改进YOLOv5的工业线圈缺陷检测系统  

Improved YOLOv5 for Industrial Coil Defect Detection System

作　　者：刘坤 向长春 董建新 郝涌汀 Liu Kun;Xiang Changchun;Dong Jianxin;Hao Yongting

机构地区：[1]沈阳理工大学机械工程学院,辽宁沈阳110159

出　　处：《一重技术》2025年第1期58-62,共5页CFHI Technology

摘　　要：设计一种改进YOLOv5算法的智能化工业线圈缺陷检测系统。该算法能够智能识别和报警工业线圈中的间隙、回叠等缺陷,记录检测结果以便于统计分析。实验结果显示:与YOLOv5s算法相比,改进算法后map提升6.4%。检测系统功能齐全,能够满足工业线圈缺陷检测的实际需求。This paper designs an intelligent industrial coil defect detection system by applying improved YOLOv5 algorithm.The algorithm can intelligently identify and alarm defects such as gaps and overlaps in industrial coils and record the detection results for statistical analysis.The test results show that comparing with the YOLOv5s algorithm,the improved algorithm improves the map by 6.4%.The detection system adopts the improved algorithm is with all necessary functions and can meet the actual requirements of industrial coil defect detection.

关 键 词：工业线圈 YOLOv5 缺陷检测 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TM55[自动化与计算机技术—计算机科学与技术]