In the realm of vehicle dynamics, the sideslip angle is a critical parameter. For the challenges posed by the current modelbased methods, which heavily rely on the accuracy of dynamic models, and the poor robustness of datadriven methods in unfamiliar operating conditions, in this paper a sideslip angle estimation method based on a hybrid of physics and datadriven approaches (DeepPhy) is proposed. The aim is to combine the strength of physical modeling and datadriven techniques to achieve reliable and accurate estimation of the sideslip angle. DeepPhy integrates prior values of the sideslip angle obtained from the lateral force model of the rear axle tires with a deep neural network, enabling the learning of nonlinear mapping relationship not captured by the physical model, thereby enhancing the model's reliability in unfamiliar conditions. The simulation results indicate that under continuous DLC conditions, the RMSE of the estimation results from DeepPhy is reduced by 93% compared to the physical model method and by 63% compared to the datadriven method, exhibiting robustness in scenarios with limited data. Realworld validation further confirms DeepPhy's exceptional generalization capabilities, as the models trained through simulation can be transferred to realworld conditions while maintaining highprecision estimation results.

The damper is a core component of the suspension system, exerting significant influence on both vehicle handling and ride comfort. Traditional damper exhibits unstable response and distorted characteristics under hightemperature and highspeed conditions. Moreover, the development process heavily relies on extensive experimentation, leading to prolonged design cycles and increased cost. For this, firstly, the scheme of the continuous damping control (CDC) damper with builtin combination valve is proposedd, and the response characteristics of the valve system are quantified based on finite element method. Secondly, the nonlinear features of the damper external characteristics are analyzed, with which the hybrid model that combines piecewise models and compensation models is established to effectively capture the nonlinear gas hysteresis characteristics. Finally, all damper model parameters are identified based on measured data under different currentfrequency coupling excitation effect. Subsequently, the parameters frequencyvarying characteristics and the model accuracy are verified. The results indicate that the accuracy of the proposed hybrid model is improved by 55.91% on average compared with the piecewise model, with the error less than 10% compared with the measured data. The proposed innovative damper structure along with its characteristic modeling method can significantly enhance damper performance while simultaneously reduce development cost.

For the limitation of traditional type1 Smith fuzzy control in terms of inadequate time delay compensation and insufficient robustness under varying parameter driving conditions, an interval type2 Smith fuzzy time delay compensation control method is introduced for magnetorheological (MR) semiactive suspension systems. This approach incorporates the vehicle's vertical acceleration, suspension deflection, and tire dynamic displacement as the state input of the control system, enabling a comprehensive capture and response to dynamic vehicle changes. By introducing in upper and lower membership functions, the method defines clear membership intervals for fuzzy variables, which are then leveraged to calculate activation intervals under various fuzzy rules, significantly enhancing the system's antiinterference capability. Additionally, the Centerofsets algorithm is innovatively introduced into the fuzzy reduction process, avoiding redundant normalization calculation during the type reduction of type2 fuzzy sets, thereby improving the system's execution speed and realtime performance. Simulation results demonstrate that the proposed interval type2 Smith fuzzy delay compensation control strategy achieves improvement in both control effectiveness and robustness for MR semiactive suspension systems, effectively tackling complex and varied driving environment.

In the application of vehicleroad cooperative technology for dynamic display of the roadside twin maps, due to the delay problem of the communication between networked devices and the existence of the roadside perception error, the fusion perception accuracy of the roadside edge computing unit will be seriously affected, which will lead to the jitter and delay of the vehicle display track in the twin map. Hence, in this paper a vehicleroad cooperative sensing and localization method that fuses high definition map under high communication delay is proposed. The method first analyzes and models the communication delay between the vehicle end of the connected vehicle and the roadside edge processing unit in the vehicleroad cooperative system, divides the delay model into sensor synchronization delay and communication transmission delay, and proposes a synchronization optimization method for the delay. After the synchronization optimization, a collaborative multidimensional particle filter algorithm for swarm vehicles is proposed, where the states of the particles represent the pose of different connected vehicles and nonconnected vehicles in the swarm vehicles. In the proposed multidimensional particle filter algorithm, the state of the particles is firstly updated using the observation of the state of the particles by utilizing the roadside RSU observation data and the curvature information of the lanes in the highdefinition map. Then the selflocalization information of the received delayed synchronized smart connected cars combined with the left and right lane line lateral constraint information and the lane line equations of the lanes in the high definition map are used to update the observation of the state portion of the particle that represents the smart connected cars. The experimental results show that the perceptual and localization accuracy of the edge server is improved by 59.4% in the low delay scenario with less communication interference, and its accuracy is improved by 38.6% in the high delay scenario with severe communication interference. Therefore, the proposed vehicleroad cooperative sensing method incorporating high definition map under high communication delay can effectively deal with the communication delay problem and improve the multivehicle perception accuracy of the edge computing unit, thus improving the accuracy, stability and continuity of the twin map dynamic data.

