Search

Fast and accurate detection of airfield pavement damage is crucial to airport flight safety and airfield pavement maintenance. An efficient and lightweight detection algorithm that can be embedded into the mobile detection device has been in urgent demand. However, traditional Convolutional Neural Networks (CNNs) usually generate redundant feature maps during feature extraction or use extra operations during feature fusion to gain better performance, which greatly challenges the efficiency of the algorithm. We approached this issue by proposing an accurate and efficient detection algorithm, the YOLOv5-APD. The algorithm improves the model performance in two ways: Speeding up training and inferencing by using cheaper operations during feature extraction; Reducing the model complexity by removing redundant nodes during feature fusion. We verified the detection performance of YOLOv5-APD on a self-made dataset and compared it with the other state-of-the-art (SOTA) models. Then ablation experiments were carried out to investigate the effects of the proposed model design and the impact of image augmentation. Results showed that the proposed YOLOv5-APD model outperformed the SOTA algorithms in model performance and efficiency, which attained the optimal performance mean average precision (mAP) of 0.924. The proposed model also achieved the fastest inference speed of 142 frame-per-second (FPS), with a model footprint of 8.3 G FLOPs and 8 MB Parameters. [ABSTRACT FROM AUTHOR]

For electric power steering system (EPS), road interference, noise of the sensor, and the uncertainty of the steering system may make EPS control effect and the driver's road sense worse. EPS system which takes advantage of good current tracking ability, good anti-interference ability, and good operation stability is becoming more and more important in automotive research. The traditional H∞ control algorithm can solve the system uncertainty theoretically, but it cannot solve the contradiction between robustness and performance without considering the performance of the system. Therefore, this paper proposes a EPS current tracking method based on the hybrid sensitivity H∞ control algorithm, which takes the current tracking performance as one of the control objectives, so that the system can maximize the robustness and performance. Firstly, the dynamic model of EPS is established. Then, the two-degree-of-freedom vehicle model and tire model are introduced. The state space equation of the system is constructed on the basis of the system state space with random disturbance signals, the hybrid sensitivity H∞ controller is designed in the sensitivity index design, and the proposed algorithm can use weighting function to minimize the performance of the current tracking error as well as the robustness of the yaw rate error in response to robustness. Simulation analysis and experimental verification of EPS system are also carried out. The results show that the control method of the hybrid sensitivity H∞ can better achieve EPS target current tracking, effectively suppress the effect of external interference and noise, improve the system performance and robustness, ensure the driver get good road sense, and improve the system of steering stability. [ABSTRACT FROM AUTHOR]