Power equipment fault diagnosis method based on infrared image

Abstract

The invention discloses a power equipment fault diagnosis method based on an infrared image, and the method comprises the steps: collecting the infrared image of power equipment, carrying out the preprocessing of the infrared image, and building an infrared image data set; importing the test image data set to train the Mask R-CNN network; importing the infrared image data set into a trained Mask R-CNN network, and obtaining an infrared image detection network through small sample transfer learning; inputting a to-be-detected infrared image into the infrared image detection network, performingtemperature analysis and target detection on the to-be-detected infrared image to obtain temperature distribution and a region position of the to-be-detected infrared image, and comparing the temperature distribution and the region position with the infrared image fault feature library to diagnose whether the power equipment has a fault or not. According to the invention, an infrared temperature measurement fault automatic diagnosis method combining a pixel-level target detection technology and a temperature analysis method is introduced, and automatic diagnosis of power equipment faults can be realized.

Description

technical field [0001] The disclosure belongs to the field of state monitoring and fault diagnosis of electric equipment, and in particular relates to an infrared image-based fault diagnosis method for electric equipment. Background technique [0002] Infrared temperature measurement technology uses infrared thermal imaging cameras to detect infrared radiation emitted by objects, and converts the invisible radiation images through a series of conversion processes to obtain an intuitive temperature distribution map of the equipment, so as to realize the detection of abnormal temperature points or abnormal temperature distribution of substation equipment probing. In recent years, infrared temperature measurement and diagnosis technology has been very mature and widely used in various industries. When using this technology for substation inspection, it is generally necessary to quickly scan a large area of ​​the equipment under test to monitor the overall heating status of the...

AI Technical Summary

Problems solved by technology

However, the disadvantages of this technology are also obvious, that is, during the inspection process, whether it is the discovery of suspicious points or the diagnosis of subsequent faults, it is greatly affected by human factors

After using a thermal imager to generate a large number of continuous detection pictures through long-distance and large-area scanning in a short period of time, it is often impossible to find faults in time when screening pictures only relying on manpower, and the inspection time and planning arrangements cannot achieve the expected results

Images