2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于机器学习的信息物理系统安全控制

刘坤 马书鹤 马奥运 张淇瑞 夏元清

刘坤, 马书鹤, 马奥运, 张淇瑞, 夏元清. 基于机器学习的信息物理系统安全控制. 自动化学报, 2021, 47(6): 1273−1283 doi: 10.16383/j.aas.c190352
引用本文: 刘坤, 马书鹤, 马奥运, 张淇瑞, 夏元清. 基于机器学习的信息物理系统安全控制. 自动化学报, 2021, 47(6): 1273−1283 doi: 10.16383/j.aas.c190352
Liu Kun, Ma Shu-He, Ma Ao-Yun, Zhang Qi-Rui, Xia Yuan-Qing. Secure control for cyber-physical systems based on machine learning. Acta Automatica Sinica, 2021, 47(6): 1273−1283 doi: 10.16383/j.aas.c190352
Citation: Liu Kun, Ma Shu-He, Ma Ao-Yun, Zhang Qi-Rui, Xia Yuan-Qing. Secure control for cyber-physical systems based on machine learning. Acta Automatica Sinica, 2021, 47(6): 1273−1283 doi: 10.16383/j.aas.c190352

基于机器学习的信息物理系统安全控制

doi: 10.16383/j.aas.c190352
基金项目: 国家自然科学基金(61873034, 61503026, 61836001), 北京自然科学基金(4182057), 国家自然科学基金重大国际(地区)合作项目(61720106010), 北京市智能物流系统协同创新中心开放课题(BILSCIC-2019KF-13), 北京理工大学研究生创新项目(2019CX20031)资助
详细信息
    作者简介:

    刘坤:北京理工大学自动化学院教授. 主要研究方向为网络化控制理论与应用, 复杂网络控制与安全. 本文通信作者. E-mail: kunliubit@bit.edu.cn

    马书鹤:北京理工大学自动化学院硕士研究生. 主要研究方向为攻击检测, 安全控制, 机器学习. E-mail: mashuhehe@163.com

    马奥运:北京理工大学自动化学院博士研究生. 主要研究方向为模型预测控制, 优化控制. E-mail: maaoyun92@gmail.com

    张淇瑞:北京理工大学自动化学院博士研究生. 主要研究方向为信息物理系统的安全控制, 最优化控制. E-mail: qiruizhang@bit.edu.cn

    夏元清:北京理工大学自动化学院教授. 主要研究方向为云控制, 云数据中心优化调度管理, 智能交通, 模型预测控制, 自抗扰控制, 飞行器控制和空天地一体化网络协同控制. E-mail: xia_yuanqing@bit.edu.cn

Secure Control for Cyber-physical Systems Based on Machine Learning

Funds: Supported by National Natural Science Foundation of China (61873034, 61503026, 61836001), Beijing Natural Science Foundation (4182057), Major International (Regional) Joint Research Project of National Natural Science Foundation of China (61720106010), the Open Subject of Beijing Intelligent Logistics System Collaborative Innovation Center (BILSCIC-2019KF-13), and Graduate Technological Innovation Project of Beijing Institute of Technology (2019CX20031)
More Information
    Author Bio:

    LIU Kun Professor at the School of Automation, Beijing Institute of Technology. His research interest covers theory and applications of networked control, and control and security of complex networked systems. Corresponding author of this paper

    MA Shu-He Master student at the School of Automation, Beijing Institute of Technology. Her research interest covers attack detection, secure control, and machine learning

    MA Ao-Yun  Ph.D. candidate at the School of Automation, Beijing Institute of Technology. His research interest covers model predictive control and optimal control

    ZHANG Qi-Rui Ph.D. candidate at the School of Automation, Beijing Institute of Technology. His research interest covers secure control of cyber-physical systems and optimal control

