A Rail Wear Detection Method Based on Particle Swarm Algorithm. Issue 1 (1st April 2022)

• Record Type: Journal Article
• Authors: Chen, Zhiyuan; Jiang, Xintao; Luo, Qingli; Zhang, Shubin; Chen, Honghui; Chen, Xiang
• Is Part Of: Journal of physics. Volume 2224:Issue 1(2022)
• Publication Date: 2022-04-01
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/2224/1/012129
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: In China, the high-speed rail network has developed rapidly in recent years. The wear of rail is a risk to its safe operation. Compared with traditional static detection methods, the methods applying computer vision have become one of the major detection methods due to its non-contact ability, high efficiency, and low cost. However, the accuracy of dynamic detection is affected by the flexible outdoor detection conditions, random vibration during the detection process and other undesirable factors. Thus, in order to improve the accuracy of rail wear detection under complex detection conditions, this paper develops a rail wear detection method based on particle swarm algorithm. The experimental results with line-structured light data show that the proposed method improves the accuracy of rail wear detection and provides technical references for the dynamic detection of rail wear.