Browse Topic: Neural networks

Items (1,510)
Aiming at the inherent instability, strong nonlinearity, and high dynamic characteristics of normal-conducting maglev suspension systems, this paper adopts a composite supervisory control scheme integrating PD control and an RBF neural network. First, a high-speed maglev train-track coupled dynamics model considering track elasticity is established. On this basis, a phased control strategy is designed: the initial phase employs a PD controller to ensure system stability, after which control is seamlessly handed over to an RBF neural network. The weights of this network are continuously refined online via a gradient descent algorithm, enabling progressive enhancement of control precision. Simulation results validate the effectiveness of this approach, confirming its superior performance in both precise suspension gap regulation and robust disturbance rejection. Consequently, the proposed method not only underpins the stable operation of maglev trains but also constitutes a reliable intelligent control framework for high-speed maglev systems.
Yu, YongZhang, JieWang, YuLiang, Shi
Machine Learning and more specifically Deep Learning has successfully erupted into a vast number of engineering fields in the recent years, specially leaping traditional simulation approaches by leveraging data usage. Even though the potential is huge, the delicate selection of an adequate Machine Learning architecture for a specific problem determines the success of its implementation. This is essential for non-Euclidean datasets, like the ones found in social networks, molecule structures, manifolds, and others. In those datasets, the distance between two points does not correspond to the Euclidean distance, but to the path along the edges (either weighted or unweighted). This is the case of Computational Fluid Dynamic (CFD) meshes. In all these fields, the fitting of Graph Neural Networks (GNNs) for this type of datasets have made them gain popularity in the recent times. Specially as aerodynamic predictors they have had a remarkable dominance during the last few years, as not only there is a strong academic research trend toward these architectures, but many “AI-consulting engineering companies” offer them as the surrogate model of choice. In this survey, a brief introduction to GNNs is presented. More importantly, and different from other GNN surveys, this review paper focuses on their current application as aerodynamic coefficients and flow field predictors (academic and industrial), with emphasis on their specific architecture. Nineteen publications have been selected for this review, focusing, but not exclusively, on external aerodynamics.
Lazaro Prat, AleixSchütz, ThomasGau, Holger
Aircraft assembly systems, as a critical phase in aerospace manufacturing, face significant challenges in maintaining production efficiency and ensuring product quality. This complex manufacturing system exhibits two distinct characteristics: (1) tightly coupled interactions among manufacturing elements involving process sequences, material flows, and equipment utilization; and (2) dynamic resource allocation and material distribution plans. The inherent variability in production element configurations often leads to operational instability and schedule deviations, which may result in abnormal production states. To address these challenges, this study proposes a data-driven predictive framework that integrates Long Short-Term Memory (LSTM) neural networks with multi-criteria evaluation. The developed LSTM-based model effectively forecasts two critical production indicators of cycle time and balance rate, achieving temporal prediction through historical operational data analysis. The proposed methodology facilitates timely anomaly detection and early warning, allowing proactive risk mitigation and ensuring sustained production system stability. This research contributes to advancing intelligent monitoring and control strategies for aircraft assembly operations within data-driven manufacturing environments.
Chen, BolinWu, JunjieSun, JinfengWang, Kai
Variable stiffness composite laminates with curvilinear fibres have demonstrated significant capability in lightweight structural design, particularly regarding buckling resistance and stiffness enhancement. However, directly applying optimization algorithms often faces challenges such as high computational cost and slow convergence during the optimization design process. Consequently, the incorporation of surrogate models prior to employing optimization algorithms is necessary to simplify computations and accelerate convergence. Manual testing is a conventional approach for hyper-parameter (HP) tuning and continues to be widely used in research. However, manual tuning is suboptimal and time-consuming for many problems. Additionally, the effectiveness of these surrogate models largely depends on the training samples. Therefore, a dynamic hybrid sampling and adaptive surrogate model HP co-optimization strategy is proposed for the optimization design of the variable stiffness composite laminate with curvilinear fibre. In the numerical results, the performance of different surrogate models, comprising Support Vector Regression (SVR), Radial Basis Function Neural Networks (RBFNN), and Back Propagation Neural Networks (BPNN), is systematically compared under varying sample set sizes. Neural results show significant differences in accuracy and efficiency among these three models under varying sample set sizes. SVR demonstrates optimal generalization ability in small sample scenarios, RBFNN strikes a balance between accuracy and efficiency with medium sample size, while BPNN exhibits superior overall predictive performance under large sample condition. The proposed cooptimization strategy overcomes the limitations of traditional single strategy through the closed-loop interaction between dynamic sampling and Bayesian hyper-parameter optimization (HPO). This approach not only significantly improves the predictive accuracy of surrogate models but also greatly reduces the computational cost during the optimization process, making it suitable for computational mechanics problems with high nonlinearity and high-dimensional features. This study provides theoretical foundations and practical guidance for the selection and application of surrogate models in composite material structural optimization, contributing to improved design process efficiency and reliability.
Chen, DengnuoZou, RuiChen, Binqi
In recent years, driven by increasing consumer demands for vehicle aesthetics and perceived quality, automotive instrument panels (IPs) have extensively adopted materials with poor friction compatibility, such as chrome-plated strips and synthetic leather. Concurrently, the engineering requirement for tighter matching gaps between components has significantly escalated the risk of friction noise. Traditional mitigation strategies—such as material substitution, increasing gap clearances, or applying physical isolation—are often difficult to implement due to design constraints, rendering the IP a critical high-risk zone for abnormal noise. This paper proposes a methodology to mitigate squeak noise between polycarbonate/acrylonitrile butadiene styrene (PC/ABS) and its mating counterparts by modifying the viscoelastic characteristics of the PC/ABS base material through the addition of a specialized polymer. Furthermore, a neural network model was established to objectively determine the noise compatibility of these materials. Evaluations of the material compatibility before and after modification demonstrate that adding a specific proportion of the special polymer to PC/ABS significantly improves its friction compatibility with materials such as polyvinyl chloride (PVC) skin. The efficacy of this solution was confirmed through application and verification in a mass-production vehicle.
Liu, ZubinCao, ChunyuHou, Hangsheng
Efficient and reliable path planning remains a core challenge for autonomous vehicles operating in dynamic and crowded environments. Although Deep Reinforcement Learning (DRL) has shown considerable potential in autonomous decision-making, it still faces challenges such as insufficient feature extraction, sparse rewards, and low obstacle avoidance efficiency in complex scenarios. To address these issues, this paper proposes an end-to-end path planning framework, PPO-ICM-Attn. Built upon the Proximal Policy Optimization (PPO) algorithm, the framework incorporates a dual-channel attention convolutional neural network module (Attention-CNN) to enhance spatial and semantic understanding of dynamic obstacles, and introduces an Intrinsic Curiosity Module (ICM) to promote active exploration in sparse-reward settings. Furthermore, a reactive avoidance reward function based on velocity-obstacle theory is designed and embedded to achieve real-time proactive collision avoidance in highly dynamic environments. Experiments are conducted in a semi-structured dynamic crowd scenario constructed on the GAZEBO simulation platform. The results demonstrate that PPO-ICM-Attn achieves significant improvements in key metrics such as path success rate, travel time, and path efficiency compared to baseline methods like A*+DWA and standard DRL. Although the gap remains in path efficiency compared to A*+DWA, the proposed method exhibits superior robustness and navigation performance overall, validating its effectiveness in complex dynamic environments.
