Vehicle Subsystems Research Articles

Data-Driven Machine Learning-Informed Framework for Model Predictive Control in Vehicles

A machine learning framework is developed to interpret vehicle subsystem status from sensor data, providing actionable insights for adaptive control systems. Using the vehicle’s suspension as a case study, inertial data are collected from driving maneuvers, including braking and cornering, to seed a prototype XGBoost classifier. The classifier then pseudo-labels a larger exemplar dataset acquired from street and racetrack sessions, which is used to train an inference model capable of robust generalization across both regular and performance driving. An overlapping sliding-window grading approach with reverse exponential weighting smooths transient fluctuations while preserving responsiveness. The resulting real-time semantic mode predictions accurately describe the vehicle’s current dynamics and can inform a model predictive control system that can adjust suspension parameters and update internal constraints for improved performance, ride comfort, and component longevity. The methodology extends to other components, such as braking systems, offering a scalable path toward fully self-optimizing vehicle control in both conventional and autonomous platforms.

The role of integration in the future of autonomous vehicles: A data integration perspective

Autonomous vehicles represent a transformative force in transportation, with middleware functioning as the critical integration layer enabling their operation. This technological backbone facilitates communication between vehicle subsystems, manages sensor data fusion, and coordinates interactions with external infrastructure. The integration challenges faced in autonomous vehicle development highlight the essential role of middleware architecture in creating reliable, responsive systems capable of operating in complex environments. Intelligence-enhanced middleware leverages artificial intelligence and machine learning to improve decision-making capabilities, enabling vehicles to navigate unpredictable scenarios and learn from accumulated experiences. Middleware orchestration creates cohesive transportation networks by coordinating interactions between vehicles, infrastructure, and cloud services, significantly enhancing traffic flow and efficiency. Cross-platform standardization addresses interoperability challenges while improving security posture across autonomous systems. Looking forward, emerging technologies including edge computing, 5G connectivity, blockchain, and quantum algorithms will dramatically enhance middleware capabilities. Hyper automation within middleware frameworks promises autonomous calibration, seamless updates, and self-healing functionality. Addressing scalability and security concerns remains paramount as autonomous fleets expand, requiring robust architecture to process massive data volumes while defending against sophisticated attacks. The integration capabilities provided by middleware will ultimately determine the success of autonomous transportation networks, transforming mobility ecosystems through intelligent coordination of increasingly complex autonomous systems.

Onboard Vehicle Diagnosis Fault Monitoring System Using IoT for Electric Vehicle

Abstract— The paper proposes a user-friendly cloud-based data acquisition and analytics system for vehicle diagnostic monitoring in real time. The vehicle's condition is assessed using the Onboard diagnostics (OBD) framework and the report is sent to the mobile of the driver via wifi on detection of unsafe and anomalous events in real time. Vehicle parameter values are instantaneously uploaded to the server. The smartphone app also visualizes data from the sensor and also generates warnings in real time. Keywords: Internet of Vehicles, On-board diagnostics (OBD), Vehicle self-diagnosing system, Reporting capability, Vehicle owner, Repair technician access, Vehicle subsystems, Diagnostic information, On-board vehicle computers, OBD II engine parameters.

Generative artificial intelligence in intelligent transportation systems: A systematic review of applications

Abstract Rapid urbanization is reshaping mobility demands, calling for advanced intelligence and management capabilities in urban transport systems. Generative Artificial Intelligence (AI) presents new opportunities to enhance the efficiency and responsiveness of Intelligent Transportation Systems (ITS). This paper reviews the existing literature in transportation and AI to investigate the core technologies of Artificial Intelligence Generated Content (AIGC)–including dialog and reasoning, prediction and decision making, and multimodal generation. Applications are summarized across the four primary ITS subsystems (road subsystem, vehicle subsystem, traveler subsystem and management subsystem). This paper finds that AIGC has become an important way to promote the progress and development of ITS by exploring the research progress of cutting-edge technologies such as data generation, assisted driving decision-making, and intelligent traffic prediction. Meanwhile, this paper explores the potential challenges that AIGC brings to human society from the perspectives of safety risks of fake content, human-machine relationships, social cognition and emotional trust, and related ethical issues, providing insights for the development of safer and more sustainable ITS in the future.