    XIA Yuan-Qing Professor at the School of Automation, Beijing Institute of Technology. His research interest covers cloud control, cloud data center optimization scheduling and management, intelligent transportation, model predictive control, active disturbance rejection control, flight control, and networked cooperative control for integration of space, air and earth

  • 摘要: 研究了控制信号被恶意篡改的信息物理系统的安全控制问题. 首先, 提出一种改进果蝇优化核极限学习机算法(Kernel extreme learning machine with improved fruit fly optimization algorithm, IFOA-KELM)对攻击信号进行重构. 然后, 将所得重构信号作为系统扰动加以补偿, 进而设计模型预测控制策略, 并给出了使被控系统是输入到状态稳定的条件. 另外, 本文从攻击者角度建立优化模型得到最优攻击策略用以生成足够的受攻击数据, 基于此数据, 来训练改进果蝇优化核极限学习机算法. 最后, 使用弹簧−质量−阻尼系统进行仿真, 验证了改进果蝇优化极限学习机算法和所提安全控制策略的有效性.
  • 图  1  遭受攻击的信息物理系统框图

    Fig.  1  The diagram of the CPS under cyber attack

    图  2  极限学习机结构图

    Fig.  2  The structure of ELM

    图  3  FOA优化参数

    Fig.  3  The optimization parameter of FOA

    图  4  IFOA寻优过程

    Fig.  4  The optimization process of IFOA

    图  5  弹簧−质量−阻尼系统结构图

    Fig.  5  The structure of spring-quality-damping system

    图  6  系统状态轨迹

    Fig.  6  The state of the system

    图  7  训练样本

    Fig.  7  The training sample

    图  8  IFOA-KELM测试样本绝对误差

    Fig.  8  The error between the real attack and the attack learned by IFOA-KELM

    图  11  LSSVM测试样本绝对误差

    Fig.  11  The error between the real attack and the attack learned by LSSVM

    图  9  FOA-KELM测试样本绝对误差

    Fig.  9  The error between the real attack and the attack learned by FOA-KELM

    图  10  PSO-BP测试样本绝对误差

    Fig.  10  The error between the real attack and the attack learned by PSO-BP

    图  12  IFOA和FOA最优适应度值变化曲线

    Fig.  12  The Smellbest of IFOA and FOA

    图  13  受攻击系统引入MPC前后的状态轨迹

    Fig.  13  The state trajectory of the attacked system with MPC and without MPC

    图  14  真实攻击信号与重构攻击信号之间的误差

    Fig.  14  The error between the real attack and the learned

  • [1] Lee J, Bagheri B, Kao H A. A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manufacturing Letters, 2015, 3: 18−23 doi: 10.1016/j.mfglet.2014.12.001
    [2] 李洪阳, 魏慕恒, 黄洁, 邱伯华, 赵晔, 骆文城, 何晓, 何潇. 信息物理系统技术综述. 自动化学报, 2019, 45(1): 37−50

    Li Hong-Yang, Wei Mu-Heng, Huang Jie, Qiu Bo-Hua, Zhao Ye, Luo Wen-Cheng, He Xiao, He Xiao. Survey on cyber-physical systems. Acta Automatica Sinica, 2019, 45(1): 37−50
    [3] Inoue J, Yamagata Y, Chen Y, Poskitt C, Sun J. Anomaly detection for a water treatment system using unsupervised machine learning. In: Proceedings of the 2017 IEEE International Conference on Data Mining Workshops. New Orleans, LA, USA: IEEE, 2017. 1058−1065
    [4] Li D, Chen D C, Goh J, Ng S K. Anomaly detection with generative adversarial networks for multivariate time series. arXiv: 1809.04758, 2018.
    [5] He H B, Yan J. Cyber-physical attacks and defences in the smart grid: A survey. IET Cyber-Physical Systems: Theory and Applications, 2016, 1(1): 13−27
    [6] 夏元清, 闫策, 王笑京, 宋向辉. 智能交通信息物理融合云控制系统. 自动化学报, 2019, 45(1): 132−142