Establishing an accurate air spring model is key and crucial for analyzing the vibration characteristics of air suspension electric buses. For the variation in the characteristics of air springs under different load, a comprehensive model of the air spring with dynamically adjustable parameters is proposed, considering the effect of rubber airbag force and changes in payload, taking a membranetype air spring as the research object. Key parameters of the rubber airbag are identified through mechanical experiments, and the accuracy and effectiveness of the proposed model are verified. Based on the comprehensive air spring model, a 14seat, 21degreeoffreedom electric bus dynamics model is established. The model's validity is verified through simulation comparison with a CarSim model with identical parameters. Subsequently, the influence of air spring nonlinear characteristics, vehicle speed, road roughness, and passenger distribution on the dynamic performance of the electric bus system is analyzed. The study shows that the proposed comprehensive air spring model can dynamically adjust its parameters in response to variation in load and road excitation. The hysteretic mechanical characteristics of the air spring cannot be ignored. Compared with linear models, thermodynamic models without considering hysteresis, and equivalent air spring model, the comprehensive air spring model significantly reduces suspension deflection, with reduction of 22.95%, 42.13%, and 18.20%, respectively. Increase of vehicle speed, lower road quality, and uneven passenger distribution negatively affect the ride comfort of the electric bus, with discomfort increasing for passengers seated farther from the bus's center of gravity.

Injection overmolding after compression for thermoplastic composites balances the low cost and high performance. It can quickly and stably achieve integration of continuous/discontinuous fiberreinforced composites, meeting the requirements of the automotive industry. This paper reviews the key points of equipment selection, process control and molding simulation, introduces the types of domestic materials, summarizes the optimization design methods for anisotropic bimaterial structures, generalizes the evaluation methods for interface and overall performance, and puts forward some critical scientific and technological issues in the integrated design of "material process structure performance".

Distributed electrically-driven heavy-duty vehicles achieve compound steering through the differential between the steering assist motor and the wheelend drive motor. By means of coordinated control of multiple motors, various active safety control functions are realized and the driver's operational burden is reduced. For the driving safety issues brought about by the failure of the drive motor and the steering assist motor, in this paper a faulttolerant control strategy encompassing mode-switching and faulttolerant torque distribution is proposed. The proposed modeswitching strategy, based on the vehicle pose information, introduces in the yaw rate residual function as the switching condition for the faulttolerant mode. The proposed faulttolerant torque distribution strategy takes into account of the output redundancy and the vehicle's stability to solve for the target output torque of the drive motor and the steering assist motor. Finally, a hardware-in-the-loop simulation platform is established to verify the effectiveness and real-time performance of the control strategy.

There are many investigated parameters in the powertrain mounting system (PMS) of electric vehicles, and it involves multiperformance design. For the problem that the traditional singleoutput sensitivity analysis is difficult to accurately evaluate the influence of system parameters on the system comprehensive performance, the multioutput response sensitivity analysis of the PMS of electric vehicle is carried out by considering the uncertainty of system parameters. Firstly, a 13degreeoffreedom analysis model of PMS is established, and the uncertain parameters of system are described by the random variables. Then, based on the summation of covariance decomposition, the first order index and the global sensitivity index of the multioutput response of system are derived. Next, a method of calculating the sensitivity indexes of multioutput response is proposed based on Monte Carlo analysis. Finally, the effectiveness of the proposed method is verified by the numerical example of the PMS of an electric vehicle. The analysis results show that the single output sensitivity analysis may not be able to accurately evaluate the comprehensive influence of parameters on the system response, and it may produce contradictory results. The proposed multioutput sensitivity analysis method can effectively evaluate the comprehensive influence of system parameters on the system response, and it can obtain more accurate sensitivity ranking for system parameters.

Multiclass traffic participant detection in dense traffic scenarios remains a challenging visual task, which is crucial for traffic management and safety. To address this, a deep neural networkbased detection algorithm, DSODet, is proposed to handle the challenges of partial occlusion and smallscale targets in dense traffic environment. Firstly, a lightweight CSPDarkNet network is used to extract features from traffic images. Then, a multiscale feature fusion upsampling module is designed to enhance the representation capability for hardtodetect targets. Next, a highresolution detection branch is incorporated to improve detection accuracy for smallscale targets. Finally, a histogram feature distillation training method is proposed, which effectively guides the student model's training by minimizing the intersection ratio of feature histograms between the teacher and student models at corresponding layers, thus enabling parameter optimization and model compression. The experimental results show that DSODet achieves an average detection accuracy of 66.9% for traffic participants and 13.0% for small targets with partial occlusion, outperforming current stateoftheart algorithms. The model contains only 2.9 M parameters, demonstrating its friendliness for edge device. The related code will be shared at https://github.com/XMUTVsionLab.

To improve the accuracy and stability of path tracking for light commercial vehicles under complex curvature conditions, in this paper a PredictivePure Pursuit (PPP) control method is proposed. Firstly, a PPP controller is designed based on the vehicle's discrete kinematic model, and a PID compensator is developed based on heading error to enhance tracking accuracy and stability. Secondly, to address the challenge of maintaining both accuracy and stability under complex curvature conditions with a fixed prediction horizon algorithm, a variable prediction horizon optimization algorithm is proposed. A cost function based on the lateral and curvature errors within the prediction horizon is established, and Bayesian optimization is used to determine the optimal prediction horizon, resolving the conflict between accuracy and stability. Finally, TruckSim/Simulink cosimulation and real vehicle tests are conducted. In the real vehicle tests, the root mean square values of the lateral error, heading error, and steering wheel angle for the Bayesianoptimized PPP controller is 0.113 m, 0.045 rad, and 153.2°, respectively, all of which are superior to the corresponding metrics of the PPP controller based on fuzzy control and the MPC controller, indicating that the proposed controller maintains good precision and stability under complex curvature conditions.