Fault-Tolerant Control Algorithm of Neural Network Based on Particle Swarm Optimization

doi:10.3696/j.issn.1006-396X.2011.03.022

Journal of Petrochemical Universities ›› 2011, Vol. 24 ›› Issue (3): 95-98.DOI: 10.3696/j.issn.1006-396X.2011.03.022

1.School of Information and Control Engineering, Liaoning Shihua University, Fushun Liaoning 113001, P. R. China;  2. SIASUN Robot & Automation Co., Ltd., Shenyang Liaoning 110168, P. R. China

Received:2011-01-10 Revised:2011-04-22 Published:2011-06-25 Online:2011-06-25

基于粒子群优化的神经网络容错控制算法

周立群¹,张晓琴²,李书臣¹,苏成利¹,翟春艳¹

1.辽宁石油化工大学信息与控制工程学院,2.沈阳新松机器人自动化股份有限公司

作者简介:周立群(1982 -), 女, 山东威海市, 在读硕士
基金资助:
辽宁省高校创新团队支持计划项目(2009T062)

Abstract

Abstract: A fault-tolerant control method combining fault diagnosis and fault-tolerant control was proposed for sensor faults of a class of nonlinear system. A BP neural network based on particle swarm optimization algorithm was used to estimate system states and fault parameters of the constructed model for sensor faults. The estimated fault parameters were processed by the modified Bayes classification algorithm to achieve sensor faults detection, separation and estimation online, and fault-tolerant control was realized by compensation algorithm. Simulation results for continuous stirred tank reactor (CSTR) show good convergence of the approach and strong fault-tolerant ability for sensor faults.

Key words: Fault diagnosis, Fault-tolerant control, BP neural network, PSO, CSTR

摘要： 针对一类非线性系统的传感器故障, 将故障诊断与容错控制方法相结合, 提出了一种容错控制方法。用BP 网络建立传感器故障模型, 并用粒子群算法来训练BP 网络的参数, 在线估计系统的状态和故障参数。然后将故障参数与修正的Bay es 分类算法相结合, 对传感器故障在线检测、分离和估计, 通过补偿算法, 实现容错控制。对连续搅拌釜式反应器(CST R)的仿真结果表明, 该方法收敛性好, 对传感器故障具有很强的容错能力。

关键词: 故障诊断 , 容错控制 , BP 神经网络 , 粒子群优化算法 , 连续搅拌釜式反应器

ZHOU Li-qun,ZHANG Xiao-qin,LI Shu-chen,et al. Fault-Tolerant Control Algorithm of Neural Network Based on Particle Swarm Optimization[J]. Journal of Petrochemical Universities, 2011, 24(3): 95-98.

周立群,张晓琴,李书臣,苏成利,翟春艳. 基于粒子群优化的神经网络容错控制算法[J]. 石油化工高等学校学报, 2011, 24(3): 95-98.

[1]	Wei Lixin， Zheng Lilong， Li Wenzhong， Ouyang Xin， Chu Yongqiang， Liu Junbo. Optimization of Production and Operation Parameters of New Daqing-Harbin Oil Pipeline in Alpine Region [J]. Journal of Petrochemical Universities, 2021, 34(1): 39-44.
[2]	Li Chuanxian, Liu Dinghong, Li Jian, Zhu Haoran, Lu Taihui, He Weiguang. Condition Recognition of Liquid Pipeline Based on Optimized BP Artificial Neural Network [J]. Journal of Petrochemical Universities, 2018, 31(6): 73-81.
[3]	Peng Kexiang. Fault Diagnosis of Electric Submersible Pump Based on BP Neural Network [J]. Journal of Petrochemical Universities, 2016, 29(1): 76-79.
[4]	LIU Xiaoqin, WANG Dazhi,ZHANG Cuiling,et al. Fault Diagnosis Apporach of Power Grid Based on Genetic Wavelete Neural Network [J]. Journal of Petrochemical Universities, 2013, 26(6): 78-82.
[5]	HUANG Wei,CONG Yu-feng,GUO Da-peng. Catalytic Oxidized Reaction of Paraffin Wax Based on BP Neural Network [J]. Journal of Petrochemical Universities, 2012, 25(6): 30-33.
[6]	ZHANG Hai-tao,JIANG Hai-yang. Predicting System of Asphalt Aging in Field Based on the Neural Network [J]. Journal of Petrochemical Universities, 2012, 25(5): 71-75.
[7]	MENG Shuai，HOU Li-gang,Lv Pin-chao. Fault Diagnosis Expert System of FCCU Fractionating System [J]. Journal of Petrochemical Universities, 2010, 23(2): 93-96.
[8]	CUI Hou-xi, ZHANG Lai-bin, WANG Zhao-hui,et al. Compressor Valve Fault Diagnosis Based on Wavelet Packet Entropy and SVM [J]. Journal of Petrochemical Universities, 2009, 22(1): 86-88.
[9]	ZHANG Ding-xue,LIU Xin-zhi,GUAN Zhi-hong. Radial Basis Function Neural Netw ork Algo ri thm and I ts Applicat ion [J]. Journal of Petrochemical Universities, 2007, 20(3): 86-88.