基于PSOGSA前向神经网络的石化控制系统入侵检测

doi:10.11949/j.issn.0438-1157.20181244

化工学报 ›› 2018, Vol. 69 ›› Issue (S2): 350-357.DOI: 10.11949/j.issn.0438-1157.20181244

基于PSOGSA前向神经网络的石化控制系统入侵检测

徐文星¹, 王万红¹, 王芳¹, 刘才², 景邵星¹, 赵国新¹

1 北京石油化工学院信息工程学院, 北京 102617;
2 北京石油化工学院化学工程学院, 北京 102617

收稿日期:2018-10-22 修回日期:2018-10-30 出版日期:2018-12-31 发布日期:2018-12-31
通讯作者: 赵国新
基金资助:
国家自然科学基金项目（61304217，21703013，61702040）；北京市属高校青年拔尖人才培育计划项目（CIT&TCD201704048）。

Intrusion detection of industrial control system based on PSOGSA feedforward neural network

XU Wenxing¹, WANG Wanhong¹, WANG Fang¹, LIU Cai², JING Shaoxing¹, ZHAO Guoxin¹

1 College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China;
2 College of Chemical Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China

Received:2018-10-22 Revised:2018-10-30 Online:2018-12-31 Published:2018-12-31
Supported by:
supported by the National Natural Science Foundation of China (61304217, 21703013, 61702040) and the Cultivation Plan of Young Talents in Municipal Colleges and Universities (CIT&TCD201704048).

摘要/Abstract

摘要：

针对日趋严峻的石化行业工业控制系统（ICS）安全形势，提出一种基于粒子群优化（PSO）和万有引力搜索算法（GSA）的前向神经网络（FNNPSOGSA），用于解决其中的入侵检测问题。分别利用GSA的全局寻优能力和PSO快速局部收敛优势，提出了一种基于PSO和GSA的混合算法PSOGSA，并将其用于前向神经网络（FNNs）的训练。通过多组基准测试数据集，将FNNPSOGSA预测结果同FNNPSO、FNNGSA和参考文献中改进的FRGNN（K-NN）和FRGNN（Naive Bayes）预测结果相比较，验证了PSOGSA在训练FNNs中是可行的，并且FNNPSOGSA具有更高的预测准确率和更强的泛化能力。更进一步，对工控入侵检测标准数据集的仿真结果表明其在工控系统入侵检测中的可行性和有效性。

Abstract:

Aiming at the increasingly serious safety situation of industrial control system (ICS) in petrochemical industry, a forward neural network (FNNPSOGSA) based on particle swarm optimization (PSO) and universal gravitation search algorithm (GSA) is proposed to solve the problem of intrusion detection. A hybrid algorithm based on PSO and GSA is proposed by using the global optimization ability of GSA and the fast local convergence of PSO. PSOGSA is used as a new training method of FNNs to study the effectiveness of FNNPSOGSA model in practical engineering application scenarios. By comparing the FNNPSOGSA prediction results with the FNNPSO, FNNGSA and the improved FRGNN (K-NN) and FRGNN (Naive Bayes) prediction results in the reference literature, the results show that PSOGSA is feasible in training FNNs and has higher prediction accuracy and more generalization ability. The algorithm is applied to attack prediction in intrusion detection of industrial control system (ICS), and simulation study is carried out using industrial intrusion detection standard data set. The results show that the algorithm can achieve very good results in intrusion detection of industrial control systems.

中图分类号:

徐文星, 王万红, 王芳, 刘才, 景邵星, 赵国新. 基于PSOGSA前向神经网络的石化控制系统入侵检测[J]. 化工学报, 2018, 69(S2): 350-357.

XU Wenxing, WANG Wanhong, WANG Fang, LIU Cai, JING Shaoxing, ZHAO Guoxin. Intrusion detection of industrial control system based on PSOGSA feedforward neural network[J]. CIESC Journal, 2018, 69(S2): 350-357.

