To quantify driving risk and develop a safe braking strategy, this paper introduces the concept of Collision Evasion Point (CEP) and builds mathematical models for straight-driving and turning scenarios. Using the CEP, a risk-representation index is defined to quantify driving risk. Moreover, 116 accident cases from China In-Depth Accident Study (CIDAS) database are classified, and the risk representation index is applied to identify high-risk cases. Finally, a dynamic braking strategy based on the braking-time indicator is proposed. Test results show that, across various high-risk scenarios, the proposed risk representation index outperforms Time-to-Collision (TTC) based strategy in identifying scene-level risk, while the braking strategy achieves more reasonable braking times and smoother speed profiles, thereby better avoiding collisions.

In order to overcome the collision and stability issues of the connected vehicle formation in dynamic, uncertain and complex driving scenarios, and improve the driving safety for the connected vehicles, an obstacle avoidance strategy for the connected vehicle formation is proposed basing on optimized artificial potential field method. The obstacle avoidance strategy framework for the connected vehicle formation is designed and the vehicle formation controller basing on the classical artificial potential field method is established. On this basis, the vehicle formation search logic with Levi's flight random search characteristics is proposed to overcome the parameter limitation of the incremental coefficient of attraction and repulsion in artificial potential field method, and enhance the adaptability of the vehicle formation to complex driving environment. The proposed obstacle avoidance strategy is verified by a co-simulation testing platform. Results show that the connected vehicle formation basing on the optimized artificial potential field method can adapt to the complex driving environment more quickly, and has a shorter vehicle formation obstacle avoidance time.

To address the limitations of existing vehicle platooning control methods, such as poor behavior-extendable capabilities, difficulties in handling diverse platoon behaviors during highway driving, and the lack of real-world road testing, this paper proposes a behavior-extendable vehicle platooning control method. Additionally, a leader vehicle acceleration prediction method under packet loss conditions is designed, and a real-vehicle platooning test platform is established. The proposed method is implemented on the real-vehicle platform, and real-vehicle experiments are conducted under packet loss conditions to validate its effectiveness. Road test results, with a maximum speed of 80 km/h and a cumulative distance of approximately 1 000 kilometers, demonstrate that the proposed vehicle platooning control method can safely and effectively manage and extend various platoon behaviors. During stable driving, the average speed errors of the following vehicles are less than 0.62 km/h and 1.55 km/h, respectively, while maintaining stable inter-vehicle spacing. These results verify the effectiveness, real-time performance, and robustness of the proposed control method and the real-vehicle platform.

Addressing the limitations of current intersection collision warning systems, including non-line-of-sight issues and limited consideration of drivers' characteristics, this paper proposes a cooperative collision warning strategy for connected vehicles at intersections, incorporating driver traits. Firstly, driving behaviors at intersections are categorized into straight and turning, and a turning speed model tailored to driver characteristics is built using the InD dataset. Secondly, vehicle turning trajectory prediction is enhanced with a constant yaw rate model and Extended Kalman Filter, while collision risks are dynamically assessed using a dual-circle vehicle geometry model based on Time Exposed to Risk. Thirdly, a two-level warning strategy grounded in non-cooperative game theory is devised, considering driver heterogeneity and dynamic interactions in unsignalized conflicts. Finally, the strategy is validated through simulations and real-vehicle tests. Results indicate the strategy successfully detected all collisions with a 100% warning rate, reduced collisions by up to 100% among diverse drivers, and decreased accidents by 95.06% and kinetic energy by 52.71% even with aggressive drivers.

To address the issue that temporal features and spatial factors of the traffic environment affect the accuracy of vehicle trajectory prediction in vehicle driving, this paper proposes a vehicle trajectory prediction method integrating temporal multi-head self-attention and social pooling based on the Social Generative Adversarial Network (SMA-GAN). Firstly, the historical trajectory features are extracted by the temporal correlation of the target vehicle’s own trajectory data using the multi-head self-attention mechanism. Then, the spatial dimensional features of the target vehicle are extracted by the social pooling mechanism based on the spatial positional relationship between the target vehicle and the surrounding vehicles. Finally, the predicted trajectory of the target vehicle is obtained by the encoder-decoder. Model training and comparison tests are conducted using the NGSIM dataset, and the results show that the SMA-GAN model has higher prediction accuracy and efficiency in the highway scene.

