Intelligent substation relay protection hard pressing plate checking method based on target detection model

Abstract

The invention discloses an intelligent substation relay protection hard pressing plate checking method based on a target detection model, and the method specifically comprises the steps: downloading a reference file corresponding to a work task, scanning a screen cabinet two-dimensional code, and building a relation with the reference file; after photographing is completed, calling of the YOLOv4-tiny model and analysis of the reference file are synchronously carried out, and a result checked by a worker is finally displayed; if missing detection and false detection do not occur, a worker can directly store the record to the local; and if the phenomenon of missing detection or false detection occurs, a worker needs to correct the corresponding hard pressing plate. According to the method, the protection screen cabinet does not need to be additionally transformed, the hard pressing plate picture shot on site is used for manufacturing the data set, the data enhancement algorithm is researched and used for expanding the data set, the problems of missing detection, error detection and the like in the prior art are further solved, and the method has higher universality and robustness.

Description

technical field [0001] The invention belongs to the technical field of power grid operation and maintenance, and in particular relates to a method for checking a relay protection hard pressure plate of an intelligent substation based on a target detection model. Background technique [0002] Smart grid is an inevitable trend of power grid development, such as document 1: Zhang Yao, Wang Aohan, Zhang Hong. Overview of China's smart grid development [J]. Power System Protection and Control, 2021, 49(5): 180-. and document 2: Yu Yixin. The urgency and long-term nature of smart grid implementation [J]. Power System Protection and Control, 2019, 47(17): 1-5. The relay protection is a relatively weak link, especially the inspection work to protect the hard platen. This work is an important part of the secondary operation and maintenance of the substation. Once the wrong switch or missed switch occurs, it may cause an accident. Therefore, this work requires high reliability, which...

AI Technical Summary

Problems solved by technology

In the process of collecting images, it is found that the color of many hard press boards is very close to the color of the screen cabinet, and they are all camel-like, which will make it difficult to distinguish the hard press board from the background

Some researchers also try deep learning methods, such as: Document 16: Wu Di, Tang Xiaobing, Li Peng, Yang Zengli, Wen Bo, Li Hengxuan. State monitoring technology for substation relay protection devices based on deep neural network [J]. Power System Protection and Control, 2020,48(05):81-85.DOI:10.19783 / j.cnki.pspc.190516. Using convolutional neural network + feature transformation; Document 17: Wang Wei, Zhang Yanlong, Zhai Denghui, etc. Based on OpenCV+SSD depth Intelligent identification of substation pressure plate state based on learning model [J / OL]. Electrical Measurement and Instrumentation: 1-10 [2020-09-13]. http: / / kns.cnki.net / kcms / detail / 23.1202.TH.20200827.1838. 052.html. and Document 18: Zhou Ke, Yang Qianwen, Wang Yaoyi, et al. An Improved SSD Algorithm for Platen State Recognition [J / OL]. Electrical Measurement and Instrumentation: 1-10 [2020-09-17]. http: / / kns.cnki.net / kcms / detail / 23.1202.TH.20200917.1717.002.html. Adopted SSD target detection model; Document 19: Leng Conglin. Research on state recognition system of substation pressure plate switch based on machine vision [D] .Wuhan University of Technology, 2019. The YOLOv3 target detection model is used, but its model accuracy is lower than the model of the article

Some researchers have also found another way. Document 20: Jian Xuezhi, Liu Zijun, Wenming Hao, etc. Application of AR Augmented Reality Technology in Operation and Inspection of Substation Secondary Equipment [J]. Power System Protection and Control, 2020,48(15):170 -176. Applying AR Augmented Reality Technology to Transportation Inspection, Literature 21: Xu Genyang, Weng Shizhuang, Sun Changxiang, etc. Accurate identification method of protection platen state based on phase characteristics [J]. Journal of Anhui University (Natural Science Edition), 2020 , 44(03):38-42. Another proposed a method for identification of the pressure plate state based on phase competition coding, and literature 22: Gao Yuansheng, Chen Qiang, Xiong Xiaofu, etc. Intelligent verification method for relay protection pressure plate [J]. Journal of Chongqing University, 2015, 38(06): 91-98. and Document 23: Zhang Man, Feng Ning, Liu Yingtong, et al. 500kV smart substation pressure plate status monitoring and smart verification technology [J]. Electrical Technology .

[0004] Chinese patent CN113794277A (application number: 202110980430.4) invented a method and system for image recognition of platen status. This invention is also based on deep learning, and also uses mobile devices instead of manual inspection work, but the deep learning model of this invention The accuracy is lower than the present invention, and it does not further solve the missed detection and false detection problems of the model, although the false positive rate and the false positive rate of its model are not higher than 3%, but when such problems occur, the The invention can only be repeated again and again, which will reduce work efficiency

[0005] Chinese patent CN113255827A (Application No.: 202110669583.7) proposes a system and method for identifying the state of the relay pressure plate based on the YOLO Nano algorithm. This invention is also based on the YOLO algorithm and mobile devices, but the mobile device in this invention only completes the pressure plate The identification work of the state, but the core checking work in the inspection work is not completed on the mobile device, so this invention requires frequent data exchange between the mobile device and the server, and the amount of data exchanged at a time is larger

The recognition model designed in the invention with patent publication number (CN) 113794277A still has nearly 3% false negative rate and false positive rate, especially when the imaging angle is inclined or the light is uneven.

Occurrence of false negatives and false positives will lead to inspection personnel needing to take multiple images, which reduces work efficiency and is an urgent problem to be solved

[0008] 2) Correction and completion of the pressure plate for false detection and missed detection

The target detection algorithm based on deep learning cannot guarantee 100% recognition accuracy, that is, the situation of false detection and missed detection cannot be completely eliminated. For example, the invention with the invention patent publication number (CN) of 113255827A can only Take another image and retest

In many cases, the secondary detection cannot solve the false detection and missed detection. Therefore, it is necessary to solve this problem from other angles

Images