基于深度孤立森林的输电线路缺陷预测算法研究  

Research on Transmission Line Defect Prediction Algorithm Based on Deep Isolation Forest

作　　者：陈亚辉 CHEN Ya-hui(Shihezi University,Shihezi 832003,China)

机构地区：[1]石河子大学,新疆石河子832003

出　　处：《全面腐蚀控制》2024年第5期61-63,共3页Total Corrosion Control

摘　　要：基于YOLO构建输电线路缺陷检测模型,初始化输电线路巡检图像并进行特征提取,将提取的特征作为模型输入量,采用深度孤立森林算法对输电线路缺陷完成预测。实验表明:该方法能够提高预测精度,缩短预测时间。Based on YOLO,a transmission line defect detection model is constructed,the transmission line inspection image is initialized and feature extraction is performed.The extracted features are used as model inputs,and the deep isolation forest algorithm is used to predict transmission line defects.Experiments show that this method can improve prediction accuracy and shorten prediction time.

关 键 词：深度孤立森林 输电线路 缺陷预测 风险值 YOLO 

分 类 号：TM75[电气工程—电力系统及自动化]