The YOLO series of target detection networks are widely used in transportation targets due to the advantages of high detection accuracy and good real-time performance. However, it also has some limitations, such as poor detection in scenes with large-scale variations, a large number of computational resources being consumed, and occupation of more storage space. To address these issues, this study uses the YOLOv8n model as the benchmark and makes the following four improvements: (1) embedding the BiFormer attention mechanism in the Neck layer to capture the associations and dependencies between the features more efficiently; (2) adding a 160 × 160 small-scale target detection header in the Head layer of the network to enhance the pedestrian and motorcycle detection capability; (3) adopting a weighted bidirectional feature pyramid structure to enhance the feature fusion capability of the network; and (4) making WIoUv3 as a loss function to enhance the focus on common quality anchor frames. Based on the improvement strategies, the evaluation metrics of the model have improved significantly. Compared to the original YOLOv8n, the mAP reaches 95.9%, representing an increase of 4.7 percentage points, and the mAP50:95 reaches 74.5%, reflecting an improvement of 6.2 percentage points.
Good seat comfort can bring a pleasant experience to commercial vehicle drivers. Therefore, it is necessary to study the vibration characteristics of commercial vehicle seats. This study focuses on commercial vehicle seats with air spring suspension. The friction damping expression of the suspension system was derived. Comprehensive simulation and experimental investigations were conducted on the vertical vibration transmission characteristics of the seat. A multi-objective optimization framework was established by integrating the NSGA-II algorithm with a BP neural network. Specifically, a nonlinear mathematical model was developed using the GA-BP neural network algorithm, with four design parameters as optimization variables: air spring stiffness (K1), damper damping coefficient (C1), cushion equivalent stiffness (K2), and cushion equivalent damping coefficient (C2). The optimization objective was defined as minimizing the maximum seat transmissibility (TR) at the resonance frequency (f). Through the NSGA-II, Pareto optimal solutions were systematically explored, and an optimal parameter combination was identified to enhance the dynamic comfort of the commercial vehicle seat.
Excessive pressure drop within the internal flow channel of the water hydraulic throttle valve will generate severe noise. In order to reduce the noise of the throttle valve, in this paper, the model of the throttle valve was established, and the flow characteristics and acoustic characteristics of the valve were simulated. The simulation results showed that the parameters of the throat structure, such as the half angle, throat inlet angle and throat length, have a significant effect on the noise of the valve. Then, the three main structural parameters were used as optimization variables, and radial basis function (RBF) neural networks and multi-island genetic algorithms (MIGA) were used to reduce the noise of the valve. The approximate model of the relationship between the structural parameters of the valve and noise was established by RBF neural networks, and MIGA was used to optimize the approximate model. Finally, the optimal valve model was established based on the obtained optimal parameters, and its noise was analyzed through simulation and experiment. The research results indicated that the optimization method, which combines RBF Neural Network and MIGA, can effectively reduce the noise of hydraulic throttle valves.
12 October 2022 in Journal of Vibration Engineering & Technologies
With heavy trucks being more widely used in the logistics industry, more and more lorry drivers are frequently exposed to the acoustic-thermal dynamically coupled cockpit environment for a long time. The comfort in the cockpit directly affects driving safety and occupational health. However, the existing research lacks a multi-parameter fusion prediction method for occupant annoyance in this scenario. In this paper, we studied the effect of an acoustic-thermal composite environment on the annoyance level of truck occupants and predicted the annoyance level of the human body by combining environmental parameters and physiological parameters. A total of 20 adult males participated in the subjective annoyance evaluation test, and 60 sets of sample data were obtained under four working conditions by collecting environmental parameters and monitoring physiological parameters, and the effect of acoustic-thermal composite environments was explored using statistical analysis in combination with the subjects’ annoyance polls. The results showed that the human physiological parameters were significantly correlated with the thermal environment, and the correlation coefficient between PMV value and skin temperature was r1 = 0.99, with p < 0.05. The subjective annoyance level was more sensitive to the thermal environment than noise. The correlation coefficient between PMV and annoyance level was r2 = 0.931, and the correlation coefficient between the noise parameter roughness R and annoyance level was r3 = 0.545. The results of this study were based on the screened predictor variables, the annoyance prediction model using the random forest algorithm showed high accuracy on the test set (R2 = 0.941, root mean square error RMSE = 0.259, mean absolute error MAE = 0.201). The study showed that the annoyance prediction model incorporating environmental and physiological parameters could estimate subjects’ annoyance more accurately.
The aerodynamic noise produced by the annular axial cooling fan significantly impacts the NVH performance of automobiles. In response to this challenge, the paper proposes a low-noise annular axial cooling fan design, which based on the principle of small-hole jet flow. To balance the aerodynamic performance and the benefits of noise reduction, an L16 orthogonal array was utilized to optimize the perforated blade parameters at the fan rated operating condition (rotational speed of 2400 rpm and a static pressure rise of ΔPs =120 Pa). Numerical simulations reveal that micro-jets ejected from the perforations effectively optimize the blade surface pressure distribution, diminishing negative pressure backflow zones and significantly reducing vorticity at the guide ring and blade trailing edge. The comprehensive optimal configuration was identified as: radial spacing divided into 15 equal segments, 1 circumferential locating line, 3 radial locating lines, and a 2 mm perforation diameter. Under the identical 120 Pa aerodynamic loading, the optimized model successfully maintained the required mass flow rate while achieving a 1.92 dBA experimental reduction in the A-weighted Total Sound Pressure Level (TSPL) compared to the original model. While discrete tonal noise is significantly suppressed at high speeds, an inherent acoustic tradeoff was observed, characterized by a slight increase in broadband high-frequency noise at lower speeds. The results confirm that this perforation-based method is a viable noise reduction strategy. It provided new insights and references for the low-noise design of annular axial cooling fans.