Shen, ShiquanLiu, JiahaoChen, ZhengLi, ZongdianZhao, YutingWu, MinggongZhao, JieQin, ZongquanWang, Yanfeng
The rapid evolution of electric vehicles (EVs) has led to the development of innovative approaches to optimize ride comfort, handling, and the overall suspension performance. EVs introduce unique challenges due to their distinct weight distribution, powertrain dynamics, and noise characteristics, unlike their conventional internal combustion engine (ICE) counterparts. This paper outlines an advanced damping force modeling methodology using machine learning (ML) techniques to enhance the suspension design process for next-generation EVs. The analysis is based on data-driven ML algorithms, i.e., Gradient Boosting, Random Forest, and Neural Networks, to simulate the nonlinear and frequency-dependent phenomenon of dampers in different operating conditions. A comprehensive dataset, generated through simulation and experimental testing, captures the effects of road profiles, vehicle dynamics, and damping settings. Additionally, this research evaluates the impact of machine-learned damping force predictions on critical ride and handling metrics, including ride comfort, road-holding ability, and energy efficiency. The results demonstrate that the ML models can enhance the iterative design process considerably and help to create the adaptive suspension systems that will address the particular requirements of EVs. This paper contributes to advancing the state-of-the-art of the suspension modeling, incorporating the ML-based insights in the development cycle. It highlights the possibility of artificial intelligence to transform suspension design, paving the way for superior ride quality and vehicle performance in electric mobility.
Hazra, SandipTangadpalliwar, SonaliKhan, Arkadip
This study aims to verify the accuracy and stability of a system used for measuring and analyzing the welding deformation of vehicle bodies under different welding parameters. A 3D laser scanner was employed to capture the surface topography data of the vehicle’s front deck before and after welding. In order to determine the welding deformation, PolyWorks software was utilized for deformation analysis, which processed the 3D scanning data and compared the post-welding data set. A dedicated vehicle body welding deformation measurement system was developed, including hardware configuration and software development. The BP neural network algorithm was adopted to predict the welding deformation, and the results indicated that the deviation between the predicted values and the average experimental measurements was less than 10%. This confirmed the practicality of the BP neural network in predicting welding deformation and highlighted its effectiveness in technical support for the optimization of welding parameters and deformation control in automotive manufacturing.
Li, LinaZhang, YiqiSun, HongchangWei, Xiezhen
Machine learning (ML) techniques are increasingly being applied to establish correlations between input parameters and key process responses in the wire arc additive manufacturing (WAAM) process. Despite their potential, there remains limited understanding of how to develop an integrated ML framework that simultaneously considers both the dataset characteristics and the modeling approach to ensure accurate and reliable predictions. The present study addresses this gap by developing an integrated ML framework to predict the deposition behavior of Inconel 625 in WAAM. To capture nonlinear system behavior, three ML methods, namely artificial neural network (ANN), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS), were developed and systematically evaluated for predictive modeling and process optimization, considering deposited geometry, area, and efficiency as the key output characteristics. The input parameters, i.e., voltage, wire feed rate, torch travel speed, and shielding gas flow rate, were identified as critical factors influencing the deposition process. The datasets were preprocessed to remove noise and analyzed to extract relevant features that captured the intrinsic physical behavior of the process. Performances of the ML models were evaluated using a separate test dataset, and predictions were assessed through mean absolute percentage deviation (MAPD). Results demonstrated that integrated ML framework could accurately represent intricate interdependencies among process parameters on deposition outcomes, providing a robust method of predictive modeling and parametric process optimization for Inconel 625 deposition by WAAM process. The ANN model demonstrated satisfactory performance for forward modeling with MAPD values of 12.24, 14.87, and 11.91 for deposition geometry, deposition area, and deposition efficiency, respectively. For inverse modeling, the ANN accurately predicted key inputs from outputs, with MAPD values of 1.39, 18.91, 12.25, and 19.36 for voltage, wire feed rate, torch speed, and shielding gas flow rate, respectively. Bidirectional predictive modeling keeps to set operating conditions to achieve desired depositions and process automations.
Samanta, AvishekMaji, Kuntal
Rocket projectiles are a type of ammunition that get their power from rocket engines. Long-range guided rockets, in particular, hold great significance as they seem to mark the way forward in modern warfare. These guided projectiles take full advantage of the considerable range that long-range rockets offer and, at the same time, manage to achieve improved accuracy. This paper delves into a model that is used for predicting the impact point of rocket projectiles, with the application of the proportional navigation guidance law. It also undertakes an analysis of both the strengths and the weaknesses of this model. Through the formulation of equations related to the dynamics of the center of mass and some other supplementary equations, a rather comprehensive trajectory equation was worked out. When this trajectory was simulated, it brought about the creation of a firing table, which is of help in predicting the initial trajectory inclination angle.
Tao, WenwenWang, RuZhang, LiangPi, Runge
Accurate prediction of ground settlement induced by rectangular pipe jacking, a prevalent trenchless technology in urban infrastructure development, remains a significant challenge. This study addresses this by developing and evaluating a robust machine learning (ML) framework. Leveraging 104 sets of field monitoring data from the Liuye Avenue West Extension rectangular pipe jacking project in Hunan, China, key construction parameters including jacking force, advance rate, and grouting pressure were utilized as inputs to predict ground settlement. A Particle Swarm Optimization (PSO) algorithm was integrated for automated hyperparameter tuning of six distinct ML models: standalone Least Squares Support Vector Machine (LSSVM), Backpropagation Neural Network (BPNN), Random Forest (RF), and their respective PSO-optimized counterparts. Comprehensive performance evaluation using Mean Squared Error (MSE), Mean Absolute Error (MAE), and Coefficient of Determination (R^2) revealed that the PSO-LSSVM hybrid model achieved superior predictive accuracy and generalization capability. Specifically, on the test dataset, the PSO-LSSVM model yielded an MSE of 0.367, MAE of 0.424, and an R^2 of 0.941. These findings demonstrate that the proposed PSO-enhanced LSSVM model significantly outperforms baseline models, offering a highly effective and reliable tool for predicting ground deformation in similar complex pipe jacking projects.
Hu, ShiweiHu, RongZhang, HongChen, YiHu, Da
During the high-speed operation of packaging machines, if the abnormal components evolve into faults, the packaging machines often stop for inspection or even damage, causing production stagnation and huge economic losses. If key variables are predicted and faults are identified before the evolution of packaging machine failures, it is of great significance to ensure equipment safety and reduce maintenance costs and losses for enterprises. The purpose of fault prediction is to use the information modeling of equipment historical data to output the changes in key features before component failures in the future. Firstly, for the redundant data of multiple measurement points of the same variable in the packaging machine process variables, Pearson correlation analysis is used to obtain more accurate variable data. We reuse adaptive empirical mode decomposition (EEMD) for signal processing and feature extraction, reduce redundant information, use convolutional neural network (CNN) models for spatial feature learning, and then use bidirectional long short-term memory models to capture temporal dependencies of CNN information for capturing time series data. A model is established on the normal training set to fit the normal state of the packaging machine, identify different types and degrees of equipment fault characteristics through normal test set data, and send the predicted results of the equipment state to the fault classifier for judgment to determine whether to issue a fault warning. The results indicate that this article has validated the effectiveness of the model in fault feature extraction and high-precision fault classification through training on equipment status data.
