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.

Hydraulic braking torque and motor braking torque are the main sources of braking torque of new energy vehicles. Hydraulic braking converts vehicle kinetic energy into heat dissipation, and motor braking converts vehicle kinetic energy into electric energy to achieve energy recovery. In the process of vehicle braking, when the wheels tend to lock, it is easy to cause vehicle instability, which seriously threatens the safety of driving. Therefore, how to coordinate the braking torque of the two braking systems to ensure the vehicle braking safety and energy recovery efficiency is still an urgent problem to be solved. In this paper, the electric vehicle equipped with electro-hydraulic compound braking system is taken as the research object, and the electro-hydraulic compound braking coordinated control strategy considering the general braking state and emergency braking state is proposed. Firstly, a 3-DOF vehicle longitudinal dynamic model is established according to the vehicle dynamic characteristics. Secondly, in the general braking state, the braking torque of the front and rear axles is optimally distributed with the energy recovery as the optimization objective. Then, in the emergency braking state, taking the vehicle braking safety as the optimization target, based on the sliding mode control method, by adjusting the braking torque of the front and rear axles to make the actual slip ratio follow the expected slip ratio, the optimal control of the vehicle slip ratio is carried out. Finally, the electro-hydraulic compound braking torque distribution is carried out on the braking torque of the rear axle. Simulation and real vehicle test results show that, compared with the conventional rule-based coordinated control strategy, the proposed strategy significantly reduces the fluctuation of vehicle slip ratio and improves the energy recovery efficiency by at least 7.7%, so the vehicle safety and energy recovery efficiency are significantly improved.

Advanced autonomous driving is a critical component in the intelligent development of new-generation electric vehicles. Research on reliable chassis control algorithms ensures the safety and stability of autonomous vehicles during operation. To enhance the control performance of autonomous vehicles and improve the accuracy of trajectory tracking, this paper proposes a data-driven feedforward compensation trajectory tracking control approach. By optimizing the design of the feedforward compensation loop, systematic errors and latency in the vehicle’s steering system are mitigated, thereby enhancing the precision and robustness of the control algorithm. Initially, the paper analyzes the control errors present when the vehicle responds to controller commands. Subsequently, the paper focuses on the steering angle errors in trajectory tracking, identifying and analyzing the most relevant factors. A time-delay neural network (TDNN) based on data-driven principles is designed to model and predict these errors. This network captures the temporal characteristics of steering angle errors, enabling accurate predictions. Finally, the feedforward controller compensates for prediction errors by integrating feedforward compensation with the Model Predictive Control (MPC) controller’s predictions. This approach enables high-precision trajectory tracking by delivering precise control inputs. Experimental results demonstrate that the data-driven feedforward compensation control algorithm reduced trajectory tracking error by approximately 19% in co-simulations using Matlab/Simulink and Carsim, and by 56% in real-vehicle tests, thereby validating the effectiveness of the proposed approach.

To effectively improve the performance of chassis control of distributed drive intelligent electric vehicles (EVs) under difference road conditions, especially in combing road information and chassis control for improving road handling and ride comfort, is a challenging task for the distributed drive intelligent EVs. Simultaneously, inaccurate chassis control and uncertainty with system input, are always existing, e.g., varying road input or control parameters. Due to the higher fatality rate caused by variable factors, how to precisely chose and enforce the reasonable chassis control strategy of distributed drive intelligent EVs become a hot topic in both academia and industry. To issue the above mentioned, an adaptive torque vector hierarchical controller based on road level and adhesion is proposed, which optimizes the comprehensive. First, combined with the characteristic of the unbalance dynamic force caused by the air gap between the stator and the rotor of the in-wheel motor, a nonlinear vehicle model based on motor unbalanced electromagnetic force is developed. Then, using the deep neural network, an algorithm for road level and adhesion recognition based on system response data is designed. Meanwhile, an adaptive torque vector controller based on road information is designed to improve the driving safety and handling stability of chassis. Finally, the proposed algorithm is validated on the full-car test rig platform, results show that the proposed algorithm can improve chassis performance under double lane-change test. The research achievements develop a reasonable algorithm to apply to the improving road handling and ride comfort performance for distributed drive intelligent EVs.

