Substation grounding wire state detection system and method based on deep learning technology

Abstract

The invention discloses a substation grounding wire state detection system and method based on a deep learning technology. The system is composed of a working layer, a transmission layer and a processing layer. The working layer comprises a plurality of cameras, a video monitoring system and an intelligent grounding wire device. The transmission layer comprises a switch and a firewall; the processing layer comprises a server; the detection method comprises the following steps that video data are acquired in real time by a camera, and the video data are uploaded to a video monitoring system to provide a data source for subsequent feature extraction and feature verification; the intelligent grounding wire device obtains chip coding data and collects grounding wire information; and the extracted feature verification result and the ground wire information collected by the intelligent ground wire are gathered and then transmitted to the anti-error logic verification module, whether the anti-error logic is met is judged, and if not, the alarm output module is notified and alarm information is sent out. The system has the advantages that the position and the state of the grounding wire can be detected in real time, operation accidents of the grounding wire are avoided, and on-line, whole-process and omnibearing state detection of the grounding wire of the transformer substation is realized.

Description

technical field [0001] The invention relates to a system and method for detecting the state of a substation grounding wire based on deep learning technology. Background technique [0002] With the rapid development of power grid construction, there are more and more on-site operations in electric power engineering, and personal safety accidents have occurred frequently in recent years. Although safety systems such as the "Safe Work Regulations for Electric Power Operations" and the "two invoices" management have clarified the safety requirements for operations, their binding force is only reflected in the signature, and there are still violations in the implementation process. More effective measures need to be taken to strengthen Supervision and inspection of the operation process. In addition, the power industry has built a relatively complete high-definition video surveillance system for substation networks. However, the video surveillance system is mainly used for the s...

AI Technical Summary

Problems solved by technology

However, in this way, only limited information such as primary equipment status can be obtained, and many information such as video surveillance, secondary equipment, and grounding devices cannot be effectively analyzed and extracted. Even a few substations with monitoring and identification have fixed and single working modes , Judging the legitimacy of the operation by preset feature points, less feature points will easily cause the operator to fail to detect the details of the operation details, more feature points for normal operation but the system cannot recognize a series of problems such as false alarms

Images