Wu, AiminLiu, ShixianZhao, LihuiLiu, ZhaoWu, TaoLi, Lianbing
Accurate projectile dynamic modelling requires identifying aerodynamic parameters. The traditional methods for identifying aerodynamic parameters of missiles suffer from significant modeling errors. Therefore, this study proposes an improved butterfly-shaped optimization hybrid extreme learning machine algorithm. It combines the butterfly algorithm with a hybrid extreme learning machine, Cauchy mutation, and adaptive weight. The search ability of the Butterfly algorithm is enhanced by introducing the Cauchy distribution function and adaptive weighting factors. In addition, to balance the weights of searches and to optimize the regularization coefficients and kernel function parameters, the dynamic switching probability p is introduced. The identification accuracy of four different algorithms was compared under noise-free conditions. The feasibility of the improved butterfly-optimized hybrid extreme learning machine was verified. When there is noise, the strength of the algorithm is confirmed by comparing the effect of different noise levels on how well it can identify things. The simulation results show that the improved butterfly optimization hybrid extreme learning machine algorithm has higher accuracy and better robustness in identifying projectile aerodynamic parameters. The simulation results show that the improved butterfly optimization hybrid extreme learning machine algorithm has higher accuracy and better robustness in identifying projectile aerodynamic parameters.
Wang, QianqianWang, KangjianJiao, WenjieYi, WenjunChen, Jintong
This study aimed to develop a real-time Pilot-Induced Oscillation (PIO) detector by utilizing a Convolutional Neural Network (CNN) and applying it to flight test monitoring. For data training, a database of PIO samples is established. CNN has the advantage of lower complexity and automatic feature learning; it is chosen to develop the PIO detector. The results showed that the accuracy of the trained model has reached 93.71%, where the recall rate reaches 94.74%. To better assist the monitoring team, a simple software is designed based on the trained model for PIO detection, and it has been applied in flight test monitoring. In conclusion, this research demonstrates that the CNN Algorithm can be utilized in PIO discrimination and improve the monitoring capacity for flight testing.
Han, YiwenLiu, Chaoqiang
In this study, an efficient method for concurrent thermomechanical performance and weight optimization under modal constraints is proposed to address the coupled design challenges of thermomechanical characteristics (thermal capacity, thermal deformation, and modal) and structural weight in straight-ribbed brake discs. Based on high-fidelity computer-aided engineering (CAE) simulations of brake disc thermomechanical behavior, a neural network (NN)-based surrogate model and a ResNet-guided geometric feature recognition (RGFG) model for automatic modality recognition were developed, and integrated with a particle swarm optimization (PSO) framework for optimal solution exploration. When applied to a passenger vehicle brake disc case study, the surrogate model of NN demonstrates remarkable accuracy: it shows more than 95% agreement with the CAE results in thermal capacity prediction, the prediction accuracy of thermal deformation exceeds 90% compared to CAE results and 83.4% compared to test result, thereby validating the method’s effectiveness. Compared with conventional CAE approaches, the surrogate model of NN achieves a subsecond prediction speed, significantly reducing computational costs. The surrogate model of RGFG achieves a test accuracy exceeding 95%. Furthermore, the proposed optimization framework offers valuable insights for the inverse design of brake discs.
Han, SimiaoJiang, DaxinHan, ChaoWang, JindaSui, Qinghai
In map-free geomagnetic navigation conditions, the traditional matching algorithms will be ineffective, and the regular position searching optimization algorithms still face the problems of low navigation accuracy and inefficiency. How to further improve the accuracy and efficiency of the algorithm has become the key to the application of this method in maple’s geomagnetic navigation conditions. Based on the above background, this paper proposes an evolutionary gradient search navigation algorithm optimized via position estimation (PE-EGA). The world geomagnetic model (WMM) is used to establish the nonlinear correlation relationship between geographic position and geomagnetic features, and the inverse mapping of the geomagnetic model is fitted by a fully connected neural network to get the rough estimation of the geographic position of the vehicle, with a root mean square error (RMSE) of 0.0121 in position estimation. Finally, the information of the rough estimation is used to assist the decision-making of the navigational azimuth angle involved in the EGA algorithm. The simulation results show that the offset distance of the improved algorithm is only 27.09 m, and the path ratio reaches 1.0178 with an error ratio of 0.38%. Comparative study using measured geomagnetic data of Boao town with model data shows that the final offset distance is only 51.63 m, path ratio 1.0036, and error ratio 0.73%, which significantly improves the accuracy and timeliness of navigation compared to the original EGA algorithm. This article provides an innovative and practical solution strategy for map-free geomagnetic navigation.
Xie, WenbinLiu, HongjieZheng, RuifanRen, XintianYan, BingQiu, WeiChen, Zhuo
Terminal guidance is critical for ensuring strike precision in the final phase of flight. However, traditional methods, such as proportional navigation and optimal guidance laws, face significant challenges regarding real-time performance and adaptability to dynamic targets. To address these issues, neural networks offer a promising solution by enabling adaptive adjustments to guidance parameters, thereby improving performance under various constraints.
Ma, HengweiWang, YongfengWen, HongLiu, DiWei, YuanhangDong, LonghaoLuo, Ying
Efficient optimization of aerodynamic shapes is a critical challenge in aircraft design. Traditional CFD-based optimization workflows suffer from high computational costs and low efficiency, which severely restricts their practical engineering application. In this paper, a novel aerodynamic optimization method based on a hierarchical neural network with adaptive activation functions is proposed. The network adopts learnable B-spline activation functions and is hierarchically constructed in accordance with the sharing status of B-spline control points. After being trained to achieve fast and accurate prediction of aerodynamic performance, the network can effectively replace the traditional CFD module in the optimization loop. The primary advantage of the proposed method is that it significantly reduces the computational cost during the optimization process while ensuring that the prediction accuracy is not compromised. This work thereby presents a novel strategy and technical framework for streamlining the design process of hypersonic vehicles.
Liu, DiWang, YongfengWen, HongWei, YuanhangMa, HengweiZhao, Runhui
This paper constructs a reinforcement learning framework based on the PPO algorithm for drone air combat to solve 1v1 pursuit-evasion in 2D beyond-visual-range air combat. Firstly, the mission scenario is modeled, defining key roles of ATA and AA. Then, state transition models of pursuer and evader are built based on flight kinematics. To handle reward sparsity in policy network training, a dense reward function combining distance and angle rewards is designed to guide the agent in learning tail-chasing and interception strategies. Using the Actor-Critic architecture, deep neural networks implement the decision-making and evaluation modules. The PPO algorithm trains the pursuing drone in a simulation. Results show that after ~5 million steps, the agent learns a stable strategy, completing tasks promptly and generalizing well in unseen scenarios. This research offers ideas for drone combat and guidance, and supports autonomous decision-making in complex air battles.
Yu, KangjieGong, ZhengHu, RunchangLiu, Huixiang
This paper presents an innovative study in exploring, evaluating, and implementing deep-learning architectures for the calibration of multimodal sensor systems. The aim of this paper is to leverage the use of sensor fusion to achieve dynamic, real-time alignment between 3D LiDAR and 2D camera sensors. Static calibration methods are tedious and time-consuming, which is why we propose utilizing conventional neural networks (CNNs) coupled with geometrically informed learning to solve this issue. We leverage the foundational principles of extrinsic LiDAR–camera calibration tools such as RegNet, CalibNet, and LCCNet by exploring open-source models that are available online and compare our results with their corresponding research papers. Requirements for extracting these visual and measurable outputs involved tweaking source code, fine-tuning, training, validation, and testing of each of these frameworks for equal comparisons. This approach aims to investigate which of these advanced networks produces the most accurate and consistent predictions. Through a series of experiments, we reveal some of their shortcomings and areas for potential improvements. We find that LCCNet yields the best results among all the models that we validated.
