An intelligent infrared image fault diagnosis for electrical equipment
Ying Lin, Weiwei Zhang, Hao Zhang, Demeng Bai, Jun Li, Ran Xu
Abstract
Infrared Thermography is an important way for electrical equipment live detection to monitor the equipment status. In this paper, an intelligent infrared image fault diagnosis method is proposed. We first use a modified deep learning method to detect the arbitrary capture angle equipment part, and then the diagnosis features are extracted according to the detection result. With temperature value extracted, the quantitative fault diagnosis is achieved by taking advantage of data mining methods. Infrared images captured by substation live detection are used to verify the performance. The experimental results show that the algorithm is flexible and can give a feasible way to achieve an automatic infrared image fault diagnosis for electrical equipment.