Industrial system anomaly detection method based on graph attention network and LSTM automatic coding model

Abstract

The invention discloses an industrial system anomaly detection method based on a graph attention network and an LSTM automatic coding model. The method comprises the following steps: 1) sample division and standardization: dividing original industrial system data into samples by adopting a sliding window; 2) building an anomaly detection model: building the anomaly detection model by adopting a graph attention network and an LSTM (Long Short Term Memory) automatic coding machine; and 3) performing real-time anomaly detection: calculating an anomaly degree score based on a reconstruction error, and performing anomaly state judgment on the basis. According to the method, the automatic coding machine is adopted, the anomaly detection model is trained in an unsupervised mode, and an anomaly annotation sample does not need to be provided; and the graph attention network is adopted to mine the association between different dimensions of the industrial system, and the anomaly detection accuracy in the complex industrial system is improved.

Description

technical field [0001] The invention relates to machine learning technology, in particular to a method for detecting anomalies in industrial systems. Background technique [0002] With the rapid development of the industrial Internet, more sensitive and efficient automatic control and resource allocation of industrial systems have been realized. However, since the Industrial Internet breaks the boundary between the cyber world and the physical world, the industrial manufacturing system is more vulnerable to external malicious acts. In addition, production problems such as equipment failure, performance degradation, and quality defects are inevitable in industrial manufacturing systems. If abnormal situations such as intrusion and failure in industrial production cannot be detected in time, it may bring serious losses to the entire manufacturing system. Therefore, anomaly detection is a basic requirement of the Industrial Internet and is of great significance to smart manuf...

AI Technical Summary

Problems solved by technology

[0005] However, there are still deficiencies in the existing anomaly detection model based on "recurrent neural network + autoencoder": first, the existing method regards the multi-dimensional time-series industrial system data as an overall input anomaly detection model, but in fact the different monitoring of industrial systems Devices are not completely independent, making potential correlations between different dimensions of industrial system data

Secondly, existing methods treat different dimensions of multi-dimensional time-series industrial system data equally (usually different monitoring devices), but in fact, different dimensions have different influences on abnormal states in different scenarios.

Images