Karramreddy, Venkat Sai RaxitMitchell, Liam
This paper puts forward a Privacy-Preserving UAV-Based Traffic Data Acquisition Platform to address 1) privacy leakage, 2) limited scenario coverage, and 3) low traffic data utilization efficiency in urban traffic monitoring environments. Our system integrates three innovations: 1) Dynamic Privacy Masking (DPM) and Dual-Track acquisition (DTC), which hides sensitive information (e.g., faces, license plates or LPL) in real-time while preserving critical traffic data (e.g., vehicle density, speed), 2) traffic data Localization (DL) and Privacy-Enhanced Federated Learning (FEFL), enabling cross-regional collaboration without raw traffic data sharing by perturbing neural network updates with differential privacy (DP), and 3) Ground-Air Collaboration (GAC) and VPF (VPF), combining UAVs with ground sensors and digital twins (DTs) to cover blind spots (e.g., tunnels, extreme weather). Experimented on UA-DETRAC and CitySim traffic data-sets, the platform achieves 92% privacy compliance (GDPR/PIPL), 87.5% mAP accuracy, and 85% road network coverage, outperforming other methods (e.g., FedUAV, static blurring). It supports applications such as traffic flow optimization, accident prevention, and regulatory alignment.
Zhang, ShilinYan, Ming
With the rapid development of the low-altitude economy—represented by drone logistics, aerial inspections, and air taxis—air traffic has exhibited new characteristics including diverse forms, high density, and significant speed differences. To address these changes, the traditional air traffic control system requires upgrades, particularly in dynamic aircraft scheduling. This study proposes an air traffic control model (DS-ATM) tailored to this domain, built on the Deepseek large model. By integrating spatiotemporal graph neural networks with multi-objective reinforcement learning algorithms, the model achieves real-time path planning and conflict resolution in complex airspace environments. Validated using public datasets such as OpenSky Network, NASA UTM Dataset, and METAR meteorological data, experimental results demonstrate its significant advantages in reducing conflict rates and scheduling delays.
Li, RuiZhao, FangyuShe, YueLi, Wujie
To address the high operating cost of online cylinder pressure monitoring systems for low-speed engines in ships and the limitations of existing alternatives - i.e., the lack of flexibility of the mechanical model under different operating conditions and the lack of physical interpretability of the data-driven model - this study proposes a hybrid-driven based in-cylinder pressure calculation model. Taking the 6EX340EF marine low-speed engine as the object of study, the method first constructs a mechanical model and optimizes the Wiebe function parameters using the Dung Beetle Optimizer (DBO). Subsequently, the mapping relationships between operating parameters, Wiebe parameters, initial compression stage temperature and charge mass are learned by constructing a combined neural network of Convolutional Neural Network (CNN) and Bi-directional Long and Short-Term Memory Network (Bi-LSTM). Finally, the overall calculation of in-cylinder pressure was realized by integrating a multidimensional parametric framework of engine configuration parameters, real-time running inputs and dynamic MAP maps. The results show IMEP R2 = 0.9864 and peak pressure error ≤ 2%, confirming that the model can provide technical support for long-term real-time pressure measurement and closed-loop optimization control based on in-cylinder pressure for marine low-speed engines.
Huang, Jialong
This paper reviews data fusion strategies for generating aerodynamic databases and evaluates their suitability for motorsport aeromaps, with emphasis on the operational constraints specific to Formula One. A structured survey and classification of the state of the art is presented, grouping approaches into (i) surrogate-agnostic methods, (ii) kriging-based methods, and (iii) neural network–based methods. In addition, the survey explores advanced techniques currently underutilized in aerodynamic database applications but that show promise. These methodologies are discussed in the context of addressing limitations inherent in traditional approaches, such as dependency on nested sampling plans and linear correlation assumptions between low- and high-fidelity datasets. The review indicates that, although multi-fidelity data fusion is well established in aerospace aerodynamic database generation, its direct translation to motorsport requires additional considerations. In the Formula One context, the most plausible deployment may involve fusing legacy and current datasets, rather than combining low- and high-fidelity evaluations of the same geometry. This shift in premise could increase exposure to negative transfer and therefore necessitate additional methods to minimize it. This study provides one of the first motorsport-focused reviews and syntheses of data fusion methods for aerodynamic database generation. It is intended to guide motorsport engineers and researchers toward more efficient and effective aeromap generation strategies. Collectively, the findings establish a foundation for subsequent phases of a broader project to minimize the number of data points required to generate an aeromap, with the present survey constituting the first part of that effort.
Ongley, Thomas James HenryTeschner, Tom-RobinAshton, NeilSiampis, Efstathios
Software-defined, highly customizable vehicle architectures drastically increase the number of hardware–software constellations that must be validated, especially under safety and timing constraints. Traditional unit and integration testing, as well as current regression and combinatorial methods, cannot practically cover this configuration space or reliably capture emergent effects arising from complex interactions, such as bandwidth contention and non-linear latency behavior. This work presents a proof-of-concept for predictive, situational validation of self-describing hardware and software components within realistic automotive E/E architectures. Proposing a novel Machine Learning- (ML) based method for early systemic feasibility prediction of automotive configurations using Graph Neural Networks (GNNs). Specifically, the subclass Graph Isomorphism Networks (GINs) is applied to predict the compatibility of a randomly composed configuration of software and hardware components, assessing both structural compatibility and functional stability. The trained models achieve recall and accuracy above 90%, even when detailed behavioral metadata is hidden during training, indicating that systemic incompatibilities are learnable from topological features alone. Results were achieved from training on a realistic, synthetic dataset representing less than 10e−27% of all possible permutations without finetuning or further parameter optimization. It demonstrates the potential of GIN-based graph learning to enable early, automated feasibility assessment, substantially reducing testing time and development effort for modular, personalized, and update-capable vehicle architectures.
Wizl, JensGuarda, Filippo
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 range of applications in AI-driven truck development.
Vaudrevange, Patrick K.S.Halverson, JamesRuehle, FabianFabcic, TomazDingler, ChristianPiskala Dilipkumar, SanthoshkumarIbrahim, MuhammedHerrnberger, MichaelKasper, JohannaTürk, LarsKeckeisen, Michael
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 explainability, a circumstance which renders them challenging to employ in production vehicles. In this article, we present an explainable approach to automating the calibration process using residual RL which follows established automotive development principles. Its applicability is demonstrated by means of a map-based air path controller in a series control unit using a hardware-in-the-loop (HiL) platform. Starting with a sub-optimal map, the proposed methodology quickly converges to a calibration which closely resembles the reference in the series ECU. The results prove that the approach is suitable for the industry where it leads to better calibrations in significantly less time and requires virtually no human intervention.
