Carbon Fiber Reinforced Plastic (CFRP) were used to replace traditional metals to construct battery pack box to achieve lightweight design of battery pack box. Firstly, based on performance requirements, finite element analysis was conducted for the dynamic and static performance of carbon fiber battery pack, topography and size optimization was carried out on the upper cover plate, and structural optimization was made on the lower box body respectively, which increased the first-order natural frequency to 50.63 Hz and reduced weight of the lower box by 31.1%. Secondly, optimization analysis was made on the box layer, and based on the Isight platform, multi-objective optimization was conducted on the weight and first-order natural frequency of the lower box, meanwhile the entropy TOPSIS decision-making method was used to determine the optimal layer design scheme. Finally, the layer sequence was optimized by considering the lamination board laying process. The optimization analysis results show that lower box achieves a weight reduction of 58.9%, and both the maximum displacement and maximum stress under all operating conditions were reduced, and the dynamic and static performance of the battery pack box has been improved.

In order to predict the induction noise of commercial vehicles, a new 1-D simulation model of air compressor is proposed. The Compressor-Engine coupling simulation model can predict the frequency and amplitude of the noise at the main order accurately, and can both recognize the order noise from the air compressor and the engine in the meantime. The characteristic of compressor noise and the noise reduction method of compressor path are studied by this coupling model. The results show that the noise of the compressor has typical pulse noise characteristic. When dealing with this type of noise, the arrangement sequence of different types of mufflers will have a significant impact on the noise reduction effect.

In order to study the influence of shielding structure on electvical vehicles wireless charging system, based on the theory of shielding effectiveness, this paper establishes a relationship model between the thickness of the shielding material and its parameters. Firstly, the shielding effectiveness of single-layer shielding materials with different thicknesses and different shielding materials on the magnetic field is analyzed, and the numerical solutions are compared with the analytical solutions to preliminarily validate the accuracy of the established shielding material thickness model. Based on this, a composite wireless charging shielding structure with the minimum thickness is proposed under the premise of ensuring electromagnetic safety and verified by electromagnetic tests. The results show that when a combination of 0.05 mm ultra-thin silicon steel and 2.52 mm ferrite is used as a dual-layer shielding, the magnetic field intensity reaches the safety limit, and the transmission efficiency reaches 90.92%. Compared with the traditional ferrite and aluminum composite shielding structure, the thickness of the shielding structure is reduced by 1.95 mm.

It is crucial to effectively identify abnormal connections in the battery system of new energy vehicles in order to address their operational safety issues. By utilizing an emergency warning cloud monitoring platform and big data analysis methods, combined with the similarities and differences in data patterns between normal vehicles and vehicles with abnormal or faulty connections, this paper aim. to explore the factors contributing to abnormal defects in power battery connections. A data-driven algorithm for identifying abnormal risk factors in the connection of new energy vehicle battery systems is developed. According to the risk factors, the degree of abnormal connection in the battery system is classified into different levels, and the results show that the proposed algorithm can accurately and effectively identify high-risk vehicles with abnormal connections.

In order to prevent vehicle mass changes and road slope interfering with longitudinal speed of autonomous driving truck, this article utilizes an intelligent navigation system to obtain information including vehicle speed trajectory and road slope. Vehicle longitudinal dynamic model and Compressed Natural Gas (CNG) engine dynamic model are established, and a real-time Dynamic Programming (DP) speed trajectory tracking controller is designed based on the Model Predictive Control (MPC) framework. The simulation results under NEDC and WLTC operating conditions show that the controller can keep vehicle speed stable under conditions of truck mass change and road slope interference, and can optimize speed tracking error while reducing natural gas consumption.

