Automatic infrared image recognition method for substation equipment based on a deep self-attention network and multi-factor similarity calculation
Automatic infrared image recognition method for substation equipment based on a deep self-attention network and multi-factor similarity calculation作者机构:School of Electronic Information and Electrical EngineeringShanghai Jiao Tong University200240 ShanghaiP.R.China State Grid Shandong Electric Power Company Jinan Power Supply Company250001 ShandongP.R.China Maintenance&Test Center of EHV power Transmission CompanyChina Southern Power Grid510000 GuangdongP.R.China
出 版 物:《Global Energy Interconnection》 (全球能源互联网(英文版))
年 卷 期:2022年第5卷第4期
页 面:397-408页
核心收录:
学科分类:080802[工学-电力系统及其自动化] 0808[工学-电气工程] 080901[工学-物理电子学] 0809[工学-电子科学与技术(可授工学、理学学位)] 08[工学] 080203[工学-机械设计及理论] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 0802[工学-机械工程] 0803[工学-光学工程]
基 金:This work was supported by National Key R&D Program of China(2019YFE0102900)
主 题:Substation equipment Infrared image intelligent recognition Deep self-attention network Multi-factor similarity calculation
摘 要:Infrared image recognition plays an important role in the inspection of power *** technologies dedicated to this purpose often require manually selected features,which are not transferable and interpretable,and have limited training *** address these limitations,this paper proposes an automatic infrared image recognition framework,which includes an object recognition module based on a deep self-attention network and a temperature distribution identification module based on a multi-factor similarity ***,the features of an input image are extracted and embedded using a multi-head attention encoding-decoding ***,the embedded features are used to predict the equipment component category and *** the located area,preliminary segmentation is ***,similar areas are gradually merged,and the temperature distribution of the equipment is obtained to identify a *** experiments indicate that the proposed method demonstrates significantly improved accuracy compared with other related methods and,hence,provides a good reference for the automation of power equipment inspection.