Trajectory planning is essential for ensuring the safe operation of autonomous vehicles. However, existing methods rarely consider the vehicle’s multi-coupled dynamics, including lateral-longitudinal motion coupling, tire force coupling, and lateral instability. This omission can result in infeasible trajectories, vehicle instability, or even accidents under extreme conditions. To address this challenge, this study presents a multi-coupled dynamics trajectory planning (MCTP) scheme. MCTP establishes a coupled kinematics model to accurately represent vehicle motion states and constructs a tire force representation model, which based solely on vehicle motion states, facilitating seamless integration into trajectory planning. By incorporating coupled tire force characteristics and lateral stability analysis, a set of coupled dynamic constraints is formulated to ensure trajectory feasibility and lateral stability. Additionally, a multi-objective function is designed to further optimize trajectory safety, dynamic feasibility, and lateral stability, with the optimal trajectory obtained through receding horizon optimization. Closed-loop validation on both hardware-in-the-loop and real-vehicle experimental platforms demonstrates that, MCTP generates trajectories with enhanced safety and feasibility. It also improves tracking stability margins and dynamics performance, highlighting its effectiveness in handling extreme conditions.

Path-tracking control occupies a critical role within autonomous driving systems, directly reflecting vehicle motion and impacting both safety and user experience. However, the ever-changing vehicle states, road conditions, and delay characteristics of control systems present new challenges to the path tracking of autonomous vehicles, thereby limiting further enhancements in performance. This article introduces a path-tracking controller, time-varying gain-scheduled path-tracking controller with delay compensation (TGDC), which utilizes a linear parameter-varying system and optimal control theory to account for time-varying vehicle states, road conditions, and steering control system delays. Subsequently, a polytopic-based path-tracking model is applied to design the control law, reducing the computational complexity of TGDC. To evaluate the effectiveness and real-time capability of TGDC, it was tested under a series of complex conditions using a hardware-in-the-loop platform. The results demonstrate that through the polytopic-based path-tracking model and delay compensation strategy in TGDC, it can effectively enhance path-tracking performance with minimal computational load, even under conditions of parameter variability and control delays.

To optimize vehicle chassis handling stability and ride safety, a layered joint control algorithm based on phase plane stability domain is proposed to promote chassis performance under complicated driving conditions. First, combining two degrees-of-freedom vehicle dynamics model considering tire nonlinearity with phase plane theory, a yaw rate and side slip angle phase plane stability domain boundary is drew in real time. Then based on the real-time stability domain and hierarchical control theory, an integrated control system with active front steering (AFS) and direct yaw moment control (DYC) is designed, and the stability of the controller is validated by Lyapunov theory. Finally, the lateral stability of the vehicle is validated by Simulink and CarSim simulations, real car data, and driving simulators under moose test and pylon course slalom test. The experimental results confirm that the algorithm can enhance the maneuverability and ride safety for intelligent vehicles.

Multi-axle vehicles offer strong load capacity and driving stability, while all-wheel steering (AWS) improves their maneuverability and Control stability. However, coordinating multiple steering axles while balancing flexibility and stability remains a challenge in path tracking control. This paper proposes a novel control framework that integrates AWS into the path tracking process of multi-axle vehicles. A nonlinear model predictive controller (NMPC) is developed to optimize tracking performance, incorporating kinematic and dynamic objective functions that explicitly regulate front and rear wheel steering angles. This integration enables coordination of axle angles based on path tracking demands. Additionally, an adaptive weighting mechanism is introduced, in which the adjustment coefficients vary according to the vehicle's stability domain boundary to dynamically tune the control strategy under different operating conditions. Simulation results demonstrate that the proposed method significantly enhances both flexibility and stability in various driving scenarios, validating its effectiveness for complex maneuvering tasks.

If disturbances are not properly handled, autonomous driving in commercial vehicles may result in significant tracking errors or even deviate from the intended trajectory. This article proposes a solution to these issues by introducing a compensatory lateral control technique for path tracking that employs model predictive control (MPC) as its underlying control strategy. Additionally, to enhance the robustness of the MPC, the article presents a control algorithm that combines MPC with active disturbance rejection control (ADRC) compensation. Also, this article introduces the radial basis function neural network (RBFNN) as a technique for optimizing the parameters of the extended state observer (ESO) within the framework of ADRC. The introduced control strategy is evaluated via a hardware-in-the-loop (HIL) experiment, where it is demonstrated that the approach can precisely track an upper reference locus while remaining resistant to external interference.

