Method and device for dynamic risk assessment of community gas system based on graph neural network

Abstract

The embodiment of the present invention provides a dynamic risk assessment method and device for a community gas system based on a graph neural network. The method includes: building a community gas system knowledge map based on the community gas system risk assessment index system, which will include The relational community gas system knowledge map is input into the community gas system dynamic risk assessment model, so as to obtain the risk level of the target entity, reason the cause of the community gas accident and predict the dynamic consequences of the accident; among them, the community gas system dynamic risk assessment model includes the first An entity-level attention layer, a first semantic-level attention layer, a second entity-level attention layer, a second semantic-level attention layer, an entity classification layer and a relationship prediction layer. The embodiment of the present invention realizes the dynamic risk assessment of the community gas system and improves the accuracy of the risk assessment by acquiring the risk level of the target entity, reasoning the cause of the community gas accident, and predicting the dynamic consequences of the accident.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a graph neural network-based dynamic risk assessment method and device for a community gas system. Background technique [0002] In recent years, my country's gas industry has made great progress. The popularization and application of gas has played an extremely important role in optimizing the energy structure, improving environmental quality, and improving people's living standards. Gas equipment and facilities are an important part of the community security system, which is related to the safety of people's lives and property, the safety of energy supply, and the safe development of cities. As the popularity of civil gas becomes wider and wider, accidents such as explosions, fires, and poisonings caused by gas leakage occur frequently every year, causing a large number of casualties and property losses, and the safe use of gas has gradually attracted people's ...

AI Technical Summary

Problems solved by technology

[0004] Most of the traditional risk assessment methods for gas systems are static analysis methods based on expert experience and knowledge, which lack dynamics. For example, the risk assessment of gas systems is realized by using Delphi method, AHP and fault tree methods.

Moreover, these methods generally only model individual components in the community gas system. For example, building a risk assessment model only for the gas pipeline network or indoor gas system, the model is generally relatively simple, ignoring the coupling of various components in the community gas system. complex connections

Due to the complexity of the community gas system, once a gas accident occurs, it is often difficult to determine the cause of the accident

The existing gas system risk assessment methods cannot accurately and comprehensively cover such complex scenarios as the community gas system, nor can they establish a dynamic risk assessment model for the multi-type components of the community gas system and the relationship between them for risk assessment

Images