Power equipment operation state detection method based on infrared image

Abstract

The invention relates to a power equipment operation state detection method based on an infrared image, and belongs to the field of automation. The method comprises the following steps: S1, collecting and integrating data of each inspection platform of a power grid, and uniformly preprocessing the data for subsequent algorithms to use; s2, identifying and positioning the power equipment based on a Faster RCNN algorithm, and making a response strategy of a corresponding state of the power equipment; and S3, carrying out auxiliary judgment on the state detection of the power equipment with the assistance of a temperature threshold method, and implementing a corresponding response strategy. According to the method, an existing electrical equipment infrared image state detection and recognition scheme is improved, the method can be used for electrical equipment infrared image state detection, recognition and positioning marking, infrared image information is automatically processed through an algorithm model, manual judgment or a traditional machine recognition method is omitted, and a state detection model which is more efficient, more accurate and higher in generalization is established.

Description

technical field [0001] The invention belongs to the field of automation, and relates to an infrared image-based operating state detection method for electric power equipment. Background technique [0002] The current infrared detection and identification technologies based on the state of electrical equipment mainly include: ① Image feature comparison method. The human body observes the abnormal red and white areas in the collected infrared images with the naked eye, and then compares similar equipment and before and after images. ②Threshold discrimination method. The software sets the maximum allowable temperature. When it is detected that the temperature of the device is close to or reaches the set threshold, it means that the device is in an abnormal state. ③ temperature difference calculation method. Set the detection standard and calculate the temperature rise ratio according to the standard. If the temperature rise is too large, attention should be paid to it. ④ fi...

AI Technical Summary

Problems solved by technology

[0003] At present, there are still the following problems and difficulties in the identification and positioning of the infrared image status of power equipment. (1) Due to the influence of shooting angle quality and environment, there will be situations where the infrared image of power equipment is not clear, the angle deviates, and the characteristics of the equipment are not obvious.

This makes the current substations face problems such as complex background and difficult image identification; (2) the processing speed of massive equipment images generated by intelligent inspection robots is slow, lacks intelligence, and relies on human eyes to judge; (3) there is power Missed detection of equipment and real-time detection have not been effectively realized

[0004] Aiming at the problem that the state of the infrared image of the traditional substation power equipment cannot be efficiently and intelligently identified and located, a set of efficient and highly accurate power equipment operating state detection and recognition system is designed for the power system based on deep learning

Images