Aiming at the problems that the Rapid-exploration Random Tree (RRT) algorithm is easy to lead to node expansion redundancy and the generated path does not meet the vehicle rotation angle constraint, an improved secondary rotation angle constraint RRT algorithm is proposed. Based on the traditional RRT algorithm, the sampling space is first cut, and the target offset strategy is introduced to reduce the sampling time. Then, the vehicle expansion processing and the straight line method are used to detect the obstacle collision, and the first rotation angle constraint is introduced to obtain the coarse solution path. Then, the secondary angle constraint optimization processing is established for the rough solution path, and the vehicle optimization path is obtained and fitted, and the simulation verification is carried out. The results show that compared with the biased RRT algorithm with the goal-oriented strategy, the maximum curvature of the path is reduced by 34.33 %, the average curvature is reduced by 47.36 %, the number of extended nodes is reduced by 47.62 %, the path distance is reduced by 7.76 %, and the planning time is reduced by 14.98 %.

To maximize energy absorption of EV body structure in frontal collision, vehicle front-end structure is designed by analyzing the characteristics of the optimal collision waveform configuration, and combining theoretical and empirical formulas. Meanwhile, deformation modes such as bending are introduced, and a method to improve vehicle structure frontal collision property based on the theoretical optimal waveform configuration is proposed. The results show that the collision waveform of the improved vehicle body structure is basically consistent with the optimal waveform configuration, and there is a significant decrease in passenger acceleration, which improves the overall safety of the vehicle.

Combining spare wheel identification and wheel speed compensation, limited slip feedforward control based on equal utilizable friction coefficient on the front and the rear axle and limited slip feedback control based on axle speed difference were designed. And an on-demand 4WD vehicle dynamics simulation platform was built to verify the effectiveness of small spare tire identification, wheel speed compensation, and limited slip control. The strategy can achieve the central differential and differential slip limiting functions of on-demand 4WD vehicle, improve vehicle’s power performance and driving stability, avoid the error trigger of limited slip control caused by the difference in rolling radius, and solve the abnormal wear and ablation of the multiple-plate clutch caused by the small rolling radius of the spare tire.

In order to address the issue of long cycle, high cost and low safety of traditional vehicle chassis tuning test, this paper proposes a test method of virtual chassis tuning using dynamic driving simulator. By comparing the subjective and objective test results of vehicle dynamics between virtual chassis tuning and real vehicle chassis tuning, it is shown that the virtual chassis tuning of dynamic driving simulator can achieve the same effect compared with the traditional real chassis tuning.

In order to reduce the energy consumption of heat pump air conditioning systems, take the heat pump air conditioning system matching Active Grille Shutter (AGS) thermal management system of electric vehicles as the research object, a heat pump air conditioning thermal management system and energy consumption control strategy are developed based on various parameters including vehicle speed and intake grille opening area. The energy consumption values of the system are simulated and calculated for different AGS openings in high and low temperature environments. Using the calibration method in the actual vehicle cabin environment, this paper analyzes the variations in measured values of air conditioning systems and wind resistance energy consumption for AGS openings in low temperatures of -7 ℃ and high temperatures of 35 ℃. The experimental results show that in high and low temperature environments, the larger the AGS opening, the higher the wind resistance energy consumption value, whereas the lower the comprehensive energy consumption value of air conditioning and wind resistance. When the AGS opening increases by the same value, the impact on energy consumption at high temperatures is greater than that at low temperatures.

The results of whiplash test show that whiplash injury is very serious and whiplash score is low. To solve this problem, the seat finite element model was established by HyperMesh software, and the whipping simulation analysis was carried out. The factors affecting substantially whipping injury were analyzed as follows: angle adjuster stiffness coefficient, head pillow rod diameter, thickness of backrest left support plate, thickness of backrest right support plate, thickness of backrest rear support plate, thickness of seat cushion left support plate and thickness of seat cushion right support plate. The above seven influencing factors were taken as design variables, sample points were collected by Hammersley experimental design, and approximate model fitting was carried out by moving least square method. The global response surface method was used to perform multi-objective optimization of the approximate model. The verification results show that the accuracy of the optimized model meets the requirements, and the whip score was increased, which greatly enhanced the seat’s ability to prevent whip injury.

This study provided a review of classification methods and quantitative evaluation of driving behavior, which firstly expounded the meaning and representation methods of driving behavior, and divided the driving behavior classification methods into three categories: statistics based classification method, machine learning based classification method, and the hybrid (combination, integration) classification method. Different driving behavior classification methods were summarized from the aspects of representative algorithms, advantages and limitations. Secondly, the quantitative evaluation research of driving behavior was systematically described from multiple dimensions. Finally, the application status and prospect of driving behavior classification and quantitative evaluation results in many fields were introduced.

A driver fatigue detection method based on parallel short-term facial features is proposed to achieve faster and more accurate fatigue warning. The method utilizes the YOLOv7-MCW object detection network, which incorporates the MicroNet module, CA attention mechanism, and Wise-IoU loss function, to extract short-term facial features of the driver’s face. The parallel Informer temporal prediction network is then used to integrate the spatiotemporal information obtained from the YOLOv7-MCW object detection network, enabling the detection and warning of driver fatigue. The results demonstrate that the YOLOv7-MCW-Informer model achieves accuracy rates of 97.50% and 94.48% on the publicly available datasets UTA-RLDD and NTHU-DDD, respectively, with a single-frame detection time reduced to 28 ms, proving the excellent real-time fatigue detection performance of the model.

To balance braking safety and braking energy recovery of distributed drive electric vehicles, this article explored the vehicle braking torque distribution control strategy based on NSGA-II multi-objective optimization algorithm. An optimization module based on fuzzy control was established, and the optimal torque distribution coefficient was determined from the Pareto frontier optimization according to vehicle speed and demand braking torque. With an electric passenger vehicle as the research object, a brake torque distribution control strategy model was built based on Matlab/Simulink and VPAT and simulated. A hardware-in-loop simulation platform was built, and real-time performance and validity of this algorithm were verified. As was shown in the result, the brake torque distribution coefficient of the control strategy based on NSGA-II was closer to the distribution coefficient of ideal I curve, and the operation points of the motor braking efficiency zones were increased by 9.51 percentage point, and the energy recovery rate of vehicle regenerative braking was increased by 4.71 percentage point.

The current available capacity of the battery is difficult to obtain, and the health status of the battery is difficult to estimate accurately during the operation of the vehicle. Therefore, this paper proposed to use the parking and charging segment data of the vehicle to correct the battery capacity obtained by ampere-hour integration method through box diagram and Kalman filter algorithm. The support vector regression model was constructed for battery degradation prediction. The effective model input parameters were determined by Pearson correlation analysis. The model parameters were optimized by genetic algorithm. Results show that the fitting accuracy of the optimized model reaches 88%, which is 12% higher than that before optimization, can accurately predict the SOH of vehicle battery.