Intrusion Detection Method of Industrial Control Network Based on Lightgbm

Aiming at the requirements of high accuracy and high real-time for industrial control network intrusion detection, combined with the characteristics of high accuracy of supervised learning machine learning algorithm under label data set, an intrusion detection method for industrial control network based on lightgbm is proposed. And bayesian optimization algorithm is used to optimize the parameters of lightgbm model to solve the difficult problem of parameter adjustment; finally, this algorithm is compared with other traditional methods in the standard industrial control network data set. The simulation structure shows that the proposed method has higher detection accuracy and efficiency than the traditional method.