct causal explanations. The variant of CoT, CoT-SC, is a more promising attempt at yielding consistent outputs by randomly sampling multiple reasoning paths, and voting for the most probable answer. However, for its implementation, CoT-SC also demands expensive computations. The
Yang, Jiaoyun, Qi, Botao, Liu, Li, Li, Lian, An, Ning
Cabbage Cleaning Device Based on Fischertechnik Model2026-99-07345/15/2026
This article focuses on the problem of high labor cost, low processing efficiency and poor automation of the existing equipment in the postharvest processing of Chinese cabbage. It will design and produce an automated Chinese cabbage processing method called Smart Fresh Pack. Root removal, leaf removal, washing, loading, weighing, packaging and labeling functions were integrated, and smart dexterous intelligence was applied to core concepts and this can be used in the bulk production scenario of supermarkets in the city and countryside Compared with traditional assembly line equipment, obvious advantages in terms of structure, function and processing capacity: Key innovations include: Low-pressure air jet cleaning replaces water washing, which prevents a second contamination and weighing error due to surface moisture; pneumatic gripper and multi-DOF robotic arms combine to package and dynamically weigh simultaneously, streamlining these tasks; machine vision relies on an SSD
Chen, Yuhui, Zhang, Yixuan, Ruan, Jia, Zhu, Huayun, He, Lianzheng, Zhao, Ping
Design and Implementation of an Intelligent Mobile Waste Classification and Collection Robot System2026-99-07025/15/2026
To address the growing demand for waste management, improve the efficiency and accuracy of waste classification, reduce costs, promote environmental protection and circular economy development, and solve environmental pollution and resource waste problems through technological innovation. This paper proposes an intelligent mobile waste classification and collection robot system. The system consists of a picking mechanical arm subsystem, a waste classification and collection subsystem, a self-moving chassis subsystem, and a solar tracking power generation subsystem. The picking mechanical arm subsystem actively collects waste through a mechanical arm combined with machine vision technology and deposits it into the waste classification device, while the waste classification and collection subsystem completes functions such as classification, compression, collection, and dumping, utilizing a navigation and positioning-driven chassis to achieve autonomous waste collection, simultaneously
Xia, Ying, Zhu, Huabing, Jia, Ruitong, He, Yifan, Hou, Wentao, Fu, Shaozao, Lin, Jiaoyang
Hierarchical Reinforcement Learning For Task Generation of Transmission Tower Inspection Using Point Clouds2026-99-07545/15/2026
Unmanned Aerial Vehicles (UAVs) are widely used for inspecting transmission towers. However, traditional waypoint planning relies heavily on manual experience. This leads to low efficiency, incomplete coverage, and a lack of standardization. Facing these problems, this paper proposes an intelligent generation method based on Hierarchical Reinforcement Learning (HRL). This method achieves end-to-end automation, converting raw point cloud data directly into an optimal set of waypoints. Preprocess and grid the point cloud data to build a model of the coverage area. Then design a hierarchical framework to break down the complex planning task. This framework divides the task into high-level waypoint selection and low-level pose optimization. Specifically, the high-level part uses a Deep Q-Network (DQN) to learn the best sequence of waypoints. The low-level part uses Q-learning tables to optimize the pitch and yaw angles for each point. Meanwhile, design a reward function to maximize
Cui, Shicheng, Lin, Shizhong, Shao, Zhan, Chen, Ruiduan, Li, Xingyu, Luo, He
A Reinforcement Learning Trajectory Planning Model with Kalman Filter-Based Dynamic Tracking for Six-Axis Robotic Manipulators2026-99-07385/15/2026
Robot Arm Tracking Control refers to the control of robot end effectors following a prescribed trajectory as their movement in robotic systems. The work presents a combination of Kalman Filter Based Dynamic System Tracking with Reinforcement Learning Based Trajectory Planning. These two aspects of tracking and planning help the robotic manipulator dynamically track a target that is located on an arbitrary moving path. In particular, by using Kalman filtering to estimate the position of a moving target and to compensate for sensor noise and sparse sampling, we take high-precision estimation values of each point’s coordinates along the target trajectory as a reliable basis to build a policy network using reinforcement learning. Based on it, the robot manipulator could produce effective motion planning under its own dynamic capabilities and physical constraint limit. Comprehensive simulation results illustrate advantages of the new algorithm against the classical control method, confirm