    Xia Yuan-Qing, Yan Ce, Wang Xiao-Jing, Song Xiang-Hui. Intelligent transportation cyber-physical cloud control systems. Acta Automatica Sinica, 2019, 45(1): 132−142
    [7] Wang H J, Zhao H T, Zhang J, Ma D T. Survey on unmanned aerial vehicle networks: A cyber physical system perspective. arXiv: 1812.06821, 2018.
    [8] 刘烃, 田决, 王稼舟, 吴宏宇, 孙利民, 周亚东, 沈超, 管晓宏. 信息物理融合系统综合安全威胁与防御研究. 自动化学报, 2019, 45(1): 5−24

    Liu Ting, Tian Jue, Wang Jia-Zhou, Wu Hong-Yu, Sun Li-Min, Zhou Ya-Dong, Shen Chao, Guan Xiao-Hong. Integrated security threats and defense of cyber-physical systems. Acta Automatica Sinica, 2019, 45(1): 5−24
    [9] Wolf M, Serpanos D. Safety and security in cyber-physical systems and internet-of-things systems. Proceedings of the IEEE, 2018, 106(1): 9−20 doi: 10.1109/JPROC.2017.2781198
    [10] De Persis C, Tesi P. Input-to-state stabilizing control under denial-of-service. IEEE Transactions on Automatic Control, 2015, 60(11): 2930−2944 doi: 10.1109/TAC.2015.2416924
    [11] Liu K, Guo H, Zhang Q R, Xia Y Q. Distributed secure filtering for discrete-time systems under Round-Robin protocol and deception attacks. IEEE Transactions on Cybernetics, 2020, 50(8): 3571−3580 doi: 10.1109/TCYB.2019.2897366
    [12] Peng L H, Shi L, Cao X, Sun C Y. Optimal attack energy allocation against remote state estimation. IEEE Transactions on Automatic Control, 2018, 63(7): 2199−2205 doi: 10.1109/TAC.2017.2775344
    [13] Zhang Q R, Liu K, Xia Y Q, Ma A Y. Optimal stealthy deception attack against cyber-physical systems. IEEE Transactions on Cybernetics, 2020, 50(9): 3963−3972 doi: 10.1109/TCYB.2019.2912622
    [14] Zhu Q Y, Basar T. Game-theoretic methods for robustness, security, and resilience of cyberphysical control systems: Games-in-games principle for optimal cross-layer resilient control systems. IEEE Control Systems Magazine, 2015, 35(1): 46−65 doi: 10.1109/MCS.2014.2364710
    [15] Vu N H, Choi Y S, Choi M. DDoS attack detection using K-nearest neighbor classifier method. In: Proceedings of the 4th IASTED International Conference on Telehealth/Assistive Technologies. Baltimore, Maryland, USA, 2008. 248−253
    [16] Kumar P G, Devaraj D. Intrusion detection using artificial neural network with reduced input features. ICTACT Journal on Soft Computing, 2010: 30−36
    [17] Nawaz R, Shahid M A, Qureshi I M, Mehmood M H. Machine learning based false data injection in smart grid. In: Proceedings of the 1st International Conference on Power, Energy and Smart Grid. Mirpur, Azad Kashmir, Pakistan, 2018. 1−6
    [18] Esmalifalak M, Liu L, Nguyen N, Zheng R. Detecting stealthy false data injection using machine learning in smart grid. IEEE Systems Journal, 2017, 11(3): 1644−1652 doi: 10.1109/JSYST.2014.2341597
    [19] Kiss I, Genge B, Haller P. A clustering-based approach to detect cyber attacks in process control systems. In: Proceedings of the 13th International Conference on Industrial Informatics. Cambridge, United Kingdom, 2015. 142−148
    [20] Yan Z, Wang J. Model predictive control of nonlinear systems with unmodeled dynamics based on feedforward and recurrent neural networks. IEEE Transactions on Industrial Informatics, 2012, 8(4): 746−756 doi: 10.1109/TII.2012.2205582
    [21] 封鹏. 基于PSO-BP神经网络的网络流量预测算法的研究与应用[硕士学位论文], 东北大学, 中国, 2015.

