电力信息与通信技术2025，Vol.23Issue(8)：41-52,12.DOI:10.16543/j.2095-641x.electric.power.ict.2025.08.06
基于SCAS-YOLO的变压器电力设备渗漏油检测研究
Study on Oil Leakage Detection of Transformer Power Equipment Based on SCAS-YOLO
摘要
Abstract
Oil leakage detection of transformers and other power equipment is crucial to the safe and stable operation of the power system.For transformer and other power equipment oil leakage is difficult to detect and algorithm complexity and detection accuracy of difficult balance detection and network structure is complex,this paper introduced Swin-Transformer module and CA attention mechanism to enhance the feeling field,improve the backbone network feature extraction ability,and introduce a lightweight Slim-Neck layer,reduce the model complex structure and improve the feature fusion and expression ability.The experimental results show that the number of parameters and computation of the improved model are reduced by about 11%and 7%,and the detection accuracy is improved by 1.8%.At the same time,the model has better detection performance when considering different lighting and different equipment categories.关键词
Swin-Transformer模块/CA机制/Slim-Neck/YOLOKey words
Swin-Transformer module/CA attention mechanism/Slim-Neck/YOLO分类
信息技术与安全科学引用本文复制引用
赵勇彪,张雨柔,邵晓琪,琚贇,张之刚..基于SCAS-YOLO的变压器电力设备渗漏油检测研究[J].电力信息与通信技术,2025,23(8):41-52,12.基金项目
国家自然科学基金项目(2023BJ0221). （2023BJ0221）
