Research On Intrusion Detection Technology Of Industrial Control System

In recent years,with the rapid development of Internet of Things and Industry 4.0,a large number of industrial control communication network and external networks connected,making the industrial control system communication network defects exposed,vulnerable to a variety of attacks.In view of this,in order to realize the protection of the industrial control system communication network,an intrusion detection system is constructed.The main work of this paper is:1.This paper constructs the overall framework of intrusion detection system,including white list self-learning and detection module,deep packet analysis module,traffic-based intrusion detection module and neural network-based multi-protocol intrusion detection module.2.Design and implement a white list self-learning and detection module and traffic-based intrusion detection module.The automatic whitelist is applied to the industrial control system,the automatic establishment of the whitelist and the abnormal detection of the communication packet are realized.The correspondence between the number of packets and the time is taken as the detection feature,and the accuracy of the detection is improved.Characteristics of the intrusion detection module design.3.The multi-protocol intrusion detection module based on neural network is designed and implemented.It mainly includes intrusion detection module based on Modbus / TCP,OPC and DNP3 protocols,and uses the neural network to complete the training and anomaly detection.Finally,on the experimental platform,the test results verify that the intrusion detection module with the bidirectional function code as the detection feature realizes the abnormal detection of the illegal function code of the legal function code set.The intrusion detection system improves the industrial Control system communication network security.