Vehicle interior noise is an important factor affecting ride comfort. To reduce the noise inside the vehicle at the vehicle body design stage, a finite element model of the vehicle body must be established. While taking the first-order global modal of the body-in-white, the maximum sound pressure level of the target point in the vehicle, the body mass, and the side impact conditions into account, the thickness of the body panel as determined via sensitivity analysis is treated as the input variable, and the sample is determined by following the Hamersley experimental design. Specifically, the Elman neural network predicts the noise value in the vehicle, and a vehicle body structure optimization method that comprehensively considers NVH performance and side impact safety is established. The prediction errors of the Elman neural network algorithm were within 3%, which meets the prediction accuracy requirements. To achieve satisfactory restraint performance, the maximum sound pressure level of the target point in the vehicle is reduced by 5.92 dB, and the maximum intrusions of the two points on the B-pillar inner panel are reduced by 31.1 mm and 33.71 mm, respectively. The side impact performance is improved while the noise inside the vehicle is reduced. This study provides a reference method for multidisciplinary research aiming to optimize the design of vehicle body structures.

A ball screw type energy regenerative active suspension under fractional order PID control is proposed and studied in order to improve the vibration damping performance of the suspension. A mathematical model of the energy regenerative actuator is established, the energy recovery power at different frequencies is measured through experiments, and then the electromagnetic torque constant, representing the proportional relationship between the output torque and current of the motor, is calculated according to the experimental results. A mathematical model of the control circuit is established and the feasibility and the superiority of the fractional order PID control are verified by simulation and experiments. To achieve a better damping effect, the fractional order PID controller of the whole vehicle suspension system is parameterized using the Beetle Antenna Search (BAS) algorithm. The results showed that the mean energy recovery power of the actuator was about 3.5091 W at a vibration frequency of 11/6 Hz, and the electromagnetic torque constant of the motor was about 0.2885. The actuator control circuit was feasible, and the root mean square value of current deviation under fractional order PID control was 1.1158 mA, which was optimized by 9.40%, compared to the PID control. The BAS algorithm effectively realized the parameter tuning of the controller, and both the tuned PID and fractional order PID controllers, achieved optimization of suspension damping performance. The optimal value of the damping performance objective function under fractional order PID control was 0.3270, which was optimized by 62.93%, compared to the PID control. In addition, all suspension performance indices under fractional order PID control were optimized to a certain extent, compared with the PID control.

Driver behavior and intention recognition affects traffic safety. Many scholars use the steering wheel angle, distance of the brake pedal, distance of the accelerator pedal, and turn signal as input data to identify driver behaviors and intentions. However, in terms of time, the acquisition of these parameters has a relative delay, which lengthens the identification time. Therefore, this study uses drivers’ EEG (electroencephalograph) data as input parameters to identify driver behaviors and intentions. The key to the driving intention recognition of EEG signals is to reduce their noise. Noise interference has a significant influence on EEG driving intention recognition. To substantially denoise EEG signals, this study selects wavelet transform theory and wavelet packet transform technology, collects the EEG signals during driving, uses the threshold noise reduction method on EEG signals to reduce noise, and achieves noise reduction through wavelet packet reconstruction. After the wavelet packet coefficients of EEG signals are obtained, the energy characteristics of the wavelet packet coefficients are extracted as input to the Bayesian theoretical model for driver behavior and intention recognition. Results show that the maximum recognition rate of the Bayesian theoretical model reaches 82.6%. Early driver behavior and intention recognition has important research significance for traffic safety and sustainable traffic development.

Traffic flow prediction can provide effective support for traffic management and control and plays an important role in the traffic system. Traffic flow has strong spatio-temporal characteristics, and existing traffic flow prediction models tend to extract long-term dependencies of traffic flow in the temporal and spatial dimensions individually, often ignoring the potential correlations existing between spatio-temporal information of traffic flow. In order to further improve the prediction accuracy, this paper proposes a coordinated attention-based spatio-temporal graph convolutional network (CVSTGCN) model for simultaneously and dynamically capturing the long-term dependencies existing between the spatio-temporal information of traffic flows. CVSTGCN is composed of a full convolutional network structure, which combines coordinate methods to specify the influence degrees of different feature information in different spatio-temporal dimensions, and the spatio-temporal information of different spatio-temporal dimensions by the graph convolutional network. In addition, the hard-swish activation function is introduced to replace the Rectified Linear Unit (ReLU) activation function in the prediction of traffic flow. Finally, evaluation experiments are conducted on two real datasets to demonstrate that the proposed model has the best prediction performance in both short-term and long-term forecasting.

The green wave coordinated control model has evolved from the basic bandwidth maximization model to the multiweight approach to an asymmetrical multiband model and a general signal progression model with phase optimization to improve the operational efficiency of urban arterial roads and reduce driving delays and the amount of exhaust gas generated by vehicles queuing at intersections. However, most of the existing green wave models of arterial roads are based on a single phase pattern and little consider the optimization of the combination of multiple phase patterns. Initial queue clearing time is also considered at the green wave progression line in the time–space diagram, which leads to a waste of green light time. This study proposes a coordination control optimization method based on an asymmetrical multiband model with phase optimization to address the abovementioned problem. This model optimizes four aspects in the time–distance diagram: phase pattern selection, phase sequence, offset, and queue clearing time. Numerical experiments were conducted using the VISSIM micro traffic simulation tool for intersections along Kunlunshan South Road in Qingdao, and the effect of green wave coordination was evaluated using hierarchical analysis and compared with the signal-timing schemes generated by the four models: the multiweight approach, the improved multiweight approach, an asymmetrical multiband model, and a general signal progression model with phase optimization. The results show that an asymmetrical multiband model with phase optimization obtains a total bandwidth of 314 s in both directions. In the outbound direction, average number of stops, average travel speed, average travel time, and average delay time improve by 16%, 7.9%, 17.9%, and 15.6%, respectively. In the inbound direction, they improve by 43.7%, 16.1%, 40.7%, and 36%, respectively. Polluting gas emissions and fuel consumption improve by 17.9%. The applicability of the optimization method under different traffic flow conditions is analyzed, and results indicate a clear control effect when the traffic volume is moderate and the turning vehicles on the feeder roads are few. This work can provide a reference for the optimization of subsequent arterial signal coordination and also has indirect significance for environmental protection to a certain extent.

The traditional Linear quadratic regulator (LQR) control algorithm depends too much on expert experience during the selection of weighting coefficients. To solve this problem, we proposed a Genetic K-means clustering Linear quadratic (GKL) algorithm. Firstly, a 2-DOF 1/4 vehicle model and road input model are established. The weights of an LQR controller are optimized using a genetic algorithm. Then, a possible weighting space is constructed based on this optimal solution. Random weighting coefficients of each performance index are generated in this space. Next, LQR control for the 1/4 vehicle model is performed, and the simulation data are recorded automatically, with these random weighting values, different road classes, and driving speed. A machine learning dataset is built from these simulations. Finally, a K-means clustering algorithm is used to classify the LQR control active suspension into three performance modes: safety mode, comprehensive mode, and comfort mode. The optimal weighting matrix of each performance mode is determined to satisfy requirements for different types of drivers. The results show that the new GKL algorithm not only improves the suspension control effect but also realizes different performance modes. It can better adapt to the changes in driving conditions and drivers.