基于YOLOv4的列车锁紧板图像故障检测
2021-05-09王苗张龙信
王苗 张龙信



摘 要:锁紧板偏移故障是货运列车频发的典型故障之一,针对其平均识别精确度较低的问题,将目标检测YOLOv4模型应用于改善货运列车部位锁紧板图像检测。首先,对锁紧板偏移、正常图像进行Mosaic数据增强,以解决数据集样本较少问题。其次,使用k-means聚类算法,得到更优的初始anchor的位置,以提高故障检测精确度。最后,通过非极大值抑制获取得分最高的检测结果。实验表明,通过使用目标检测YOLOv4能够精确地实现锁紧板故障的检测。
关键词:故障检测;锁紧板;YOLOv4
中图分类号:TP391.4 文献标识码:A文章编号:2096-4706(2021)20-0042-03
Image Fault Detection of Train Locking Plate Based on YOLOv4
WANG Miao, ZHANG Longxin
(Hunan University of Technology, Zhuzhou 412007, China)
Abstract: Locking plate offset fault is one of the typical faults frequently occurring in freight trains. Aiming at the problem of low
average recognition accuracy, the object detection YOLOv4 model is used to improve the image detection of part locking plate of freight trains. Firstly, Mosaic data enhancement is performed on the offset of the locking plate and the normal image to solve the problem of less samples in the data set. Secondly, K-means clustering algorithm is used to obtain a better initial anchor position, so as to improve the accuracy of fault detection. Finally, the detection result with the highest score is obtained by non-maximum suppression. Experiments show that the use of target detection YOLOv4 can accurately detect the fault of locking plate.
Keywords: fault detection; locking plate; YOLOv4
0 引 言
隨着经济的快速发展和铁路交通领域的飞跃进步,铁路货运列车开始转变为重载、大密度的运行方式,对于列车安全运行来说,列车故障检测的高效性和准确性的意义至关重要。由于传统的人工检测方式随着货运列车高速和高频率的运行而难以适应,为了推进铁路行业的现代化建设,满足列车故障快速、准确发现的要求,于是铁道部推广了列车运行故障动态检测系统(Trouble of moving freight car detection system, TFDS)[1]。锁紧板是货运列车频繁发生故障部位之一。一旦锁紧板偏移,表示螺栓发生了松动。螺栓的松动重则导致脱落,从而影响到列车的安全运行。因此对于列车安全,锁紧板偏移故障检测至关重要。孙国栋等人[2]针对列车挡键问题设计了一种基于形状上下文的丢失图像识别算法,该方法能够区分列车是否存在挡键。雷蕾等人[3]提出了基于HCRD的列车锁紧板偏转自动识别方法。……