To effectively improve the performance of chassis control of a four in-wheel motor (IWM)-driven electric vehicles (EVs), especially in combing nonlinear observer and chassis control for improving road handling and ride comfort, is a challenging task for the IWM-driven EVs. Simultaneously, inaccurate state-based control and uncertainty with system input, are always existing, e.g., variable control boundary, varying road input or control parameters. Due to the higher fatality rate caused by variable factors, how to precisely chose and enforce the reasonable chassis prescribed performance control strategy of IWM-driven EVs become a hot topic in both academia and industry. To issue the above mentioned, the paper proposes a novel observer-based prescribed performance control to improve IWM-driven EVs chassis performance under the double lane change steering. Firstly, a nonlinear nine degree-of-freedom of full-car model is developed to describe vehicle chassis dynamics, and the proposed model is used to illustrate the stable boundary of the EVs. Also, a road identification method established using system response data based on the theory of deep neural networks (DNNs) to acquire road information. Secondly, a nonlinear observer is employed to acquire the state of slip angle and yaw rate in real time. Based on the Lyapunov function and prescribed performance function (PPF), an observer-based prescribed performance control (PPC) strategy is proposed to constrain the controlled vehicle slip angle and yaw rate state within the prescribed performance boundaries. Finally, combing with a high-fidelity CarSim® software and a test rig platform, the proposed observer-based PPC algorithm is validated under the double lane change steering input. The research achievements develop a reasonable algorithm to apply to the improving road handling and ride comfort performance for a four IWM-driven EVs.

The accuracy of chassis control for intelligent electric vehicles (IEVs), especially in road-based IEVs control for improving road holding and ride comfort, is a challenging task for the intelligent transport system. Due to the high fatality rate caused by inaccurate road-based control algorithms, how to precisely and effectively choose a reasonable road-based control algorithm become a hot topic in both academia and industry. To address and improve the performance of road holding and ride comfort of IEVs by using a semi-active suspension system, an adaptive sliding mode control (ASMC) algorithm-based road information is proposed to realize the overall performance of the intelligent vehicle chassis system in the paper. Firstly, the models of road excitation and equivalent hybrid control of a quarter semi-active suspension system are established. Secondly, connecting with the minimum redundancy maximum relevance (MRMR) approach and probability neural network (PNN) theory, the method of road classification is developed based on the MRMR-PNN algorithm under various road excitation. Thirdly, using the sliding mode variable structure and neural network control theory, an ASMC algorithm based road information is developed. Then, a cuckoo search-based multi-objective optimization method is employed to obtain the optimization control parameters of the proposed ASMC algorithm. Finally, compared with the passive suspension system, the skyhook control algorithm, and the ASMC algorithm by simulation and test, the performance indexes of road holding and ride comfort are analyzed under ISO-C road excitation. Simulation and experimental results show that the better performance of the proposed ASMC algorithm can be obtained under different control weights of semi-active suspension system performance indexes, but also the root mean square values of sprung mass acceleration and rattle space compared with passive suspension system optimize no less than 6%. The research achievements develop a reasonable algorithm to apply to improving chassis performance for electric vehicles.

The active suspension system plays a crucial role in meeting the growing demand for enhanced vehicle ride comfort. This paper introduces a higher-order Sliding Mode Control algorithm (HOSM-AD) designed to effectively address actuator delay issues, thereby improving both ride comfort and vehicle robustness. Initially, An advanced active suspension model has been developed that incorporates actuator delay. The delay characteristics of the actuator and the state output of the suspension model are used to define the error surface, on which a higher-order sliding mode surface is constructed. This approach aims to enhance the robustness and responsiveness of the suspension system. Simulation results demonstrate the effectiveness of the algorithm in improving vehicle dynamics performance under various operating conditions, highlighting its superior smoothness and robustness.

Intelligent vehicles (IVs) play a pivotal role within the Intelligent Transportation System (ITS), significantly enhancing transportation efficiency and mitigating the risks of accidents. Nevertheless, the ever-evolving challenge environment, characterized by diverse scenarios with multiple dynamic vehicles and varying road conditions, present a new challenge for IVs' path planning and following algorithms in the adaption improvement under different traffic scenarios, thereby limiting IVs wider integration within ITS. This paper introduces an innovative adaptive integrated predictive control framework, which treats multi-vehicle dynamic interaction as a process of system model reconfiguration, enhancing the versatility of controller under complex scenarios. The dynamic multiple surrounding vehicles' states, the nonlinear tire model, and actuator characteristics are incorporated into the reconfigurable predictive model. Based on the arbitrary driving behavior of multiple vehicles and diverse road conditions, traffic risks are quantitatively assessed, which is applied to optimize the output of actuators within time-varying stability constraints. To assess its effectiveness, robustness, and real-time performance, the adaptive integrated controller is tested in a range of complex scenarios using a driver-in-the-loop platform. The results demonstrate that the adaptive integrated controller can effectively prevent crashes with multiple dynamic vehicles under different road conditions by employing coordinated control among actuators while ensuring driving stability.