Advancing vehicle detection for autonomous driving: integrating computer vision and machine learning techniques for real-world deployment

Road-object detection and recognition are crucial for self-driving vehicles to achieve autonomy. Detecting and tracking other vehicles is a key task, but deep-learning methods, while effective, demand high computational power and expensive hardware. This paper proposes a lightweight vehicle detection technique (LWVDT) designed for low-cost CPUs without compromising robustness, speed, or accuracy. Suitable for advanced driving assistance systems (ADAS) and autonomous vehicle subsystems, LWVDT combines computer vision techniques like color spatial feature extraction and Histogram of Oriented Gradients (HOG) with machine learning methods such as support vector machines (SVM) to optimize performance. The algorithm processes raw RGB images to generate vehicle boundary boxes and tracks them across frames. Evaluated using real-road images, videos, and the KITTI database under various conditions, LWVDT achieves up to 87% accuracy, demonstrating its effectiveness in diverse environments.

Approaches in modeling electrical energy conversion systems in hybrid vehicles

Purpose. Selection of adequate software and development of a modeling methodology for economical multi-domain simulation of the power distribution and conversion system, taking into account the control system for modern vehicles, in particular, for a hybrid electric vehicle with a fuel cell (HEV). Methodology. The main research method is mathematical modeling; for the structural synthesis of the model of the power conversion system and comparative analysis of programs, heuristic decision-making methods based on the comparison of variant metrics were used. Findings. A method of decomposition of HEV from the point of view of the scope of application of existing programs for modeling its subsystems is proposed. Subsystems from blocks of such a structural scheme are suitable for research using single-domain modeling programs. The prospects of the computer-aided design in electronics (ECAD) programs for multi-domain HEV modeling are shown, since the central and main conversion unit is the electronic domain. Based on the selected software metrics, the choice of programs for modeling the power conversion system is justified, with the possibility of organizing model interfaces to ensure multi-domain modeling and correct export-import of models when transitioning between abstraction levels. The sequential use of selected computer-aided engineering (CAE) and ECAD programs is proposed, with the transfer of information about the model and simulation results. This is capable of providing both optimal synthesis of the Automatic Control System based on the Phase Margin criterion with the study of the stability zone according to the Solution map, and in-depth analysis of the energy performance of the power stage of the converters. To test the method, a parallel topology of the power system with a block of supercapacitors, a boost-type converter in voltage control mode and a promising Four-Switch Bidirectional Buck-Boost converter in current control mode were selected. To increase the stability of the system, it is proposed to use a Type3 controller, which combines the capabilities of a compensator and a modulator. Originality. A new approach to modeling the HEV energy subsystem is proposed, which takes into account the multi-domain nature of the system and requires its consideration, first, as an Automatic Control System at the macro level in the CAE program SmartCtrl, with a preliminary expansion of its library by synthesizing Transfer Functions in the ECAD program PSIM, and a subsequent return to the micro level for analyzing energy characteristics and parametric optimization of converters together with control systems at the level of electrical circuits in PSIM. Based on the analysis of the capabilities of the programs for modeling the components of the HEV aggregate system, a variant of the structural diagram of the model of the energy subsystem is proposed, taking into account the possibilities of adequate application of "single-domain" programs and the prospects for their use for multi-domain modeling of HEV are shown. A specific set of program metrics is determined for a reasonable choice of software when studying such systems. Practical value. The presented method of sequential modeling of the energy system in the complex of automated engineering and automated design programs SmartCtrl+PSIM from Altair Group with mutual data exchange provides a comprehensive analysis and optimization of the characteristics of this subsystem of modern vehicles.