参考文献 33

[1]	BERE M, MUYINGI H.Initial investigation of industrial control system (ICS) security using artificial immune system (AIS)[C]//International Conference on Emerging Trends in Networks and Computer Communications.IEEE, 2015:79-84.
[2]	DOMGALD P C.The Application of Autonomic Computing For the Protection of Industrial Control Systems[M].Tucson:The University of Arizona, 2011.
[3]	SIWAR K, LUDOVIC P C, MARC B, et al.A survey of approaches combining safety and security for industrial control systems[J].Reliability Engineering and System Safety, 2015, 139:156-178.
[4]	BEAVER J M, BORGES-HINK R C, Buckner M A.An evaluation of machine learning methods to detect malicious SCADA commu-nications[C]//International Conference on Machine Learning and Applications.Miami, FL, USA:IEEE, 2013:54-59.
[5]	NADER P, HONEINE P, BEAUSEROY P.One-class classification for intrusion detection in ACADA systems[J].IEEE Transactions on Industrial Informatics, 2014, 10(4):2308-2317.
[6]	张腾飞, 范启福, 刘伟.基于支持向量机的SCADA系统入侵检测[J].化工自动化及仪表,2015, (2):153-156.ZHANG T F, FAN Q F, LIU W.A support vector machine-based intrusion detection method for SCADA system[J].Control and Instruments in Chemical Industry, 2015, (2):153-156.
[7]	王华忠, 杨智慧, 颜秉勇, 等.融合PCA和PSO-SVM方法在工控入侵检测中的应用[J].科技通报, 2017, 33(1):80-85.WANG H Z, YANG Z H, YAN B Y, et al.Application of fusion PCA and PSO-SVM method in industrial control intrusion detection[J].Bulletin of Science and Technology, 2017, 33(1):80-85.
[8]	尚文利, 李琳, 万明, 等.基于优化单类支持向量机的工业控制系统入侵检测算法[J].信息与控制, 2015, 44(6):678-684.SHANG W L, LI L, WAN M, et al.Intrusion detection algorithm based on optimized one-class support vector machine for industrial control system[J].Information & Control, 2015, 44(6):678-684.
[9]	IRIE B, MIYAKE S.Capabilities of three-layered perceptrons[C]//IEEE International Conference on Neural Networks.IEEE, 1988:641-648.
[10]	HORNIK K, STINCHCOMBE M, WHITE H.Multilayer feedfor-ward networks are universal approximators[J].Neural Networks, 1989, 2(5):359-366.
[11]	LIN C J, CHEN C H, LEE C Y.A self-adaptive quantum radial basis function network for classification applications[C]//IEEE Interna-tional Joint Conference on Neural Networks, 2004.Proceedings.IEEE, 2011:3263-3268.
[12]	MATISA N A, MAMAT W M F W.Clustered-hybrid multilayer perceptron network for pattern recognition application[J].Applied Soft Computing Journal, 2011, 11(1):1457-1466.
[13]	MALAKOOTⅡ B, ZHOU Y Q.Approximating polynomial functions by feedforward artificial neural networks:capacity analysis and design[J].Applied Mathematics & Computation, 1998, 90(1):27-51.
[14]	WENXU W, RUICHUN T, CHENG L, et al.A BP neural network model optimized by mind evolutionary algorithm for predicting the ocean wave heights[J].Ocean Engineering, 2018, 162(10):8-107
[15]	周爱武, 翟增辉, 刘慧婷.基于模拟退火算法改进的BP神经网络算法[J].微电子学与计算机, 2016, 33(4):144-147.ZHOU A W, ZHAI Z H, LIU H T.Improved BP neural network based on simulated annealing[J].Microelectronics & Computer, 2016, 33(4):144-147.
[16]	MOUSAVI S M, MOSTAFAVI E S, JIAO P.Next generation prediction model for daily solar radiation on horizontal surface using a hybrid neural network and simulated annealing method[J].Energy Conversion & Management, 2017, 153:671-682.
[17]	ALAVI A H, GANDOMI A H.Prediction of principal ground-motion parameters using a hybrid method coupling artificial neural networks and simulated annealing[J].Computers & Structures, 2011, 89(23):2176-2194.