Kampmeier, AndreasBadalian, KevinKoch, LucasLee, Sung-YongAndert, Jakob
The optimization of energy management strategies for hybrid electric vehicles is crucial for minimizing fuel and electrical energy consumption while maintaining the energetic stability of the electrical system. Conventional heuristic, rule-based approaches typically rely on classical optimization techniques and manual calibration by experienced engineers. These methods often suffer from simplified assumptions, sub-optimality, and are increasingly time-consuming given the growing complexity of modern hybrid powertrain architectures. This research proposes a novel methodology for the development of a learning-based energy management strategy (EMS) via deep reinforcement learning (DRL) to transition toward highly automated, data-based, and optimization-based development approaches. The methodology utilizes the Soft Actor-Critic (SAC) algorithm, an off-policy actor-critic method, to train an agent through experiences by interacting with an environment. The environment consists of a backward-looking, quasi-static vehicle longitudinal dynamics simulation model of an exemplary P2 plug-in hybrid electric vehicle (PHEV) combined with a database of customer-representative driving profiles. The agent learns optimal control policies through defined states and actions, optimizing a multi-criteria reward function that balances fuel efficiency against energetic stability. The framework permits the definition of both non-predictive and predictive states. Additionally, a shield function is implemented to consider hard constraints ensuring safe and stable operation. Variation calculations and sensitivity analyses regarding reward function shaping and hyperparameter tuning are conducted. The agent is trained in an offline simulation environment, and the learned policy of the trained deep neural network (DNN) is transferred into deterministic control maps, applicable to vehicle control units, ensuring interpretability, reproducibility, and compliance with certification requirements. Finally, exemplary simulation results of the DRL-EMS approach are presented and compared to benchmark equivalent consumption minimization strategy (ECMS). In conclusion, the proposed methodology enables a generally valid approach for the development of learning-based energy management strategies towards close-to-optimal strategies while reducing manual calibration effort.
Metzler, SebastianWinke, FlorianJungen, MarioSchmiedler, StefanHofmann, PeterGeringer, Bernhard
Achieving best-in-class Noise, Vibration, and Harshness (NVH) in electric powertrains demands a paradigm shift in development methodology. This paper presents a practice-oriented overview of simulation methods in NVH development methodology for electric drive units. This includes target cascading and multi-objective optimisation, and by attacking NVH at the source using KPIs early in the design cycle, significant reductions in development time and reliance on traditional testbed loops are realised. Machine learning (Neural Network) algorithms are utilized to find the best-in-class design, using multi-objective optimisation as well as refining simulation accuracy by adding tolerance effects while target cascading ensures alignment of system-level performance objectives down to subsystem contributions. Combined, these strategies enable rapid and robust NVH optimisation, using simulation for next-generation electric powertrain development. Several applications and real-life examples demonstrate how simulation helped with NVH issue identification or improvement.
Mehrgou, MehdiGarcia de Madinabeitia, InigoGraf, BernhardGojo, Josef
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 stage, 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 serve as training data, for various hole distributions. The trained model is then used to predict acoustic natural modes and natural frequencies from unseen input images representing different hole configurations in the package tray. These predictions are made in a fraction of the time required for traditional simulation methods, thereby validating the model’s effectiveness. Furthermore, we demonstrate that the latent variables embedded in the trained model can be manipulated to control the acoustic modes and natural frequencies of the sedan. This indicates the potential for artificial intelligence-driven acoustic design optimization in early-stage vehicle development, offering both time efficiency and design flexibility without physical prototyping or extensive simulations.
Lee, Jin WooCho, JaehoNam, YounsicHan, Yongha
In recent years, the automotive industry has actively explored the application of various AI-based models such as Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, Autoencoders, and Transformers to improve defect detection rates at the End-of-Line (EOL) stage. However, implementing these approaches in the Noise, Vibration, and Harshness (NVH) area face several practical challenges: ① extended evaluation times compared to other data types, which limit the quantity of training data and lead to overfitting; ② label imbalance caused by the relatively small amount of defect data; ③ reduced labeling accuracy due to human error; ④ decreased robustness under domain shifts such as changes in jig fixtures, test environments, and signal-to-noise ratio (SNR); ⑤ diminished model reliability when new defect arise during development; and ⑥ constraints imposed by compatibility requirements with existing test equipment. This study proposes a Convolutional Autoencoder (CAE) based framework trained on NVH datasets collected from normal and defective Column-type Electric Power Steering (C-EPS) systems. Latent variables at the bottleneck layer are used for dimension reduction, enabling visualization and unsupervised classification using a clustering algorithm. A classification model derived from the encoder is fine-tuned with clustered data, and Gradient-weighted Class Activation Mapping (Grad-CAM), an eXplainable AI (XAI) technique, is applied to extract Feature Frequency Maps (FFM) highlighting defect-related noise and vibration characteristics. The proposed approach does not rely on the deep learning model to directly classify defect. Instead, it utilizes extracted FFM as weights(mask) to detect defect. This method enables quantitative data representation and ensures high applicability with existing EOL equipment. Post-processing within the FFM enables root cause analysis, reducing issue resolution time and supporting integration with conventional signal analysis techniques.
Park, Jun-SeoJo, Hyeon-ChoelCho, In-JeSeo, Jae-YongYoo, Seong-Sik
This paper addresses the critical challenge of fault-tolerant control in autonomous multi-copters, particularly under conditions of one or two rotor failures a scenario that often leads to severe instability and a complete loss of directional control due to unbalanced torque and resultant autorotation. Existing advanced control strategies, including optimal approaches such as LQR, typically require precise system modeling and state estimation, which are difficult to achieve in real-world, dynamic failure scenarios. Alternative methods like fuzzy logic, sliding mode control, and gain-scheduling either lack robust generalization or are impractical for enumerating all possible failure cases. In this work, a hybrid control framework integrating Physics Informed Neural Networks (PINN) with a standard PID controller is proposed for fault-tolerant operation of autonomous multi-copters subject to multiple actuator failures. PINNs incorporate governing physical laws as regularization in their loss functions, allowing them to learn optimal counter-torque actions and thrust balancing necessary to arrest autorotation and stabilize flight, despite limited training data and uncertainty in failure conditions. The calculated moments and thrust commands are executed via a robust PID scheme, enabling reliable real-time implementation and minimizing residual oscillations. This hybrid control architecture demonstrates significant potential to enhance the resilience and operational safety of autonomous multi-copters during unexpected motor failures. By leveraging PINN’s physics-based generalization and PID’s consistent execution, the proposed method offers an adaptive, model-agnostic approach for maintaining stable flight and directional control under severe actuator faults, with implications for next-generation fault-tolerant UAV systems deployed in complex environments.
Charapalle, SamruddhiVenugopalan, NandagopalanNerkundram Muralidharan, ArunSundararaj, Laveen
The electrical harness system of satellite launch vehicles functions as the backbone of spacecraft avionics; inter connecting subsystems through complex networks of wires and connectors. An electrical harness is a group of wires bunched together and terminated in connectors. The common insulations used for launch vehicle applications include PTFE, Polyimide, ETFE and TKT. The connectors used are of aerospace grade and connectors tailored for space applications. With over 5000 connectors and 200 km of cables constituting nearly 20% of vehicle mass, the design, fabrication, and sustainability of these systems are critical. The insulations of connectors inserts or the wires are critical for the durability of harness elements. Nevertheless, these insulations are non-expendable and pose disposal challenges and some releases toxic gases when burned or due to vacuum outgassing phenomenon. Also, the cadmium plating which is often used for the environmental resistance of connector shells presents additional risks to the working humans due to its carcinogenic nature and shows tendency to bloom out during storage. This paper presents the methodologies and innovations implemented to develop safe, reliable, and environmentally sustainable harness systems for current and future launch vehicles. Key advancements include the adoption of lean manufacturing practices for waste reduction, the replacement of hazardous cadmium-plated connector shells with stainless-steel alternatives, and the induction of TKT-insulated wires to prevent arc tracking and ensure human-rating compatibility. Additionally, lightweight composite connectors and micro-miniature interconnects are being qualified to support mass optimization in reusable launch vehicles. Through these strategic measures, the study demonstrates how the integration of sustainable materials, safety-oriented design, and process optimization can enhance the performance, safety, and environmental footprint of launch vehicle electrical harness systems.