    Feng Peng. Research and Application of Network Traffic Prediction Algorithm Based on PSO-BP Neural Network [Master thesis], Northeastern University, China, 2015.
    [22] Huang G B, Zhou H M, Ding X J, Zhang R. Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2012, 42(2): 513−529 doi: 10.1109/TSMCB.2011.2168604
    [23] Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: A new learning scheme of feedforward neural networks. In: Proceedings of the 2004 IEEE International Joint Conference on Neural Networks. Budapest, Hungary: IEEE, 2004. 985−990
    [24] Huang G B, Siew C K. Extreme learning machine with randomly assigned RBF kernels. International Journal of Information Technology, 2005, 11(1): 16−24
    [25] Minh H Q, Niyogi P, Yao Y. Mercer' s theorem, feature maps, and smoothing. In: Proceedings of the 2006 International Conference on Computational Learning Theory. Berlin, Heidelberg, Germary: Springer, 2006. 154−168
    [26] Pan W T. A new fruit fly optimization algorithm: Taking the financial distress model as an example. Knowledge-Based Systems, 2012, 26: 69−74 doi: 10.1016/j.knosys.2011.07.001
    [27] Kennedy J, Eberhart R. Particle swarm optimization. In: Proceedings of the 1995 IEEE International Conference on Neural Networks. Perth, Australia, 1995. 1942−1948
    [28] 魏立新, 赵默林, 范锐, 周红星. 基于改进鲨鱼优化算法的自抗扰控制参数整定. 控制与决策, 2019, 34(4): 816−820

    Wei Li-Xin, Zhao Mo-Lin, Fan Rui, Zhou Hong-Xing. Parameter tuning of active disturbance rejection control based on ameliorated shark smell optimization algorithm. Control and Decision, 2019, 34(4): 816−820
    [29] Muller S D, Marchetto J, Airaghi S, Kournoutsakos P. Optimizationbased on bacterial chemotaxis. IEEE Transactions on Evolutionary Computation, 2002, 6(1): 16−29 doi: 10.1109/4235.985689
    [30] Guliyev N, Ismailov V. On the approximation by single hidden layer feedforward neural networks with fixed weights. Neural Networks, 2018, 98: 296−304 doi: 10.1016/j.neunet.2017.12.007
    [31] 戴荔. 分布式随机模型预测控制方法研究[博士学位论文], 北京理工大学, 中国, 2016.

    Dai Li. Distributed Stochastic Model Predictive Control [Ph.D. dissertation], Beijing Institute of Technology, China, 2016.
    [32] Liu K, Ma A Y, Xia Y Q, Sun Z Q, Johansson K H. Network scheduling and control co-design for multi-loop MPC. IEEE Transactions on Automatic Control, 2019, 64(12): 5238−5245 doi: 10.1109/TAC.2019.2910724
    [33] Marruedo D L, Alamo T, Camacho E F. Input-to-state stable MPC for constrained discrete-time nonlinear systems with bounded additive uncertainties. In: Proceedings of the 41st IEEE Conference on Decision and Control. Las Vegas, Nevada, USA, 2002. 4619−4624
    [34] 夏元清. 云控制系统及其面临的挑战. 自动化学报, 2016, 42(1): 1−12

    Xia Yuan-Qing. Cloud control systems and their challenges. Acta Automatica Sinica, 2016, 42(1): 1−12
  • 加载中
图(14)
计量
  • 文章访问数:  1960
  • HTML全文浏览量:  524
  • PDF下载量:  797
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-05-10
  • 录用日期:  2019-10-21
  • 刊出日期:  2021-06-10

目录

    /

    返回文章
    返回