[18]	麻士东, 龚光红, 韩亮, 等.目标分配的蚁群-模拟退火算法及其改进[J].系统工程与电子技术, 2011, 33(5):1182-1186.MA S D, GONG G H, HAN L, et al.Hybrid strategy with ant colony and simulated annealing algorithm and its improvement in target assignment[J].Systems Engineering and Electronics, 2011, 33(5):1182-1186.
[19]	闫利军, 李宗斌, 卫军胡.模拟退火算法的一种参数设定方法研究[J].系统仿真学报, 2008, 20(1):245-247.YAN L J, LI Z B, WEI J H.Study on parameter setting method for simulated annealing algorithm[J].Journal of System Simulation, 2008, 20(1):245-247.
[20]	曾小华, 李广含, 宋大凤, 等.基于遗传算法优化的BP神经网络侧翻预警算法[J].华南理工大学学报(自然科学版), 2017, 45(2):30-38.ZENG X H, LI G H, SONG D F, et al.BP neural network rollover warning algorithm based on genetic algorithm optimization[J].Journal of South China University of Technology (Natural Science Edition), 2017, 45(2):30-38.
[21]	刘浩然, 赵翠香, 李轩, 等.一种基于改进遗传算法的神经网络优化算法研究[J].仪器仪表学报, 2016, 37(7):1573-1580.LIU H R, ZHAO C X, LI X, et al.Study on a neural network optimization algorithm based on improved genetic algorithm[J].Chinese Journal of Scientific Instrument, 2016, 37(7):1573-1580.
[22]	KAYA M.The effects of a new selection operator on the performance of a genetic algorithm[J].Applied Mathematics & Computation, 2011, 217(19):7669-7678.
[23]	王东风, 孟丽.粒子群优化算法的性能分析和参数选择[J].自动化学报, 2016, 42(10):1552-1561.WANG D F, MENG L.Performance analysis and parameter selection of PSO algorithm[J].Journal of Automation, 2016, 42(10):1552-1561.
[24]	杨景明, 穆晓伟, 车海军, 等.多策略改进的多目标粒子群优化算法[J].控制与决策, 2017, 32(3):435-442.YANG J M, MU X W, CHE H J, et al.Improved multi-objective particle swarm optimization algorithm based on multiple strategies[J].Control & Decision, 2017, 32(3):435-442.
[25]	汤可宗, 李慧颖, 李娟, 等.一种求解复杂优化问题的改进粒子群优化算法[J].南京理工大学学报, 2015, 34(4):386-391.TANG K Z, LI H Y, LI J, et al.Improved particle swarm optimi-zation algorithm for solving complex optimization problems[J].Journal of Nanjing University of Science and Technology, 2015, 34(4):386-391.
[26]	ZHANG C, SHAO H, LI Y.Particle swarm optimization for evolving artificial neural network[C]//IEEE International Conference on Systems, Man, and Cybernetics.IEEE, 2002:2487-2490.
[27]	SONG L K, FEI C W, BAI G C, et al.Dynamic neural network method-based improved PSO and BR algorithms for transient probabilistic analysis of flexible mechanism[J].Advanced Enginee-ring Informatics, 2017, 33:144-153.
[28]	MIRHALILI S, SADIQ A S.Magnetic optimization algorithm for training multi-layer perceptron[C]//IEEE, International Conference on Communication Software and Networks.IEEE, 2011:42-46.
[29]	SI T, HAZRA S, JANA N D.Artificial neural network training using differential evolutionary algorithm for classification[C]//The International Conference on Information Systems Design and Intel-ligent Applications.2012:769-778.
[30]	ZHANG J R, ZHANG J, LOK T M, et al.A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training[J].Applied Mathematics & Computation, 2007, 185(2):1026-1037.
[31]	SETTLES M, RODEBAUGH B, SOULE T.Comparison of genetic algorithm and particle swarm optimizer when evolving a recurrent neural network[J].Lecture Notes in Computer Science, 2003, 27(23):148-149.
[32]	MIRJALILI S.Hybrid particle swarm optimization and gravitational search algorithm for multilayer perceptron learning[J].Music Educators Journal, 2011, (4):70.
[33]	GANIVADA A, RAY S S, PAL S K.Fuzzy rough sets, and a granular neural network for unsupervised feature selection[J].Neural Networks, 2013, 48(6):91-108.

基于PSOGSA前向神经网络的石化控制系统入侵检测

Intrusion detection of industrial control system based on PSOGSA feedforward neural network

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 33

相关文章 0

编辑推荐

Metrics

本文评价