Comparison of Simulation- and Regression-Based Approaches to Estimating Electric Car Power Consumption

The main objective of this paper is to present a methodology for the reliable estimation of the energy consumption of electric vehicles, focusing on the main electrical subsystems of passenger cars. This paper presents a comparative analysis of the available regression models and the results of our simulation experiments. While numerous regression models have been documented in the literature, their accuracy is not always satisfactory. Consequently, there is a need to develop a sufficiently accurate and comprehensive generalized simulation framework, which is presented in the paper. Currently, most of the major vehicle manufacturers have developed pure electric vehicle platforms and are using them in the production of many models available on the market. The estimation of consumption data for these vehicles is still based on traditional techniques, namely, prediction from historical operation data. To overcome this problem, in this article, we have constructed a multi-element, model-based simulation for the purpose of implementing an energy consumption monitoring system. In order to create a simulation that reflects real-life vehicle behavior, the input data are based on empirical measurements, while the simulation model is based on actual electric vehicle parameters. In the main simulation model, it is possible to simulate the energy consumption of the vehicle’s drive system and to extract the requisite input data for the simulation of the other vehicle subsystems. In regard to the simulation, the subsystems that have been incorporated are the electric vehicle steering system, the vehicle lighting system and the HVAC system. After running the simulation, the total system consumption for a given trip segment is obtained by running each vehicle subsystem simulation. The findings were validated with real data and compared with two relevant regression models. Our preliminary expectation is that, given the level of detail of our simulation, the developed model can be considered validated if the error of the estimate remains below 4% and if the simulation model in question yields superior results in comparison to other regression models.

Gamma‐ray and neutron attenuation of carbon fiber/epoxy composites with carbon nanotubes and boron nitride nanoparticles for passive shielding applications in space

Abstract Composite materials have made far‐reaching changes in the space industry since they have been adopted into the structural and thermal control subsystems of space vehicles because of their several multi‐functions, including being lightweight as well as having advanced mechanical and thermal properties. The use of composites as space radiation shielding materials is also one of the most crucial applications because space radiation is a major impediment for current and future deep‐space missions. Investigation of carbon fiber composites with a diverse array of element and nanoparticle reinforcements has revealed their potential as an alternative to conventional radiation shielding materials in space. This study focused on the alleviation of gamma‐ray and neutron radiation by carbon fiber/epoxy composites incorporated with various weight ratios of carbon nanotube (CNT) and boron nitride (BN) nanoparticles. A narrow beam geometry setup was used for gamma radiation tests with a Cs‐137 gamma‐ray source, while neutron radiation experiments were conducted in a neutron howitzer with a 239Pu‐Be neutron source. Six groups of specimens, namely, pure carbon fiber/epoxy, 0.5 wt% CNT, 0.5 wt% BN, 0.5 wt% CNT + 0.5 wt% BN, 1 wt% CNT + 1 wt% BN, and 2 wt% BN, were examined against these two types of radiation. Results have indicated that the 2 wt% BN specimen showed the best attenuation properties against both gamma‐ray and neutron radiation among all tested specimens; furthermore, it was almost three times more effective against neutron radiation than against gamma‐ray radiation.Highlights Varying weight ratios of CNT and BN nanoparticles used for radiation shielding. A Cs‐137 gamma‐ray source used in narrow beam geometry. Neutron radiation studies were conducted in a 239Pu‐Be neutron howitzer. The 2 wt% BN sample showed the best attenuation against gamma‐ray and neutron radiation. It resulted in an HVL of 6.86 cm for gamma‐ray radiation and 2.13 cm for neutron radiation.

Evaluation of Technological Readiness in Mixed Maturity Sub-systems of Large Uncrewed Underwater Vehicles

Evaluation of Technological Readiness in Mixed Maturity Sub-systems of Large Uncrewed Underwater Vehicles

A Design Method for Road Vehicles with Autonomous Driving Control

The past three decades have witnessed extensive studies on motion-planning and tracking-control for autonomous vehicles (AVs). There is, however, a lack of studies on effective design methods for AVs, which consist of the subsystems of the mechanical vehicle, tracking-control, motion-planning, etc. To tackle this problem, this paper proposes a design approach for AVs. The proposed method features a design framework with two layers: at the upper layer, a particle swarm optimization (PSO) algorithm serves as a solver to a multi-objective optimization problem for desired AV trajectory-tracking performance; at the lower layer, a coupled dynamic analysis is conducted among the three subsystems, i.e., a nonlinear model for the mechanical vehicle, a motion-planning module, and a controller based on nonlinear model predictive control (NLMPC) for direction control. The simulation results demonstrate that the proposed method can effectively determine the desired design variables for the NLMPC controller and the mechanical vehicle to achieve optimal trajectory-tracking performance. The research findings from this work provide guidelines for designing AVs.

