Substation Equipment Fault Diagnosis Based On Infrared Image Processing

In order to ensure the safe and reliable operation of the substation, the temperature monitoring and fault detection of electrical equipment in the operation of the substation is very important. Infrared detection technology is an effective method for thermal fault detection, but at present, the fault detection has a large dependence on people's experience and the detection efficiency is low. Automatic fault detection is an effective method to solve the above problems, and image processing is an important part of it.Therefore, this paper studies the denoising and segmentation of infrared image of substation equipment, and the research results are applied to the thermal fault detection of substation equipment.Firstly, this paper analyzes and summarizes the characteristics and noise types of the infrared image of the substation, and in view of the shortcomings of several common denoising algorithms, the adaptive weighted selection mask algorithm is proposed for image denoising. The algorithm can effectively remove the gaussian noise and the salt and pepper noise, and has strong adaptability. Then the traditional FCM image segmentation is studied, and aiming at the problem that the FCM algorithm is sensitive to clustering center and can not automatically determine the clustering center, a fuzzy image segmentation algorithm based on genetic algorithm and gray histogram optimization is proposed. Compared with the traditional FCM algorithm, the algorithm in this paper is more robust and effective, and can effectively extract the target region. The temperature characteristics of the device are separated by the separation of the thermal area, normal area and background, and the automatic fault detection algorithm based on relative temperature difference method is realized. The experimental results show that the algorithm has good detection effect on the current induced thermal device fault. Finally,the infrared detection system of the substation id designed and implemented in this paper.The system has realized the unified management of the infrared image, and improved the detection efficiency by automatic infrared detection and auxiliary detection tool.