Effective defence against network intrusion of cyber physical system（ CPS） is a difficult problem in network security. Based on the CPS of hazardous chemicals in chemical plants

in order to solve the network security problem of IP/TCP encryption protocol in CPS system

a CPS intrusion detection method combining information gain/KLIC and extreme learning machine（ ELM） is proposed. the KLIC is used for feature selection and data dimensionality reduction processing. In order to make ELM better identify network abnormal behavior

the particle swarm optimization（ PSO） is used to optimize the parameters. The simulation results show that the proposed method solves the CPS network security problem from the practical application point and has higher accuracy in identifying network intrusion behaviour

and has a good application prospect.