The Adaptive Cruise Control (ACC) system, which reduces driver workload and improves driver safety, still faces the challenge of avoiding a collision with a vehicle that suddenly cuts in from arbitrary directions. To address the issue, a new hierarchical ACC structure with circumferential crash avoidance (RISE) is proposed. The upper planner employs Model Predictive Control (MPC) by considering the longitudinal and lateral dynamic models. Simultaneously, the lower controller incorporates a second-order sliding mode controller that takes into account the maximum longitudinal tire force on various road surfaces. To meet the multi-objective requirement, the proposed system employs a 2-level Time-to-Collision (TTC)-based switching mechanism, allowing it to seamlessly transition between car-following and circumferential crash avoidance modes. The driver-in-the-loop platform is created to validate the controller and evaluate the real-time performance of the proposed methods. By manipulating acceleration, deceleration, and steering, this innovative ACC structure is capable of successfully avoiding collisions with vehicles that change lanes from adjacent lanes.

Current Adaptive Cruise Control (ACC) systems are prone to risk of crash from surrounding unexpected cut-in vehicles. Hence, accurate risk evaluation for collisions and corresponding crash avoidance algorithms are highly desired. Therefore, in this work, we propose an accurate Time to Collision (TTC) calculation method using elliptical vehicle geometry, and evaluate the collision risks with surrounding vehicle, quantitatively. To avoid collision with multi-direction cut-in vehicle, a controller-switching mechanism based on TTC is first designed to switch back and forth between the performance-oriented controller and safety-oriented controller. Moreover, the proposed work is validated through simulations. The simulation results reveal that, for different scenarios (car-following, front-side and rear-side cut-in), proposed method can enhance the tracking performance while avoiding crash with surrounding vehicles from front-side and rear-side cut-in, effectively.

为有效解决复杂行驶工况下非线性悬架系统运动状态无法精确获取的难题,实现模型参数不确定以及时变路面激励工况下悬架状态精确估计的目标,开展了悬架系统状态估计研究.在路面激励模型和非线性悬架系统模型的基础上,结合交互式多模型算法与基于马尔可夫链的蒙特卡洛理论,设计了考虑模型参数不确定以及时变路面激励工况下多模型交互无迹卡尔曼滤波(IMMUKF)状态估计算法,且利用随机控制稳定判据验证了所设计的非线性观测器稳定性判定.对比分析了不同路面激励工况下悬架系统对于传统无迹卡尔曼滤波观测器与IMMUKF观测器的状态估计精度,并进行了台架试验验证.试验与仿真结果表明,IMMUKF观测器可获取更高的系统状态识别精度,不同路面激励仿真工况下状态估计误差最大均方根值不超过8％.

This paper presents a novel model-based observer algorithm to address issues associated with nonlinear suspension system state estimation using interacting multiple model unscented Kalman Filters (IMMUKF) under various road excitation. Due to the fact that practical working condition is complex for the suspension system, e.g. additional load. Meanwhile, the changed sprung mass parameter will induce model changed of suspension system, and it can lead to state transition between various models. To tackle the mentioned issue, the models of road profile and suspension system are first established to describe the nonlinear suspension dynamics. Then, considering the variation of sprung mass under various movement conditions, an unscented Kalman Filter (UKF) algorithm is proposed to identify the sprung mass. Based on the interacting multiple model (IMM) and Markov Chain Monte Carlo (MCMC) theory, a novel IMMUKF observer is developed to estimate the movement state of suspension system. The stability conditions for the proposed observer is calculated using the stochastic stability theory. Finally, simulations and validations are performed on a quarter vehicle suspension system under various ISO road excitations, to validate the UKF and IMMUKF algorithms for acquiring suspension system states, and results illustrate that the maximum root mean square error of state estimation for the proposed algorithm is less than 7.5 %.

The in-wheel motor (IWM)-driven electric vehicles (EVs) attract increasing attention due to their advantages in dimensions and controllability. The majority of the current studies on IWM are carried out with the assumption of an ideal actuator, in which the coupling effects between the non-ideal IWM and vehicle are ignored. This paper uses the braking process as an example to investigate the longitudinal–vertical dynamics of IWM-driven EVs while considering the mechanical–electrical coupling effect. First, a nonlinear switched reluctance motor model is developed, and the unbalanced electric magnetic force (UEMF) induced by static and dynamic mixed eccentricity is analyzed. Then, the UEMF is decomposed into longitudinal and vertical directions and included in the longitudinal–vertical vehicle dynamics. The coupling dynamics are demonstrated under different vehicle braking scenarios; numerical simulations are carried out for various road grades, road friction, and vehicle velocities. A novel dynamics vibration absorbing system is adopted to improve the vehicle dynamics. Finally, the simulation results show that vehicle vertical dynamic performance is enhanced.