Netinfo Security ›› 2022, Vol. 22 ›› Issue (5): 46-53.doi: 10.3969/j.issn.1671-1122.2022.05.006

Previous Articles     Next Articles

An Intrusion Detection Method of Train Control System Based on Ensemble Learning

WANG Haoyang1,2, LI Wei3,4, PENG Siwei3,4, QIN Yuanqing1,2()   

  1. 1. School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China
    2. MOE Laboratory of Image Processing and Intelligent Control, Wuhan 430074, China
    3. Intelligent Network R & D Department of CRRC Zhuzhou Locomotive Co., Ltd., Zhuzhou 412001, China
    4. The State Key Laboratory of Heavy Duty AC Drive Electric Locomotive Systems Integration of CRRC Zhuzhou Locomotive Co., Ltd., Zhuzhou 412001, China
  • Received:2022-02-25 Online:2022-05-10 Published:2022-06-02
  • Contact: QIN Yuanqing E-mail:qinyuanqing@mail.hust.edu.cn

Abstract:

This paper proposes an intrusion detection method based on ensemble learning. The random forest classifier is used to integrate the spatial feature extraction model of one-dimensional multi-scale convolution network and the temporal feature extraction model of adaptive time convolution network, so as to reduce the network generalization error and improve the accuracy of intrusion detection. Based on the intrusion detection data set simulated by the hardware-in-the-loop simulation platform of train control system, this paper conducts experimental evaluation and comparative tests on the proposed intrusion detection method, and the results prove the advantages of the method.

Key words: train control system, ensemble learning, intrusion detection, convolutional neural network, adaptive computation time

CLC Number: