Control process-oriented anomaly detection system

Abstract

Through a method in the field of artificial intelligence, an anomaly detection system oriented to a control process is realized, and the system architecture is divided into two parts of a training stage and a test stage; in the training stage, sensor data of a training set is input into an association rule mining step after being discretized, and the association rule mining step is carried out onthe sensor data of the training set; the data of the actuator is directly inputted into an association rule mining step, and then an association rule is generated through an association rule mining algorithm; in the test stage, after discretization of the sensor data, the discretized sensor data, actuator data and label attributes are input into an anomaly detection model together, and the anomalydetection model finally outputs a detection result by using an association rule mining algorithm. According to the association rule-based anomaly detection method for the industrial control system, more association rules are used in an anomaly detection process, false alarms are effectively reduced under the condition of ensuring a certain recall rate, and the efficiency is prevented from being reduced by a large number of association rules under the condition of ensuring that a result is not influenced.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to an abnormality detection system oriented to a control process. Background technique [0002] With the development of computer and network technology, more and more general-purpose protocols, hardware and software are used in industrial control systems, and are connected to public networks such as the Internet in various ways, which has led to many industrial control issues in recent years. Security events in the system. At the same time, because industrial control systems are usually used in large-scale infrastructure, abnormalities in the system often cause serious economic losses and adverse social impacts. Therefore, it is of great significance to propose an anomaly detection method for industrial control systems. [0003] Due to the increasing number of attacks and their serious consequences, researchers have done a lot of research work and proposed many anomaly detec...

AI Technical Summary

Problems solved by technology

[0021] (3) When the amount of data is large, the number of frequent itemsets and association rules is large, and it takes a long time to mine association rules and detect anomalies

Images