Design and Implementation of Infrared Image Classification Algorithm for Defective Power Equipment Based on Deep Learning
Kesheng Wang, Shuai Yuan, Zhaomin Yao, Jinwen Gao and Junjie Feng
With the development of smart grid, infrared recognition technology has been widely used in substations, and gradually become a hot technology for power equipment defect detection. However, from the perspective of application effect, there are still some limitations. Based on this, this paper, on the basis of deep learning theory, designs an infrared image classification algorithm for defective power equipment, and tests it through experiment. The final result confirms the feasibility of the classification algorithm and can better detect the defect types of power equipment. The purpose of this study is to promote the application of infrared image classification algorithm for defect type recognition of power equipment, reduce the cost of operation and maintenance of power equipment, and make a positive contribution to the development of smart substation.
Keywords: deep learning; defective electrical equipment; infrared image; classification algorithm