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 enhance the efficiency of the Automatic Emergency Braking System (AEB) test scenarios for passenger cars, this study utilizes 183 highway accidents data from China In-Depth Accident Study (CIDAS) database to explore the construction of highway-based AEB testing scenarios. Static and dynamic factors are extracted from CIDAS database as clustering variables, and a K-means clustering approach is employed to perform a preliminary classification of the selected accidents. Based on the clustering results, 5 representative accident types are identified. Based on the identified typical accident scenarios, and with reference to existing evaluation standards, 5 highway test scenarios for passenger car AEB systems are developed. The findings of this study contribute to the development and performance optimization of AEB system.

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.

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.

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.

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 challenges in the communication between infrastructure and vehicles in intelligent transportation systems, this paper applies the Intelligent Reflecting Surface (IRS) to the intelligent transportation system based on visible light transmission, and deeply analyzes its channel transmission model and the influence of road infrastructure parameters. By modeling the Non-Line-of-Sight (NLOS) channel between the infrastructure and vehicles,the transmission performance of signals in the NLOS channel is analyzed. The closed-form analytical solutions of the system performance are derived for the bit error rate, downtime probability, and block error rate of the IRS-assisted NLOS communication. The impact of the compound pointing error on the bit error rate, downtime probability, and block error rate of the IRS-assisted NLOS communication system is analyzed. The bit error rate performance under M-ary Phase Shift Key (MPSK) modulation and traditional key control modulation is also analyzed. The experimental results show that under the IRS-assisted NLOS transmission condition, when the link follows the double-Rayleigh distribution or the Rayleigh-Rice combined distribution, increasing the distance between the transceiver devices and the height of the street lamp will increase the bit error rate. Increasing the downtime threshold can increase the downtime probability. Increasing the number of transmitted bit blocks can improve the block error rate. MPSK modulation can reduce the system bit error rate more rapidly, and the performance is enhanced as the modulation order increases. After considering the pointing error to the system, its bit error rate, downtime probability and block error rate all increase. The proposed scheme can effectively enhance system communication performance.

To mitigate the interference of external disturbances and environmental uncertainties and improve vehicle speed tracking accuracy, this study proposes a longitudinal motion controller that integrates a High Gain Extended State Observer (HGESO) with Model Predictive Control (MPC). First, the multi-source external uncertainties are consolidated into a stochastic time-varying resistance term in the speed control framework, which is estimated using the HGESO. This approach is combined with a nominal state-space model to enhance the description of vehicle longitudinal dynamics. Subsequently, an incremental MPC controller incorporating the estimated disturbance resistance is employed. This controller designs a multi-objective optimization function that simultaneously considers longitudinal speed tracking error, ride comfort, and energy consumption, ultimately solving for the optimal control input. Finally, precise calibration of the lower-level controller’s mapping table is performed to ensure accurate output of throttle and brake commands, thereby enhancing the controller’s real-time execution capability. Experimental results demonstrate significant improvements in speed tracking accuracy under challenging conditions: a 35%~61.54% enhancement is achieved on steep slopes, and a 26.3%~80.8% improvement is observed during continuous steering maneuvers. The proposed control strategy effectively eliminates the impact of external disturbances on vehicle longitudinal control.

To achieve accurate recognition of vehicle driving intentions in highway scenarios, this paper proposes a driving intention recognition model that combines dual reference lines in the Frenet coordinate with Gaussian Mixture Models (GMMs) and Hidden Markov Models (HMMs). The model selects driving data from different reference lines in the Frenet coordinate based on vehicle position as observed variables. By integrating the observation probabilities output by the GMM at previous and subsequent time steps with the HMM, the model identifies the vehicles’ driving intention at the current moment. The effectiveness of the model is validated using the US-101 dataset from NGSIM. The results show that the dual-reference-line GMM-HMM model achieves recognition accuracies of 93.33% for lane keeping and 92.24% for lane changing, indicating excellent recognition performance.