In order to optimize the underbody flow field of vehicle efficiently and reduce aerodynamic drag, this paper takes a electric vehicle as the research object, and proposes a multivariate joint global optimization method. Firstly, considering the influence of RPR fixturess, the method which combines CFD simulation and wind tunnel test is applied to verify the effectiveness of the initial optimization scheme and the reliability of the analysis method; Then, based on DOE, surrogate model and ASA algorithm,two optimization schemes are used to reduce aerodynamic drag: optimization of front wheel deflector, and joint optimization of front and rear wheel deflector. Finally, wind tunnel tests are conducted for verification. The test results show that, multivariate optimization of front wheel deflector has the best drag reduction effect,the drag coefficient of the optimal scheme is reduced by 5.5% compared to the original model.

To address the issue of dynamic changes in data and limited aging data in the Remaining Useful Life (RUL) prediction of lithium-ion batteries, this paper proposes the RUL prediction model of Attention Enhancement Uniformer (AEUniformer) to realize comprehensive information perception by integrating the advantages of Convolutional Neural Network (CNN) and Self-Attention Mechanism through Uniformer. Attention Guiding Mechanism (AGM) and CoordAttention are designed to realize powerful feature extraction. Experimental results show that AEUniformer can achieve accurate and fast RUL prediction with only a single aging cycle, and the MAPE prediction errors of the 2 datasets are 2.7% and 6.16%, respectively, demonstrating the accuracy of the method.

The purpose of this study is to define the automatic triggering conditions for the national standard of the Automatic Emergency Call System (AECS) in China, and to standardize the test conditions to improve the efficiency and accuracy of emergency response to traffic accidents. The paper first studies of the current status of AECS-related standards abroad, proposing the basic principles for the automatic triggering conditions of AECS suitable for China, that is, the collision intensity required for AECS automatic triggering should not exceed the collision intensity required for the airbag to be fired. Through research on the airbag calibration strategies of domestic car and the collection of a large amount of real vehicle collision acceleration data, the collision dynamics in various directions were analyzed, the vehicle body motion characteristics were studied, and the data processing and statistical analysis were carried out. The acceleration waveforms of frontal, side, and rear collisions are determined, and the test acceleration corridors and velocity change parameters for the automatic triggering conditions in the AECS standard are defined accordingly. The results of the verification test show that the defined automatic triggering conditions are more sensitive than the United Nations (UN) standards, which can effectively improve the response efficiency of AECS.

In order to accurately estimate the State of Health (SOH) of lithium-ion batteries, this paper proposes an advanced SOH estimation method that integrates Strategic Optimization Algorithm (SOA) with Memory-Enhanced Long Short-Term Memory (MELSTM) neural network. Firstly, a Variational AutoEncoder (VAE) is utilized to process raw data, reducing redundant information and extracting health indicators, thereby achieving a precise representation of battery degradation information. Subsequently, a hybrid model combining SOA and MELSTM is proposed to estimate SOH of lithium-ion batteries. Finally, effectiveness of the proposed method is validated using 2 public datasets for lithium-ion battery aging, namely CACLE and NASA. Experimental results demonstrate that the proposed method improves RMSE indicators by over 30% compared with conventional LSTM algorithm, offering new insights and solutions for accurate SOH estimation of lithium-ion battery.

In order to improve economy of Fuel Cell Electric Vehicle (FCEV) and thermal management effect of fuel cells, this paper proposes an adaptive hydrogen equivalent consumption minimization strategy based on fuel cell temperature feedback on the basis of hydrogen equivalent consumption minimization strategy. Then, the control effect of the proposed strategy is verified by simulations. The simulation results show that the proposed strategy exhibits strong robustness. Under various driving conditions, including the China Light-duty vehicle Test Cycle for Passenger car (CLTC-P), New European Driving Cycle (NEDC) and World Light Vehicle Test Cycle (WLTC), it achieves a hydrogen consumption reduction of 10.7% to 11.8% compared to rule-based energy management strategies. Furthermore, it demonstrates improvements in thermal management of the fuel cell compared to strategies without considering thermal management, thereby further enhancing the economy of fuel cell vehicles.