K S, NithishTR, BinnyD S, Praveen Kumar
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 (2) a data-driven Recurrent Neural Network (RNN), specifically a Long Short-Term Memory (LSTM) network, for dynamic degradation rate modeling. The methodology utilizes a Monte Carlo simulation coupled with RCF progression equations to generate a large, high-fidelity synthetic run-to-failure dataset under varying operational loads, accurately simulating realistic mission profiles. This approach addresses the critical "data scarcity" challenge in aviation. To ensure operational reliability, the framework incorporates Uncertainty Quantification (UQ) using Monte Carlo Dropout and addresses the "Sim-to-Real" gap through Transfer Learning on the NASA IMS bearing dataset. The HDT demonstrates a significant improvement in prognostic accuracy, achieving a Root Mean Square Error (RMSE) reduction of over 71% compared to baseline models. Furthermore, a cost-benefit analysis suggests a potential fleet savings of $240,000 per 100 engines by avoiding false negatives. This computationally efficient approach supports the Digital Engineering Transformation theme by providing a scalable blueprint for the virtual qualification of critical mechanical components.
Mohamed, Abbas
Neural Network Enabled Synthetic Air Data System: Development and Validation2026-26-07206/1/2026
Synthetic Air Data System (SADS) provides a smart solution that can be used to predict critical air data parameters in the absence of conventional air data sensors. Traditional air data sensors, such as pitot-static tubes and vanes, are generally expensive, require regular maintenance, and can fail in harsh weather conditions. In addition, these sensors, along with their processor and computers, add weight to the aircraft. To address these issues, a synthetic air data system is proposed using a Recurrent Neural Network (RNN). Several flight variables were checked for Pearson correlation coefficient with respect to the angle-of-attack and angle-of-sideslip, and thereafter, input features were selected based on the thresholding technique. The proposed neural network has two hidden layers and regularization technique was implemented by adding two dropout layers to each hidden layer to prevent overfitting of the model. The neural network was trained using actual flight test data, supplemented with simulated data wherever gaps were observed in the entire flight envelope. The RNN model is trained to predict the aerodynamic flow angles, viz., angle-of-attack and angle-of-sideslip. The proposed model was found to be able to predict the aerodynamic angles with a degree of accuracy. The accuracy was also checked with several complementary actual flight data to check the fidelity of the trained neural network model.
Sahu, SanjuC, PoornimaKaliyari, DushyantTK, Khadeeja NusrathHebbar, Archana
With the introduction of China’s dual-carbon goals (carbon peak and carbon neutrality), renewable energy has experienced rapid development in the country, particularly wind energy, which has established a pivotal role within the new energy sector. However, the inherent fluctuations in wind power generation pose significant challenges to maintaining grid stability and operational reliability. In power systems where the proportion of installed wind power capacity has significantly increased, the allocation of flexible resources becomes crucial. These resources help the system adapt to fluctuations in wind power generation and load demand, avoid wind power curtailment, and reduce costs. In addition, energy storage enhances grid flexibility and stabilizes renewable energy, but is constrained by high costs. Therefore, optimizing energy storage allocation and improving its economic efficiency have become urgent issues. This study focuses on flexibility adequacy assessment and resource allocation, proposing an optimization model that incorporates constraints from wind power, thermal power, energy storage, and load shedding. The model aims to identify the optimal energy storage configuration strategy to minimize operational costs while ensuring system flexibility adequacy. The model is constructed and simulated using MATLAB, with complex optimization problems solved using the Gurobi solver. The research involves developing flexibility evaluation indicators, determining the optimal energy storage capacity configuration, and creating an economic objective function. The goal is to minimize costs while ensuring system flexibility.
Peng, JianWei, JinpengZhu, ZhengyinHu, JianminLi, YuxiangMiao, GangZhang, Huaide
In order to achieve the research objective of simultaneously improving the air volume and reducing the noise of centrifugal fans, a combination of orthogonal experimental design, BP neural network modelling and multi-objective genetic algorithm (NSGA- II) was used to find the optimal method, and the worm tongue placement angle φ, worm tongue radius R, expansion angle θ and outlet expansion section height L of the worm casing were selected as optimization variables. The air volume and noise of the centrifugal fan under the design working condition were calculated by non-constant and constant calculations, and the air volume and noise were used as the optimization objectives. The results demonstrate that, compared to the initial design, the optimized fan model achieved a noise reduction of 10.99 dB and an airflow increase of 1.76%. Furthermore, the amplitude of the pressure pulsation coefficient at the blade passing frequency was significantly reduced at the monitoring point near the volute tongue. This suggests a reduction in the intensity of dynamic and static interactions between the impeller and the volute tongue, thereby enhancing the operational stability of the fan. The proposed optimization method has certain reference significance for improving the aerodynamic performance of centrifugal fans.
Huang, GuoxingZhang, WeihongLi, Weichang
This paper extends a previously developed adaptive pilot model framework for inner-loop roll-attitude tracking [1] to outer-loop position tracking tasks. Pilot Model identification is performed for two command signal types - a discrete step-like signal and a continuous Sum-of-Sines (SOS) signal - yielding distinct parameter signatures that reflect the different anticipatory and tracking demands of each signal type. An adaptive pilot model for the outer-loop position tracking task is formulated using a model-reference neural network (MRNN) architecture with a linearly parameterized neural network updated by a Lyapunov-stable adaptive law. Simulation results for both discrete and continuous tasks demonstrate that the adaptive pilot model remains stable and maintains position tracking performance under both a doubling and a halving of the nominal control sensitivity. Preliminary results are also presented for a multi-axis maritime task, extending the framework to simultaneous lateral and vertical position tracking.
Keller, AlexanderChen, ZhouzhouHorn, Joseph
The proliferation of Autonomous Aerial Vehicles (AAVs) necessitates robust solutions for dynamic obstacle avoidance, particularly against non-cooperative intruders whose trajectories are unpredictable. While traditional path-planning algorithms excel in static environments, they struggle with dynamic obstacles due to the inherent difficulty in accurately estimating and registering their real-time depth and velocity into a world model. This paper presents a novel two-stage vision-based framework that leverages deep learning for reactive avoidance of non-cooperative dynamic intruders. Our approach decouples the perception and decision-making processes: an object detection deep neural network first processes monocular camera images to detect and track the 2D pixel coordinates of intruders. This perceptual output is then fed into a deep reinforcement learning agent, which learns a mapping from the intruder's image-space location to a high-level avoidance maneuver. This leads to more efficient learning, as the RL agent focuses solely on the policy without the burden of learning visual features. The advantage of using RL lies in its ability to handle partially observable situations—because reliable depth or full 3-D position information is not always readily available from monocular imagery, the RL agent learns to act based on the observable visual cues. Simulation results confirm that our proposed framework provides an effective solution for vision-based, non-cooperative intruder avoidance.