In order to meet the rapid response of the automobile brake-by-wire system to the control motor, this paper proposes an improved super-twisting sliding mode algorithm to realize the accurate control of the brake master cylinder pressure. The paper firstly analyzes the convergence and stability of classical super-twisting sliding mode algorithm, then proposes an improved strategy of super-twisting sliding mode algorithm to solve the problem of slow convergence at the position where the sliding surface is far from the equilibrium point. The stability of the proposed algorithm is proved by theoretical analysis of Lyapunov equation. Finally, the effectiveness of the algorithm is verified by simulation and bench test of brake-by-wire system. The results show that the improved super-twisting sliding mode algorithm improves the convergence speed of the pressure overshoot of the brake-by-wire system by 3.87%, and the steady-state error is controlled within 2%, which improves the control robustness and demonstrates good control performance.

The 3D point cloud object detection algorithm based on deep learning is prone to issues such as inability to maintain network performance and poor transferability when changing scenes or devices. To address this issue, this article proposes an Accurate, Flexible, and highly transferable two-stage 3D point cloud object detection algorithm (AF3D). In the first stage of the AF3D detection algorithm, a segmented fitting algorithm is used to remove the road surface from the collected laser point cloud, then DBSCAN algorithm is used to cluster non-ground point clouds and obtain several clustering clusters. In the second stage of the AF3D detection algorithm, a point cloud fully connected network PFC-Net is established, and features are extracted and classified. Through experiments, it has been proven that this algorithm can achieve good detection performance on public KITTI datasets, and the detection accuracy for cars, pedestrians, and cyclists on real vehicle datasets is 69.74%, 41.25%, and 54.33%, respectively, indicating good transferability.

A method for optimizing the layout of carbon fiber composite floorings for BIW was proposed to enhance precision, efficiency, and structural lightweight. Initially, BIW finite element model was established and its efficiency was validated. Subsequently, material parameters for the carbon fiber composite were obtained through mechanical performance testing, followed by conceptual designing and modeling of the flooring layout. Subsequent utilization of continuous variable optimization determined the thickness, block shapes, and layers of the flooring, employing a discretization and rounding strategy to achieve discrete layer numbers for each layup angle. The optimization results show that the Particle Swarm Optimization-Bacteria Foraging Optimization (PSO-BFO) algorithm proposed herein improves flooring quality, static bending stiffness and BIW lightweight coefficient by 34.4%, 6.0% and 5.3%, respectively.

In order to improve the energy management of Range Extended Electric Vehicle (REEV), firstly Long Short-Term Memory (LSTM) neural network was used to predicate vehicle speed, then calculates the demand power in the prediction time domain, and the demand power in the prediction time domain and the demand power at the current moment were jointly inputted to the Deep Deterministic Policy Gradient (DDPG) agent, which outputted the control quantity. Finally, the hardware-in-the-loop simulation was carried out to verify the real-time performance of the control strategy. The validation results show that using the proposed LSTM-DDPG energy management strategy reduces the equivalent fuel consumption by 0.613 kg, 0.350 kg, and 0.607 kg compared to the DDPG energy management strategy, the Deep Q-Network (DQN) energy management strategy, and the power-following control strategy, respectively, under the World Transient Vehicle Cycling (WTVC) conditions, which is only 0.128 kg different from that of the dynamic planning control strategy when the dynamic planning control strategy is used.

In order to improve the attitude angle solving accuracy of Micro-Electro-Mechanical System Inertial Measurement Unit (MEMS IMU) in unmanned vehicle system, this paper proposed a Particle Swarm Optimization (PSO) based algorithm and a Strong Tracking Adaptive Unscented Kalman Filter (STAUKF) data fusion method. Firstly, two kinds of IMU modules with different precision were filtered by STAUKF algorithm. Secondly, two kinds of error functions were constructed and PSO algorithm was introduced to fuse the two kinds of IMU posterior estimation. Finally, the test was carried out on the built unmanned vehicle platform. Experimental results show that, compared with the data solved by two single IMU sensors, the root mean square error of the transverse roller shaft and pitch shaft angle solved by the proposed algorithm is reduced by 56.67% and 58.94%, respectively, and the data solved is reduced by 36.55% and 52.15% respectively compared with direct weighted average of the redundant dual IMU system. Therefore, the algorithm proposed in this paper is more accurate and robust.