Yu, Jingze, Wang, Yujia, Li, Junshen, Chen, Cong, Xu, Peng
CauExecutor: A Causal Executor for Causal Effect Estimation2026-99-07215/15/2026
Causal inference from observational data, particularly the estimation of a treatment’s causal effect on an outcome, has long been challenging, primarily because it hinges on correctly identifying confounders. This is typically accomplished in two main ways within causal inference frameworks: either by using causal discovery algorithms to recover the underlying causal structure through a causal graph, or by assuming that the relevant confounders are already known. Both approaches have been shown to be unreliable or simply infeasible in practical applications. Although large language models (LLMs) are advancing rapidly, their emerging capabilities in causal inference have only recently begun to receive significant attention. Nevertheless, LLMs currently lack the ability to directly interpret structured tabular data, which is widely used in causal inference. To address this limitation, we introduce a novel framework, CauExecutor, for causal inference. Our framework enables a novel
Yang, Jiaoyun, Chen, Jinxi, Yin, Yue, Liu, Li, Li, Lian, An, Ning
A Deep Learning Framework for Fast Prediction of Automotive Drag and Pressure Fields2026-99-07485/15/2026
Computational fluid dynamics (CFD) is crucial for automotive design, requiring analysis of 3D point clouds to investigate how vehicle geometry affects pressure fields and drag. Running CFD on high-resolution 3D geometry quickly becomes computationally heavy, and many solvers slow down noticeably as the geometric detail increases. We therefore introduce a dual-task deep learning framework, named AeroFormer, that predicts aerodynamic quantities directly from the vehicle’s surface geometry and avoids the need for full CFD simulations. The model is organized into two parts. One branch, AeroFormer-Cd, predicts the overall drag coefficient (Cd), while the other, AeroFormer-Press, reconstructs the pressure distribution over the vehicle’s surface. Both branches rely on a shared curvature-guided adaptive sampling process and a physics-aware attention encoding module, which enable the network to emphasize fine geometric details in aerodynamically sensitive regions such as the front bumper, A
Yan, Shengmao, Deng, Shisong, Jiang, Yanzhen, Jin, Xinyu, Cai, Zhengyang
Feature Reduction for Scenario-Based Safety Assessment of Automated Driving Systems09-14-01-00185/4/2026
Vehicles equipped with an Automated Driving System (ADS) have the potential to significantly reduce road collisions. To enable widespread adoption of ADSs, rigorous safety assessment is essential. Valuable insights for ADS safety validation can be gained by simulating scenarios across a broad range of feature variations. A common challenge in simulating these scenarios is known as the curse of dimensionality, where increasing the number of scenario features requires a near-infinite number of simulations to cover all variations. This issue of complexity presents a need for reducing scenario features. Most related work focuses on identifying important scenario features, while few evaluate how reducing these features impacts ADS failure estimation. The present study aims to address this gap by employing a wide range of feature reduction methods and assessing their effect on ADS failure estimation. Previous research generated datasets for three distinct scenario categories by performing
Lankhorst, Bram, de Gelder, Erwin, Janssen, Christian P., Scholich, Andre
Characterization of Lane Keeping and Departure Scenarios Using Large-Scale Naturalistic Driving Data09-14-01-00225/4/2026
