Abnormal detection technology of industrial control system based on transfer learning

作者：

Highlights：

• In order to solve the problem of unbalanced sample, a new Tradaboost algorithm is designed.

• An industrial control anomaly detection system based on transfer learning is constructed.

• The identification performance of both source and target domains is improved.

• The experimental results show that the improved algorithm has higher performance.

摘要

•In order to solve the problem of unbalanced sample, a new Tradaboost algorithm is designed.•An industrial control anomaly detection system based on transfer learning is constructed.•The identification performance of both source and target domains is improved.•The experimental results show that the improved algorithm has higher performance.

论文关键词：Industrial control network,Anomaly detection,Instance migration,TrAdaBoost,Unbalanced sample

论文评审过程：Received 30 May 2021, Revised 10 July 2021, Accepted 18 July 2021, Available online 4 August 2021, Version of Record 4 August 2021.

论文官网地址：https://doi.org/10.1016/j.amc.2021.126539