Electric power system field operation action risk identification method based on graph convolution

Abstract

The invention relates to a dynamic action risk identification method for field operation personnel of an electric power system. According to the method, skeleton information of the field operation personnel of the electric power system through employing a human body posture estimation method, thereby converting video information into an undirected graph containing the skeleton information; and then, the action recognition of the field operation personnel is realized by utilizing a space-time diagram convolutional network. According to the invention, the risk identification of the dynamic behaviors of the field operation personnel can be realized, and the dynamic violation behaviors and risks of the field operation personnel can be identified in real time, thereby providing a technical means for the early warning and management and control of the safety risk of the power production field, reducing the accident occurrence probability of a power system, and improving the intrinsic safetylevel of power production.

Description

technical field [0001] The invention belongs to the field of power system operation safety management and control, and in particular relates to a method for identifying dynamic action risks of on-site operators in a power system based on graph convolution. Background technique [0002] Safe production is the basic guarantee for the stable operation of the power system. Once a safety accident occurs in the power system, it will cause huge economic losses and adverse social impact. Real-time identification and control of on-site operation risks in the power system is of great significance to ensure the personal safety of operators and the safe and stable operation of the power grid. [0003] At present, the safety risk management methods for on-site operations mainly include manual safety supervision and video surveillance. The manual safety supervision method mainly supervises the behavior of the operators by specially arranging guardians. However, guardians cannot guarant...

AI Technical Summary

Problems solved by technology

However, the guardians cannot guarantee the comprehensive supervision of the operators.

In addition, supervisors are as vulnerable to external factors as operators, and their attention may not be concentrated, which may lead to safety accidents

In particular, the operation of the power system has the characteristics of many sites, many equipment, and complex operations, so the manual supervision method cannot realize real-time supervision and risk warning for all operation processes.

The video surveillance system provides effective assistance for safety supervision, but the actual monitoring tasks still require more manual work to complete, and the surveillance system usually only records video images for subsequent evidence collection

In addition, some scholars have proposed intelligent analysis methods based on surveillance video, including personnel information checks of on-site operators, safety helmet and seat belt detection, substation fire detection, and sign detection. It can be seen that these existing methods mainly focus on static Security Risk Identification

However, the actual field operation in the power system is a continuous and dynamic process, in which there are many dynamic security risks and violations

Existing safety risk identification methods for safety supervision cannot identify those dynamic risks and operator violations

Images