Roadway departures remain a major cause of crashes, injuries, and fatalities on U.S. roads. Technologies such as lane keeping assist (LKA) and lane centering assist (LCA) can help mitigate these crashes, but their development involves extensive characterization of the parameter space in which they operate. Lane and road departures (LDs/RDs) and lane changes (LCs) must be systematically described and quantified to distinguish kinematic features, identify contributing factors, and benchmark system influence on lateral control. This study developed a unified pipeline to mine over 36 million miles of naturalistic driving study (NDS) data collected from more than 3800 participants. The pipeline integrates various types of signals to detect roadway boundary crossings, classify LKA-relevant scenarios, and extract roadway, driver, environmental, and assistance-related parameters. Lane keeping epochs with and without LKA were also extracted to quantify system influence on lateral control. In
Ali, Gibran, Terranova, Paolo, Williams, Vicki, Holley, Dustin, Saffy, Joshua, Antona-Makoshi, Jacobo, Kefauver, Kevin, Shull, Emily, Li, Eric, Venegas, Michael
Advanced Tool for Traffic Crash Analysis: An AI-Driven Multi-Agent Approach to Pre-Crash Reconstruction09-14-01-00335/4/2026
Traffic collision reconstruction traditionally relies on human expertise and, when performed properly, can be incredibly accurate. However, attempting to perform pre-crash reconstruction, i.e., reconstructing the driver and vehicle behaviors that preceded the actual crash, poses significantly more challenges. This study develops a multi-agent artificial intelligence (AI) framework that reconstructs pre-crash scenarios and infers vehicle behaviors from fragmented collision data. We present a two-phase collaborative framework combining reconstruction and reasoning phases. The system processes 277 rear-end lead vehicle deceleration (LVD) collisions from the Crash Investigation Sampling System (CISS; 2017–2022), integrating textual crash reports, structured tabular data, and visual scene diagrams. Phase I generates natural language crash reconstructions from multimodal inputs. Phase II performs in-depth crash reasoning by combining these reconstructions with the temporal event data
Xu, Gerui, Chen, Boyou, Guo, Huizhong, LeBlanc, Dave, Kusari, Arpan, Yarbasi, Efe, Ahmed, Ananna, Sun, Zhaonan, Bao, Shan
Effects of Vehicle Speed, Category, and Front-End Design on Full-Body Injury Risks of a Midsized Male Pedestrian09-14-01-00175/4/2026
This study investigated how vehicle front-end geometry, impact speed, and vehicle category influence injury risk to a midsize male pedestrian. Eighty-one generic vehicle (GV) models representing sedans, sport utility vehicles (SUVs), pickup trucks, and minivans sold in the United States were developed by morphing three base models using an automated pipeline. Front-end parameters that were varied included ground clearance (GC), bumper height (BH), hood leading-edge (HLE) height, hood length (HL), bumper lead angle (BLA), hood angle (HA), and windshield angle (WSA). Each vehicle impacted the Global Human Body Models Consortium 50th percentile male simplified pedestrian (GHBMC M50-PS) model at 30, 40, and 50 kph, totaling 243 simulations. Boundary conditions followed the European New Car Assessment Program (Euro NCAP) pedestrian test protocol. Thirty-five injury metrics were extracted across the head, neck, thorax, abdomen, pelvis, and lower extremities. Linear mixed-effects regression
Poveda, Luis, Miller, Logan E., Edwards, Colin C., Pollock, Madeline, Armstrong, William M., Hsu, Fang-Chi, Gayzik, Scott F., Weaver, Ashley A., Stitzel, Joel D., Devane, Karan S.
Machine Learning–Driven Safety Analysis of Automated Vehicles in Simulated Mixed Traffic Environments09-14-01-00215/4/2026
Automated Vehicles (AV) pose new challenges in road safety, multimodal interaction, and urban planning, requiring a holistic approach that prioritizes sustainability and protects all road users. The KASSA.AST project addresses this by deploying and evaluating an automated shuttle in southern Austria on three routes. The study area is a Park & Ride zone near a train station, enabling seamless transfers and higher transit use. To assess the safety impacts of the automated shuttle, four Mobility Observation Boxes (MOBs) were deployed. These AI-based systems detect and classify road users, track their trajectories and geospatial coordinates, and identify safety-critical events via Surrogate Safety Measures (SSMs). Over 10 days, a trajectory dataset captured interactions among vehicles and the shuttle. The resulting real-world dataset is a core contribution. This dataset underpins microscopic behavior modeling. Trajectory pairs yield car-following and interaction metrics (relative distance
Losada Arias, Ángel, Rosenkranz, Paul, Hula, Andreas, Aleksa, Michael, Saleh, Peter, Erdelean, Isabela
Items per page:
1 – 50 of 2572