Dadkhah Tehrani, NavidWeintraub, JustinAmonkar, RikhilCarlson, SeanCherepinsky, Igor
This paper presents a spatio-temporal graph neural network (STGNN) centric approach to enable heterogeneous agents to collaborate and cooperate for different types of missions. The STGNN-centric approach and corresponding autonomy are encapsulated in the Advanced Graph-enabled Network Technology for Collaborative Autonomous Agents (AGENTCA) technology. Various decentralized and distributed control architectures are reported in the literature, but in some instances these approaches do not leverage the inherent graph network which can increase scalability to larger teams and algorithmic efficiency. Specifically, in this paper advances in artificial intelligence are leveraged to parameterize and encode optimal, or nearly optimal, swarm control techniques. For this work, the team focused on developing a diffusion-based STGNN swarm controller using imitation learning. An expert, centralized swarm control law was used to guide the STGNN during the learning process. The STGNN controller enables the swarm to follow a leader while avoiding static and dynamic obstacles and maintaining a desired separation distance from neighbors and obstacles. The approach is demonstrated in simulation with hundreds of agents and in flight tests with up to thirteen test vehicles.
Cooper, JaredLu, Chang-TienChen, SijiCarson, AndrewPeters, AndrewOlowin, AaronEnnasr, OsamaLichter, Matthew
This paper introduces a robust supervised machine learning framework for estimating helicopter gross weight during the takeoff phase. The methodology leverages high-fidelity datasets from Airbus's global in-service fleet to ensure a reliable training foundation. At the core of the approach is a long short-term memory recurrent neural network, supported by a patented data-curation pipeline designed to maintain high data integrity. To align with rigorous aviation safety standards, the study outlines a learning assurance process compliant with EASA guidelines, specifically addressing safety assessment objectives for machine learning. A central innovation is the characterization and monitoring of the model's operational design domain through multidimensional functional principal component analysis. By projecting high-dimensional, non-linear sensor data into a manageable tabular subspace, this approach enables the definition of safety envelopes using explainable and efficient classical methods. Validated against diverse real-world flight profiles, the framework demonstrates high predictive accuracy, marking a significant milestone toward deploying the model on airborne targets for safety-critical functions such as condition-based maintenance.
Mechouche, AmmarFabre, LouisValot, Nicolas
This paper focuses on the implementation of a novel supervised Machine Learning model for estimating helicopter weight during takeoff, utilizing extensive datasets from Airbus's global in-service fleet. The study details a learning assurance process aligned with the EASA concept paper for machine learning application, and with the on-going Eurocae ED-324. We propose a set of Machine Learning Requirements, a Machine Learning Model Description, and its implementation for a long short-term memory recurrent neural network. Finally, we verify the requirements on the implementation. Demonstrated on legacy avionics computers, the implementation is suitable for the deployment of the developed Machine Learning Model weight estimator on airborne targets for critical functions such as on-board alerting.
Valot, NicolasFabre, LouisPagetti, ClaireMechouche, AmmarLesage, Benjamin
Evaluating rotor component clearances is a multidisciplinary process aimed at ensuring that no contact occurs between rotor parts during a rotorcraft's operational life. It begins with calculating relative distances between components across all possible displacements and deformations combinations using a rotor kinematic model, and ends with clearance verification through flight data analysis and simulation. This task requires coupling detailed rotor aeroelasticity with flight mechanics to predict deformation under load, which is computationally expensive and unsuitable for real-time use. This work proposes a machine learning–based alternative: a neural network to estimate rotor clearances from flight mechanics inputs, with a specific application demonstrated in a simulated tiltrotor emergency maneuver with a pilot in the loop. The trained model successfully captures nonlinear relationships between maneuver parameters and rotor structural response, providing accurate predictions with reduced computational cost. The proposed framework can support both preliminary and detailed rotorcraft design and offers potential for real-time load prediction in applications where conventional aeroelastic tools are computationally expensive.
Zaccaria, AlessioOrsenigo, SimoneGerosa, GiacomoBergamasco, Marco
This article surveys the most recent data-driven methods of lithium-ion (Li-ion) battery state of health (SOH) estimation methods and dataset resources utilized in electrified vehicles (EV) and their potential adoption for automotive battery management systems. These include regression-based models, ensemble learners, deep neural networks, and physics-informed hybrid methods. The review describes estimation methods found in articles published between 2023 and 2025, and investigates their differences in terms of estimation accuracy, data requirement, interpretability, and real-time deployment ability. The article traverses the dataset space, focusing on laboratory aging datasets, vehicle field–based datasets, telematics-derived records, and synthetic or augmented datasets, to underline that model performance in the estimation of SOH cannot be disentangled from the quality of the data, the operating coverage, and the transfer conditions. Apart from the model design, this work reviews the large-scale estimation pipeline, which involves preprocessing under sensor noise and irregular timestamps, feature extraction from incremental capacity, differential voltage, relaxation response and impedance-related indicators, and uncertainty handling for diagnostics and safety-based decision support. Practical constraints to the deployment of embedded BMS are covered. Such as ECU memory and computing limits, communication overhead, calibration effort, update approach, and functional-safety requirements. The review determines that the distance between laboratory validation and field robustness is large raising a need for more work in this area and also, that domain adaptation, federated learning, and improving benchmarking practice turn out to be promising directions for improving generalization and reproducibility. The article concludes that future advances in automotive SOH estimation will not only rely on better learning algorithms but also on improvement in the availability of realistic and field representative data, the application of robust evaluation mechanisms, and methods that are developed under real BMS constraints.
Nyachionjeka, KumbirayiBayoumi, Ehab H.E.
The performance of chassis suspension mechanisms critically affects vehicle handling, ride comfort, and safety. Implementing real-time health monitoring for chassis systems contributes to preventing severe consequences such as increased body roll or loss of handling stability caused by shock absorber softening or spring stiffness degradation under deteriorating operating conditions, while circumventing the substantial costs associated with professional facility-based chassis inspections. With the rapid development of sensing and data analytics technologies, data-driven approaches are increasingly used in health monitoring. This study aims to achieve online monitoring of chassis suspension performance degradation using a deep neural network (DNN). First, a half-car model incorporating both vertical and pitch motions was established to simulate bumpy road conditions, with the aim of constructing a dataset that includes key vehicle suspension parameters and vehicle states related to their degradation characteristics. Subsequently, a DNN model comprising three hidden layers is developed to assess suspension performance degradation. To optimize model performance, the effects of different numbers of neurons and hidden layers on model accuracy are explored. Experimental results show that the maximum absolute percentage errors of the DNN model in predicting suspension stiffness and damping coefficients are less than 0.13% and 0.17%, respectively, with average absolute percentage errors below 0.046% and 0.06%. The coefficients of determination (R2) exceed 0.999. The proposed method accurately predicts the trend of key suspension parameters, providing robust data support for health management and maintenance decision-making. This is expected to reduce safety risks and maintenance costs while enhancing overall vehicle performance and reliability.
