基于改进的YOLOv5s绝缘子故障识别方法  

Insulator Fault Identification Method of Overhead Contact SystemBased on Improved YOLOv5s

作　　者：刘玉洁[1] 金钧[1] LIU Yujie;JIN Jun(School of Automation and Electrical Engineering,Dalian Jiaotong University,Dalian 116028,China)

机构地区：[1]大连交通大学自动化与电气工程学院,辽宁大连116028

出　　处：《机械与电子》2024年第12期31-36,共6页Machinery & Electronics

摘　　要：为解决高速铁路绝缘子故障检测中常见的错检、漏检等问题,以YOLOv5s算法为基础进行优化提出TASM YOLOv5算法。首先,增加Triplet注意力机制,以提升算法的特征提取能力;其次,引入AFPN渐进特征金字塔网络来提高特征融合利用能力,并且选用SiLU控制激活函数以提高稳定性;最后,更换损失函数为MPDIoU损失函数,可实现准确有效的边界框回归。实验结果表明,TASM YOLOv5算法的平均准确率较高,所得权重文件大小符合轻量化的要求,能有效提高绝缘子故障检测的精度。In order to solve the common problems such as wrong detection and missing detection in the fault detection of high speed railway insulators,the TASM YOLOv5 algorithm is optimized based on the YOLOv5s algorithm.Firstly,the Triplet attention mechanism is added to improve the feature extraction capability of the algorithm.Secondly,the AFPN progressive feature pyramid network is introduced to improve the feature fusion utilization capability.SiLU control activation function is used to improve the stability.Finally,replacing the loss function with MPDIoU loss function can achieve accurate and efficient bounding box regression.The experimental results show that the average accuracy of the TASM YOLOv5 algorithm is high,the weight file size meets the requirements of lightweight,and can effectively improve the accuracy of insulator fault detection.

关 键 词：绝缘子故障识别 YOLOv5s网络 AFPN MPDIoU损失函数 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]