Search

Subway vehicle roofs must be inspected when entering and exiting the depot to ensure safe subway vehicle operations. This paper presents an improved method for detecting foreign objects on subway vehicle roofs based on the YOLOv7 algorithm. First, we capture images of foreign objects using a line-scan camera at the depot entrance and exit, creating a dataset of foreign roof objects. Subsequently, we address the shortcomings of the YOLOv7 algorithm by introducing the Ghost module, an improved weighted bidirectional feature pyramid network (WBiFPN), and the Wise intersection over union (WIoU) bounding-box regression loss function. These enhancements are incorporated to build the subway vehicle roof foreign object detection model based on the improved YOLOv7, which we refer to as YOLOv7-GBW. The experimental results demonstrate the practicality and usability of the proposed method. The analysis of the experimental results indicates that the YOLOv7-GBW algorithm achieves a detection accuracy of 90.29% at a speed of 54.3 frames per second (fps) with a parameter count of 15.51 million. The improved YOLOv7 model outperforms mainstream detection algorithms in terms of detection accuracy, speed, and parameter count. This finding confirms that the proposed method meets the requirements for detecting foreign objects on subway vehicle roofs.

This study tries to improve the response performance of a moving coil linear motor (MCLM). A newly designed MCLM with a bobbin of triple coils is proposed. A mathematic model and a solution of searching time optimum using an improved Bacterial Foraging Algorithm (BFA) are developed, and a dual-mode controller with Bang-Bang & PI based on the proposed method is put forward. Control analysis and simulation results show the response time of the proposed MCLM driven by the dual-mode controller is reduced from 8.5 to 2.5 ms compared to the traditional single coil MCLM, and the ringing and overshoot are below 5%. The experimental frequency and response time of the proposed MCLM are 300 Hz at 3 dB and 4 ms, respectively. Analysis and experimental results show that the effectiveness of the proposed control technology is verified and the proposed MCLM displays good performance of high frequency and rapid response.