For the complex thin-walled structure design of the integrated front engine compartment of electric vehicles，a structure and performance collaborative design method based on topology optimization is proposed in this paper. The optimal load path under multiple load conditions is determined through topology optimization and feasibility design of the front engine compartment integrated die-casting component process is conducted. Material testing is conducted on the die-cast materials，and failure surfaces are developed based on stress triaxiality and Lode angle coefficient stress states. A simplified frontal collision model is constructed to assess the stiffness compatibility between the extruded longitudinal beams and the die-cast components within the integrated front compartment structure. The results show that the proposed design method can effectively obtain topological paths under multiple performance constraints，fully consider the feasibility of the front cabin structure process and structural performance matching，and reduce research and development cost.

False alarm and missed alarm of automotive radar are key factors affecting the safety and reliability of autonomous driving systems，thus requiring a large amount of labeled test data for targeted research. However，the occurrence probability of false alarm and missed alarm is low，and the unstable status of radar targets makes it difficult to label them. Therefore，in this paper，firstly efficient test schemes are designed to obtain key radar data based on the generation mechanism of radar false alarm and missed alarm. Then，by constructing a correlation function to quantify the correlation between radar targets and scene targets and using genetic algorithms to optimize this function，an automatic labeling method for radar targets is established. Finally，the effectiveness of the proposed method is verified through real data acquisition. The experimental results show that the proposed method can efficiently obtain crucial false alarm and missed alarm data. The labeling method in this paper can accurately identify radar targets corresponding to scene targets and distinguish between false alarm and real targets.

To solve the problem of large fluctuation of inlet and outlet temperature on vehicle proton exchange membrane fuel cell （PEMFC） under variable loading currents，a dynamic change particle swarm optimization （PSO）—proportional integral derivative （PID） algorithm is proposed. Firstly，the overall simulation model of the PEMFC engine system with rated power of 150 kW is built. Based on existing references，the accuracy of the output power and voltage of the model is validated； and according to the validated results，the supply of reactant gas is set following demand on currents，which reflects real working conditions of the PEMFC engine system. Based on the model built and the control strategy that the mass flow rate of cooling water following output power，PID，PSO-PID and dynamic change PSO-PID are used on the mass flow rate of cooling air from radiating fans to conduct research on the control effect of them on the inlet and outlet temperature and output power of FCs under variable loading currents. The results show that compared with PID，under PSO-PID and dynamic change PSO-PID，the transient overshoots decreasing amplitudes of inlet temperature of FCs are both 13.7%，those of outlet temperature both 36.0% and the output power reaching the stable condition faster. The time when dynamic change PSO-PID reaching the optimum values only accounts for 57.1% of that under PSO-PID，which can reduce more unnecessary computation and input the PID parameters into the stack temperature controller ahead of PSO-PID. The dynamic PSO-PID algorithm can be used on actual inlet and outlet temperature control of FCs more efficiently and faster，contributing to improving the stability of the temperature and the output power of vehicle PEMFC.

For the dynamic multi-objective requirements of yaw maneuverability and lateral stability under different driving states，an adaptive control strategy for vehicle yaw stability is proposed. Firstly，the vehicle dynamics model is established by piecewise linear fitting technology，and the dynamic stability region boundary related to road adhesion and longitudinal velocity is obtained in phase plane by integrated application of improved two-line method and fuzzy theory. Then，the stability risk during vehicle driving is quantitatively characterized and the dynamic multi-objective mapping function is introduced to adjust the built-in parameters of the stability control strategy designed based on the model predictive theory so as to match the dynamic multi-objective demand of vehicle lateral stability，yaw maneuverability and actuator energy consumption. Finally，the simulation test results prove that the designed control strategy can help the vehicle obtain safer and better stability control effect than the traditional method under various conditions.

For the problem that it is difficult for video vehicle detection models to extract rich target features in complex traffic monitoring scenarios，in this paper a new spatial-temporal feature fusion module SF-Module is established from the perspective of making full use of spatial-temporal feature information of video images. The multi-head self-attention mechanism in Transformer model is used to extract and fuse the temporal and spatial feature information of current and historical frames of video vehicle images to enrich the feature information of the target. On this basis，based on YOLOv8 network，the newly created spatio-temporal feature fusion module SF-Module is integrated in its neck network to mine spatio-temporal feature information of video image sequences. At the same time，the WIoU loss function is introduced as the prediction frame regression loss to reduce the harmful gradient generated by the low quality label frame，and the SFW-YOLOv8 video vehicle detection model is designed. Finally，the newly established SFW-YOLOv8 complex scene video vehicle detection model is tested on the UA-DETRAC dataset，and some images in the dataset are simulated to enhance the data on rainy and foggy days，so as to improve the generalization of the vehicle detection model. The experimental results show that the values of mAP50 and mAP50：5：95 of the SFW-YOLOv8 video vehicle detection model are 79.1% and 63.6%，which are 1.7% and 3.3% higher than that of the YOLOv8 model，respectively. The reasoning speed is 11 ms/ frame，which has excellent detection performance.

