基于改进Faster RCNN的电缆外护套破损检测  

Damage detection of cable outer sheath based on improved Faster RCNN

作　　者：薛阳 张舒翔 贾巍 秦瑶 Xue Yang;Zhang Shuxiang;Jia Wei;Qin Yao(School of Automation Engineering,Shanghai University of Electric Power,Shanghai 200090,China;Shanghai Solar Energy Engineering Technology Research Center,Shanghai 200241,China)

机构地区：[1]上海电力大学自动化工程学院,上海200090 [2]上海太阳能工程技术研究中心有限公司,上海200241

出　　处：《电子测量技术》2023年第15期158-164,共7页Electronic Measurement Technology

基　　金：国家自然科学基金(52075316);上海市2021年度“科技创新行动计划”(21DZ1207502);国网浙江省电力有限公司科技项目(5211HZ17000F)资助

摘　　要：工业现场的电缆外护套破损主要依靠人工巡检的方式,消耗人力,主观性大容易出现检查盲点,实时性差且某些工业现场人工巡检危险性较大。针对人工巡检产生的一系列问题,提出一种基于改进的Faster RCNN电缆外护套破损检测方法。为提高模型泛化能力对采集的训练集采用灰度化、翻转、平移、锐化等方法进行数据增强;使用参数量更少且层数更深的特征提取网络RseNet50替换原始的VGG16作为主干特征提取网络;采用迁移学习的方式将ImageNET数据集上训练完成的权重作为模型的初始权重;利用双线性插值法替换感兴趣区域池化操作;通过K-means聚类算法对原始数据集进行聚类分析,采用轮廓系数法作为评价标准,由聚类结果定制外护套破损检测的锚框。实验结果表明,改进的Faster RCNN对电缆外护套破损检测的平均精度均值(mAP)为88.33%比原始的Faster RCNN提高了5.49%,同时优于经典的SSD算法和YOLOv3算法,改进后检测速度达到0.36张/s满足检测要求。该模型可后续搭载各类移动检测平台,具有较高的工程使用价值。The damage of the outer sheath of the cable at the industrial site mainly relies on manual inspection,which consumes manpower,is subject to high subjectivity,and is prone to blind spots.The real-time performance is poor and the manual inspection of some industrial sites is more dangerous.Aiming at a series of problems caused by manual inspection,this paper proposes an improved Faster RCNN cable sheath damage detection method.In order to improve the generalization ability of the model,grayscale,flip,pan,and sharpen the collected training set are used for data enhancement;use the feature extraction network RseNet50 with fewer parameters and deeper layers to replace the original VGG16 as the backbone feature extraction network;use migration learning to use the weights trained on the ImageNET dataset as the initial weights of the model;use bilinear interpolation to replace the ROI Pooling operation;use the K-means clustering algorithm to analyze the original data Cluster analysis was performed on the collection,the Silhouette method was used as the evaluation standard,and the anchor frame of the outer sheath damage detection was customized based on the clustering results.Experimental results show that the improved Faster RCNN has an average accuracy(mAP)of 88.33%for the detection of damage to the outer sheath of the cable,which is 5.49%higher than the original Faster RCNN,and is better than the classic SSD algorithm and YOLOv3 algorithm.The improved detection speed achieve 0.36 frame/s to meet the testing requirements.This model can be subsequently equipped with various mobile detection platforms and has high engineering value.

关 键 词：电缆外护套 目标检测 Faster RCNN K-MEANS 迁移学习 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术]