Liao, YinshengLei, YisongSu, AilinWang, ZhenfengShi, ShuaiZhang, LeiZhang, JunzhiMa, Changye
High thermal loads on brake systems during extended descents followed by vehicle soak pose significant safety and durability risks. Excessive rotor or fluid temperatures can cause loss of braking efficacy, fluid degradation or evaporation, thermal fade, and accelerated component wear. This study uses time-history data of brake-disc and fluid temperatures which were collected during controlled hill-descent events with subsequent soak periods, where the vehicle is parked in a wind protected area. Besides the rotor and brake fluid temperatures, environmental conditions were recorded (ambient temperature, humidity, wind speed and direction) and the vehicle and brake specifications are known (rotor/caliper geometry, pad material, vehicle aerodynamic configuration and mass). 126 test runs from a dedicated vehicle program are used, each providing time-history records that form the basis of our analysis. From these records we extract phase-specific samples (descent and soak phase) and engineer compact descriptors — start and peak temperatures, environmental factors, rolling statistics and contextual metadata to represent each event. We develop and evaluate machine-learning regression and neural-network models to predict the disc and brake-fluid temperatures occurring during the descent and across the soak phase. Cross-validation is done to ensure generalization to unseen descent events. Models are evaluated with mean absolute error (MAE) and bias diagnostics. The predictive models enable early warning of critical temperature spikes and support design and operational decisions (cooling design, allowable profiles and optimization). By delivering fast temperature estimates, they reduce reliance on computationally expensive CFD during early design, while CFD and experiments remain for final validation. We present workflow, model performance and uncertainty characterization.
Poojari, Uday KumarWestphalen, JanVenugopal, Narayana
Predicting battery self-discharge across wide temperature ranges and extended durations remains a significant challenge due to the scarcity of physical test data, which is typically limited to a few temperature points and short observation windows. This limitation complicates generalization and increases the risk of inaccurate extrapolation. To address this, the paper introduces a machine learning–based framework designed to predict self-discharge behavior under diverse thermal conditions and longtime horizons. Multiple modeling strategies are examined, including feedforward neural networks, long short-term memory (LSTM) architectures, synthetic data generation, and physics-informed integration of governing equations. Particular emphasis is placed on hybrid and physics-regularized models that embed first-principles relationships to guide extrapolation beyond the observed data domain. This approach mitigates the inherent instability and potential errors associated with purely data-driven models. Each method is evaluated for predictive accuracy, robustness, and physical plausibility. The paper concludes with recommendations for model selection, and deployment strategies within battery aging prediction workflows.
Chavare, SudeepZeng, YangbingMuppana, Sai SiddharthaMiao, YongXu, Simon
The push for vehicle development through virtual prototyping and testing in motorsports highlights the critical challenge of tire model selection and calibration, especially when vehicle dynamics must be accurately captured. The calibration process for tire models such as the Pacejka Magic Formula (MF) relies on parameter identification and experimental data fitting. While optimization algorithms have been implemented to calibrate tire models, few studies explore the effects of parameter selection on overall vehicle performance, complicating prioritization for the vehicle’s modeling and simulation strategy. To bridge this gap, this paper leverages optimal control methods to quantify how the variability of MF tire model parameters propagates to the overall vehicle model and impacts lap time prediction accuracy. To achieve this, a subset of parameters critical to combined slip of the MF tire model are varied through a Design of Experiments (DOE). These variations are executed on a flat oval track to simplify the dynamics yet exhibit combined slip characteristics using a fixed vehicle configuration. The minimum lap time problem is solved using collocation methods via Dymos, an optimal control library for multidisciplinary systems. A neural network surrogate model enables an interactive profiler to visualize lap time sensitivity to tire model parameters. The primary contribution of this work is a framework that parametrically connects high-level, vehicle-wide metrics such as lap time to the calibration process and selection of tire models. The parametric and interactive nature of the framework allows high-level insights across the whole design space of tire model parameters. Insights derived from this framework provide a basis to develop a strategy for prioritizing testing and calibration efforts driven by vehicle level impacts of model parameter uncertainties.
Zarate Villazon, Angel M.Brown, IanBalchanos, MichaelMavris, Dimitri
This study develops a personalized driver model for expressway merging, embedding individual driving characteristics into automated longitudinal and lateral control via Long Short-Term Memory (LSTM) networks. Uniform assistance (Advanced Driver Assist System, ADAS) can feel uncomfortable when it does not match a driver’s style; we therefore target the merge maneuver—a safety-critical task requiring anticipation and timing—and test whether merging-related context improves model fidelity. Driving data were collected in a high-fidelity motion-base simulator across two merging scenarios (13 licensed drivers in total). Inputs comprised ego speed, Headway distance and relative speed to the lead vehicle, and geometric context variables (distance to the end of the acceleration lane and to the hard/soft nose); outputs were longitudinal and, in the cross-scenario study, lateral accelerations. Models were trained per driver and evaluated by root mean square error (RMSE). Including merging context reduced longitudinal error in Experiment 1 (Gotemba IC) by about 30% on average relative to models without context, while errors remained below 0.5 m/s2. In Experiment 2 (Tokyo–Nagoya Expressway vs. Tokyo Metropolitan Expressway), longitudinal and lateral errors were low across both geometries; group-mean trends favored context but were non-significant, reflecting small sample size and inter-individual variability. Questionnaire-based evaluations in the simulator showed ratings close to real driving for discomfort, merge timing, and perceived safety; similarity and willingness to use were slightly higher in the urban expressway scenario, suggesting good user acceptance in constrained conditions. These findings indicate that incorporating merging context enables personalized control that better reflects individual driving behavior, while pointing to future work on generalization across geometries, speed ranges, and richer interaction semantics.
Shen, ShuncongHirose, Toshiya
Accurately modeling and controlling vehicle exhaust emissions, particularly during highly transient events such as rapid acceleration, is crucial for meeting stringent environmental regulations and optimizing modern powertrain systems. While conventional data-driven modeling methods, such as Multilayer Perceptrons (MLPs) and Long Short-Term Memory (LSTM) networks, have improved upon earlier phenomenological or physics-based models, they often struggle to capture the complex nonlinear dynamics of emission formation. These monolithic architectures attempt to learn from all available data, which increases their sensitivity to dataset variability. They often require increasingly deep and complex architectures to improve performance, thereby limiting their practical utility. This paper introduces a novel approach that overcomes these limitations by modeling emission dynamics in a structured latent space. Using a rich dataset combining real-world driving data from a Portable Emission Measurement System (PEMS) with high-frequency hardware-in-the-loop test bench measurements, a Joint Embedding Predictive Architecture (JEPA) is leveraged. This framework learns to abstract away irrelevant information and encode only the key factors governing emission behavior into a compact, robust latent representation. The resulting model demonstrates superior data efficiency and predictive accuracy across diverse transient regimes, exhibiting stronger generalization than the high-performing LSTM baseline. Structured pruning and post-training quantization are applied to the JEPA framework to enhance the model’s suitability for real-world deployment. This combined strategy significantly reduces the model’s computational footprint, minimizing inference time and memory demand, with only a marginal impact on accuracy. This yields a highly accurate model well suited to on-board implementation of advanced control strategies, such as model predictive control or model-based reinforcement learning, in both conventional and hybrid electric powertrains. The results indicate a clear pathway toward more efficient and robust emission control systems for next-generation vehicles.
Sundaram, GaneshGehra, TobiasUlmen, JonasHeubaum, MirjanGörges, DanielGünthner, Michael
Items per page:
1 – 50 of 1510