Lattice mechanical metamaterials are widely applied in various protective structures due to their excellent mechanical properties and crashworthiness. Traditional lattice structures are often composed of periodically arranged regular porous materials. Inspired by the microcrystalline structures of metals，in this paper random grain boundary structures are incorporated into the design of lattice materials，then polycrystal lattice material specimens using 3D printing technology are prepared. Furthermore，crashworthiness studies are conducted based on the finite element models validated by experiments. The results show that compared to single crystal lattice materials，polycrystal lattice materials significantly improve specific energy absorption （SEA） at the same lattice angle，especially with 143% increase at the lattice angle of 30°. The crashworthiness of polycrystal lattice materials is influenced by grain size，intragranular lattice angle，and grain randomness. When grain size decreases，the energy absorption process becomes smoother，but excessively small grains may exacerbate fluctuations in the energy absorption process due to boundary effect. Polycrystal lattice materials with a 45° lattice angle and random lattice angles of 30°/60° exhibit stable energy absorption processes，and those with higher randomness in grain orientations show an even smoother energy absorption process. The novel polycrystal lattice mechanical metamaterials proposed in this paper can effectively enhance the crashworthiness of traditional lattice materials and provide guidance for the design and optimization of new lightweight lattice metamaterials.

In order to adapt to the development of urban electric buses and the needs of national energy conservation and environmental protection policies，a lightweight method for vehicle body structure is proposed in this paper based on sensitivity analysis of the static strength and rollover safety performance of electric buses. Firstly，a finite element model of a certain electric bus is established，and the static strength and rollover safety analysis of the body structure is conducted through the finite element method. Secondly，sensitivity analysis of the static strength and rollover safety of the vehicle body under bending and twisting conditions is conducted on the finite element model. Based on the sensitivity analysis results，the component plate thickness that is beneficial for lightweighting and has little impact on the static strength and rollover safety of the vehicle body is selected as the design variable. The size optimization is carried out with the goal of minimizing the mass of the vehicle body skeleton，and the constraint that the maximum von Mises stress of each material unit does not exceed its material yield strength. The optimization results indicate that the static strength and rollover safety performance of the vehicle body structure meet regulatory requirements，and the weight of the vehicle body frame is reduced by 3.8%.

In order to overcome the influence of network latency on the cooperative perception accuracy and simultaneously improve the point cloud feature expression capability，a cooperative perception method based on point cloud spatio-temporal feature compensation network for intelligent connected vehicles is proposed. Firstly，the point-to-pillar feature extraction method is used to process the raw point cloud data，and the local neighborhood features of the laser points are then spliced with pillar feature maps. Secondly，the temporal latency compensation module based on the PredRNN algorithm is designed to predict the point cloud features of historical frames received from the surrounding connected vehicles，so as to achieve the synchronization of point cloud features from two vehicles. Thirdly，the spatial feature fusion compensation module is utilized to aggregate the inter-vehicle point cloud features，and multi-resolution features are fused through the bidirectional multi-scale feature pyramid network. The output includes vehicle target geometry size，heading angle and other information. Finally，the test results on the V2V4real dataset and the self-collected dataset demonstrate that the detection accuracy of the proposed method is superior to classical cooperative perception algorithms. Furthermore，it exhibits good adaptability to various latency cases and the inference process meets the real-time requirements.

In order to improve the traffic efficiency at the signalized intersections and the fuel economy of vehicles，a cooperative optimization method of traffic signals and speed of connected vehicles considering the human driver error is proposed in this paper. In the traffic layer，by transforming the traffic signal optimization problem into a sequencing problem to find the optimal sequence of vehicles passing through the intersections，the optimal control model for traffic signal optimization is constructed and a traffic signal optimization algorithm based on dynamic planning is proposed. In the vehicle layer，the optimal control model for vehicle speed optimization is constructed by considering the influence of driver error，and a speed optimization algorithm based on fast stochastic model predictive control for connected vehicles is proposed. The simulation and intelligent connected micro-vehicle test results show that the co-optimization strategy proposed in this paper can effectively alleviate the deceleration and stopping of vehicles at intersections due to driver errors，and further reduce the travel time，idling time and fuel consumption of vehicles.

Lamb waves，with the characteristics of long propagation distance，low cost，and good sensitivity to various damages，offer significant potential for studying the visually undetectable damage caused by low-velocity impact in carbon fiber reinforced polymer （CFRP） battery box. Although relative acoustic nonlinear parameters （RANP） have been shown to be effective in quantifying the degree of impact damage to composite materials，the mechanism by which damage affects them has not been explored. In this study，a combination of experimental and simulation method is used to study for the first time the effect of different impact damages on the propagation of Lamb waves in CFRP battery boxes. To this end，a geometric model of the battery box structure is first established. Then，impact tests are carried out on CFRP，and a simulation model for damage monitoring of CFRP battery boxes is built. Finally，the effect of delamination，matrix compression damage，and fiber tensile damage on the damage assessment parameters of CFRP battery boxes is studied. The results indicate that the established CFRP simulation model is reliable in calculation accuracy，with the RANP parameter being sensitive to the damage area of each mode，though not to the damage position in the thickness direction. Damage causes the Lamb wave to generate new frequency components during propagation. The calculation of the RANP parameter can thus analyze the degree of damage. When the degree of damage is low，the size of the RANP parameter depends more on the interlayer shedding damage，and once the damage exceeds a certain threshold，the size of the RANP parameter depends more on the intralayer damage such as the fiber damage of the CFRP. The research results have important guiding value for the structural-functional integrated design of automobile collision safety components.