Stochastic optimization of levitation control system for maglev vehicles subjected to random guideway irregularity

Stochastic optimization of levitation control system for maglev vehicles subjected to random guideway irregularity

Extended Modified Bridge System (EMBS) method for decoupling seismic vehicle‐bridge interaction

Abstract Seismic vehicle‐bridge interaction (SVBI) is the study of vehicle‐bridge interaction (VBI) in the presence of earthquake excitation. SVBI is an interdisciplinary problem of increasing importance to the design and safety of railways. This study deploys a consistent methodology to decouple the vehicle‐bridge system and solve independently the bridge and vehicle subsystems, bypassing multiple challenges the seismic response analysis of a coupled vehicle‐bridge system entails. The proposed approach builds upon the previously established Extended Modified Bridge System (EMBS) method for decoupling vehicle‐bridge systems (in the absence of earthquake excitation). Its premise is to first characterize and then assess the relative importance of the VBI effect on the bridge and vehicle responses and replicate it by modifying the pertinent uncoupled equations of motion (EOMs). The formulation deployed accommodates multi‐degree of freedom models for both the vehicle and bridge and can thus tackle complex systems. The analysis examines the ability of the proposed decoupling approach to predict the response of a realistic system vehicle‐bridge system under a suit of historical earthquake records. The decoupled results are in excellent agreement with the coupled solutions for all earthquake records and scenarios (i.e., earthquake excitation solely in the transverse direction of the bridge, as well as in both the transverse and vertical directions simultaneously).

A Review of Modular Electrical Sub-Systems of Electric Vehicles

Climate change risks have triggered the international community to find efficient solutions to reduce greenhouse gas (GHG) emissions mainly produced by the energy, industrial, and transportation sectors. The problem can be significantly tackled by promoting electric vehicles (EVs) to be the dominant technology in the transportation sector. Accordingly, there is a pressing need to increase the scale of EV penetration, which requires simplifying the manufacturing process, increasing the training level of maintenance personnel, securing the necessary supply chains, and, importantly, developing the charging infrastructure. A new modular trend in EV manufacturing is being explored and tested by several large automotive companies, mainly in the USA, the European Union, and China. This modular manufacturing platform paves the way for standardised manufacturing and assembly of EVs when standard scalable units are used to build EVs at different power scales, ranging from small light-duty vehicles to large electric buses and trucks. In this context, modularising EV electric systems needs to be considered to prepare for the next EV generation. This paper reviews the main modular topologies presented in the literature in the context of EV systems. This paper summarises the most promising topologies in terms of modularised battery connections, propulsion systems focusing on inverters and rectifiers, modular cascaded EV machines, and modular charging systems.

A Novel Tire and Road Testing Bench for Modern Automotive Needs

The automotive industry is currently transforming, primarily due to the rise of electric and hybrid vehicle technologies and the need to reduce vehicle mass and energy losses to decrease consumption, pollution, and raw material usage. Additionally, road surface manufacturers emphasize improving pavement durability and reducing rolling noise. This necessitates precise load condition definitions and drives the need for reliable wheel testing benches. Many current benches use abrasive-coated rollers or synthetic tapes, but devices capable of testing on actual road surfaces are rare. In this work, a novel device for testing tire-pavement interaction is proposed. The system features a cart moving along a closed-track platform, ensuring test repeatability and enabling structural durability tests on uneven surfaces with installed obstacles. The cart is equipped with a cantilever arm capable of supporting either a testing wheel with customizable dimensions and kinematic parameters or a tire integrated with a complete suspension system, moving along a customizable pavement surface. The system includes actuators and sensors for applying vertical loads and adjusting the alignment of the testing wheel (slip angle, camber angle, etc.), allowing the characterization of tire behavior such as wear, fatigue, rolling noise, and rolling resistance. Multibody simulations were performed to evaluate the bench’s feasibility in terms of kinematics, power requirements, and structural loads. Results confirmed how this novel test bench represents a promising advancement in tire testing capabilities, enabling comprehensive studies on tire performance, noise reduction, and the structural dynamics of vehicle subsystems.

