In the process of driving a vehicle, the complex and changing environment inside the vehicle, the change of lighting conditions and the diversity of drivers’ behavioral postures affect the detection and recognition of abnormal driver behavior. To address this issue, this paper proposes a driver abnormal driving behavior detection algorithm based on contrast learning. The paper firstly considers driver’s driving behavior detection as a binary classification task, and utilizes a contrast learning approach to compare driver’s normal driving with abnormal driving samples and to improve the performance of the model by contrasting loss functions. Secondly, the depth images right ahead and above the driver serves as inputs to solve the problems of complex in-vehicle environment to change the light intensity and blind spots in viewpoint by providing the depth information of the driver. Finally, 3D convolution is introduced in the lightweight network MobileNetV2, and the operation of channel blending is added to the convolution layer of each bottleneck structure to improve the accuracy of recognition. Test results show that accuracy of the proposed algorithm reaches 94.18% in the Driver’s Abnormality Detection (DAD) dataset and ROC AUC reaches 0.962, which shows the effectiveness of the algorithm in driver’s abnormal behavior detection.

To address the scarcity of multi-source heterogeneous data and insufficient scenario adaptability in current perception algorithm training and testing of autonomous driving, a typical scenario-based multimodal perception dataset is constructed. It contains 10 specific typical scenario segments, covering multimodal sensor data from LiDAR, cameras, and 4D millimeter-wave radar. The dateset provides annotation information for six categories of targets and offers detailed descriptions of data acquisition device configurations, including sensor parameters, calibration data, and a time synchronization processing scheme. By delivering scenario-specific driving context, the constructed dataset enhances perception accuracy in complex environments, thereby improving the safety and reliability of autonomous driving systems.

In order to analyze the effects of In-Vehicle Traffic Lights (IVTL) on driving behavioral characteristics, a driver data collection system is designed in an environment with obstructed line-of-sight. Fifty human subjects between the ages of 20 and 40 are recruited for the driving simulator test, and vehicle and driver status data are collected. After preprocessing, statistical methods are used to analyze the correlation indicators. The results show that compared with driving without IVTL, the average speed of vehicles equipped with IVTL increase significantly. In the condition of traffic lights obstructed by large vehicle, the distance between following vehicle and leading vehicle is reduced, which potentially improves road traffic efficiency, and IVTL can alleviate the stress of drivers brought by the abnormal road environments.

With the introduction of deep learning technology in recent years, target detection algorithms for autonomous vehicle have made significant progress. This paper analyzes and organizes the traditional object detection algorithms and deep learning object detection algorithms currently applied in autonomous driving from the perspective of the development of object detection technology, analyzes milestone detectors, network structures and the latest detection methods, and explores the development direction of target detection technology.

To achieve more efficient detection of small traffic sign targets under complex urban street background conditions, this paper proposes an improved YOLOv5s algorithm. This enhancement is achieved by incorporating a Convolution Block Attention Module (CBAM) Spatial Channel Attention Mechanism, an Adaptive Spatial Feature Fusion (ASFF) module, and an improved loss function for detection boxes. The validation results on the TT100K traffic sign dataset demonstrate that the proposed algorithm achieves a mean Average Precision (mAP) of 84.5% in traffic sign recognition.

To address the challenge where the traditional Adaptive Cruise Control (ACC) are limited to maintain low-speed following when encountering a low-speed vehicle in front, an ACC control system with lane change function is developed. Firstly the system subdivides the driving modes into three types: cruise control, cruise following and lane change cruise, and a multi-mode switching strategy based on speed dissatisfaction is formulated to flexibly respond to different driving scenarios and driver’s needs. On the basis of the existing adaptive cruise system, the active lane change function is added, and the quintic polynomial is used to accurately plan the lane change trajectory, and then the lane change cruise trajectory tracking controller is constructed based on the Model Predictive Control (MPC) algorithm. Finally, the controller is verified based on MATLAB/Simulink/CarSim. The simulation results show that the proposed strategy meets the requirements of active lane change in line with the driver’s intention.

In order to address the issues of complex control strategy design and hardware circuit implementation of High Frequency AC (HFAC) resonant inverter power supply in Electric Vehicle (EV), this paper proposes a composite control strategy based on the combination of an integral controller and state feedback. Taking the typical LCLC DC-HFAC inverter as the research object, the Linear Quadratic Regulator (LQR) optimization control theory is used to realize the offline digital calculation of the feedback control parameters in the composite control strategy, which improves the dynamic performance of the DC/HFAC inverter and enhances the stability of the DC-HFAC inverter power supply. The control strategy and hardware circuit design are optimized by simplifying the parameter design process of the controller and the Phase-Shift Modulation (PSM) method. The experimental results show that the proposed LCLC DC-HFAC inverter power supply based on LQR optimized feedback composite control strategy not only has good steady-state performance, but also has high conversion efficiency and superior dynamic response speed.

The noise source and the noise transmission of the compressor NVH problem of the electric vehicle heat pump system are studied, and the improvement is made by optimizing the internal structure of the electric compressor, increasing the acoustic package and optimizing the air conditioning pipeline. The NVH test results show that the internal structure optimization can reduce the vibration excitation noise of the electric compressor while the addition of acoustic package and air conditioning pipeline optimization can reduce the compressor noise transmission. These enhancements contribute to a reduction in the noise level of the heat pump system during operation and the NVH performance of the vehicle.

To predict the Remaining Useful Life (RUL) of Proton Exchange Membrane Fuel Cell (PEMFC) precisely, the paper proposes a method for predicting the RUL based on neural network optimized by Improved Snow Ablation Optimizer (ISAO). Firstly the original data are preprocessed by using Pauta criterion and wavelets, then the Pearson’s correlation coefficients are used to select parameters which have strong correlation with voltage as input variables. ISAO is used to optimize hyperparameters of Convolutional Neural Network-Gated Recurrent Unit (CNN-GRU) model. Then the CNN-GRU model is used to predict the output voltage of the PEMFC. Test results show that when the training set ratio is 30%, the mean absolute error is 1.6 mV, the root mean square error is 2.2 mV, the relative error is 0.41%, and the R-squared of the method is 99.20%, which are the best results the of six models. Compared with the Sparrow Search Algorithm (SSA), Snow Ablation Optimizer (SAO) and Whale Optimization Algorithm (WOA), the ISAO has faster optimization speed and better result, proving that the prediction model and the improved algorithm are effective.

To enhance the performance and reliability of power modules, the paper addresses inherent electro-thermal-mechanical multi-physics coupling characteristics. Utilizing Finite Element Analysis (FEA), comprehensive multi-physics simulations are conducted employing ANSYS software tools, including Q3D Extractor, Fluent, Maxwell, and Twin Builder. The simulation results demonstrate that parasitic inductance and thermal resistance significantly impact the switching characteristics and thermal management performance of the power modules. A thorough system-level evaluation is performed through thermal simulation, parasitic parameter extraction, and Double-Pulse Testing (DPT) simulations. Furthermore, the simulation accuracy is significantly improved by implementing an iterative verification process where experimental measurements are used to recalibrate the simulation models. This refined methodology provides a valuable reference for the subsequent optimization of power module design.