智能系统学报2025，Vol.20Issue(2)：506-515,10.DOI:10.11992/tis.202311035
面向配电网典型部件的热故障精准判别方法
Accurate identification of thermal faults for typical components of distribution networks
摘要
Abstract
A method for thermal fault diagnosis of distribution network components is presented,which includes the fol-lowing:1)A detection task conversion method used for target detection as a precursor to thermal fault detection.Train-ing and prediction are performed using high-resolution visible light images,and the prediction information is converted into infrared images.2)A style transfer method for scene adaptation in patrol tasks.3)An improved IoU(intersection and union set)loss function,which reduces the effect of low-quality annotations on bounding box regression and im-proves model detection performance.Compared with previous methods,the proposed method uses multimodal image in-formation and is not limited to low-resolution infrared images.The improved method achieves a detection accuracy of 88.1%,maintains real-time performance,and markedly reduces the cases of false and missed detections.The excellent target detection performance provides a solid foundation for thermal fault diagnosis,with an average temperature inter-pretation error not exceeding 0.8 °C.关键词
配电网巡检/热故障判别/多模态图像/目标检测/风格迁移/交并集损失/图像融合/深度学习Key words
distribution network inspection/thermal fault diagnosis/multi-modal images/object detection/style trans-fer/IoU loss/image fusion/deep learning分类
计算机与自动化引用本文复制引用
陶岩,张辉,黄志鸿,单楚栋,徐先勇..面向配电网典型部件的热故障精准判别方法[J].智能系统学报,2025,20(2):506-515,10.基金项目
国家自然科学基金重大研究计划项目(92148204) （92148204）
国家自然科学基金项目(62027810,61971071) （62027810,61971071）
国网湖南省电力有限公司科技项目(5216A522001Y) （5216A522001Y）
湖南省科技创新领军人才项目(2022RC3063) （2022RC3063）
湖南省杰出青年科学基金项目(2021JJ10025) （2021JJ10025）
湖南省重点研发计划项目(2021GK4011,2022GK2011) （2021GK4011,2022GK2011）
长沙理工大学研究生科研创新项目(CXCLY2022088) （CXCLY2022088）
湖南省研究生科研创新项目(CX20220923). （CX20220923）