Intelligent identification of differential subgrade settlement of ballastless track system based on vehicle dynamic responses and 1D-CNN approach

Intelligent identification of differential subgrade settlement of ballastless track system based on vehicle dynamic responses and 1D-CNN approach

Lane detection networks based on deep neural networks and temporal information

Lane detection networks based on deep neural networks and temporal information

Research on dynamic characteristics of railway side-cracked slab for train-track coupled system

Research on dynamic characteristics of railway side-cracked slab for train-track coupled system

Modelling of SOLO’s Car Suspension System

The use of a virtual analysis approach to develop and modify vehicle sub-system is becoming popular nowadays as it is less time consuming, reduces the workmanship and overall testing cost compared to the experimental approach. In this paper, an actual virtual suspension system based on UiTM’s Perodua Eco Challenge (PEC) competition fullbody vehicle named SOLO was modelled using multi-body dynamic software, MSC/ADAMS Car. The virtual suspension system model was developed starting from identifying the components’ hard points, parameter setting, and joint type between the suspension components. The complete model was simulated using a static vertical parallel movement test with 30 mm as the selected bump travel movement. Following that, the values of kinematic and compliance of toe, camber and caster change were obtained. It was found that the front toe change was negative when subjected to wheel bound at 30mm (-0.3<sup>o</sup>), while the trend is opposite with the rear toe change (0.2<sup>o</sup>). Camber and caster change shows similar trends for both front and rear suspension system. Further analysis was then done to study the dynamic performance and suspension improvement after the virtual suspension system is verified.

A novel 3D train–bridge interaction model for monorail system considering nonlinear wheel-track slipping behavior

Variable speed operation of the train cause easily the wheel-track slipping phenomenon, inducing strong nonlinear dynamic behavior of the suspended monorail train and bridge system (SMTBS), especially under an insufficient wheel-track friction coefficient. To investigate the coupled vibration features of the SMTBS under variable speed conditions, a novel 3D train–bridge interaction model for the monorail system considering nonlinear wheel-track slipping behavior is developed. Firstly, based on the D’Alembert principle, the vibration equations of the vehicle subsystem are derived by adequately considering the nonlinear interactive behavior among the vehicle components. Then, a high-efficiency modeling method for the large-scale bridge subsystem is proposed based on the component mode synthesis (CMS) method. The vehicle and bridge subsystems are coupled with a spatial wheel-track interaction model considering the nonlinear wheel-track sliding behavior. Furtherly, by a comprehensive comparison with the field test data, the effectiveness of the proposed method is verified, as well as the reasonable modal truncation frequencies of the bridge subsystem are determined. On this basis, the dynamics performances of the SMTBS are evaluated under different initial braking speeds and wheel-track interfacial adhesion conditions; besides, the nonlinear wheel-track slipping characteristics and their influences on the vehicle–bridge interaction are also revealed. The analysis results indicate that the proposed model is reliable for investigating the time-varying dynamic features of SMTBS under variable train speeds. Both the axle load transfer phenomenon and longitudinal slip of the driving tire would be easy to appear under the braking condition, which would significantly increase the longitudinal vehicle–bridge dynamic responses. To ensure a good vehicle–bridge dynamics performance, it is suggested that the wheel-track interfacial friction coefficient is larger than 0.35.

Hydrogen Fuel Cell Range Extender Powertrain Simulation Study for Urban Mobility Powered Two-Wheeler

This study aims to evaluate the viability of hydrogen fuel cell (FC) technology as a range extender in powered two-wheelers (PTWs), focusing on choosing efficient FC size and under a time-limited, constant power delivery FC control strategy. The analysis presented in this study sheds light on the feasibility of hydrogen FC technology as an alternative energy source for mobility applications. In this study, a 1D powertrain simulation model was created, which enables the efficient analysing of both fundamental and advanced behaviour of individual vehicle subsystems and control strategies, even at the early conceptual design phase. The simulation results show that hydrogen FCs are a promising technology for range extension in urban mobility.