基于KPCA和SSA优化SVM的非线性过程故障检测

doi:10.3969/j.issn.1006-2475.2023.06.003

计算机与现代化 ›› 2023, Vol. 0 ›› Issue (06): 15-20.doi: 10.3969/j.issn.1006-2475.2023.06.003

基于KPCA和SSA优化SVM的非线性过程故障检测

申志, 李元

沈阳化工大学信息工程学院,辽宁沈阳 110142

收稿日期:2022-07-27 修回日期:2022-08-14 出版日期:2023-06-28 发布日期:2023-06-28
作者简介:申志（1996—）,男,江苏泰州人,硕士研究生,研究方向：过程故障检测,E-mail： shenzhi9696@163.com; 李元（1964—）,女,教授,博士,研究方向：数据驱动的工业过程故障诊断,E-mail： yuan@mail.tsinghua.edu.cn。
基金资助:
国家自然科学基金资助项目（61673279）

Nonlinear Process Fault Detection Based on KPCA and SSA Optimized SVM

SHEN Zhi, LI Yuan

College of Information Engineering, Shenyang University of Chemical Technology, Shenyang 110142, China

Received:2022-07-27 Revised:2022-08-14 Online:2023-06-28 Published:2023-06-28

摘要/Abstract

摘要： 针对工业过程产生的非线性数据存在特征维数高的问题,提出一种基于核主成分分析（Kernel Principal Component Analysis, KPCA）和麻雀搜索算法（Sparrow Search Algorithm, SSA）优化支持向量机（Support Vector Machine, SVM）相结合的过程故障检测算法。首先,采用KPCA算法提取工业过程数据的线性和非线性特征。然后,将提取特征后的数据作为训练样本建立SVM模型,同时利用SSA算法对SVM的惩罚因子和核参数进行优化,寻找最佳分类模型。最后,将最佳的分类模型应用于测试样本进行故障检测。为了验证所提算法的分类效果,本文利用田纳西伊斯曼化工过程数据,将KPCA-SSA-SVM与SVM、KPCA-GA-SVM（Genetic Algorithm, GA）进行对比分析,验证了所提算法的高效性和优越性。

关键词: 核主成分分析, 麻雀搜索算法, 支持向量机, 非线性过程, 故障检测

Abstract: To solve the problem of high characteristic dimension of nonlinear data generated by industrial process, a process fault detection algorithm based on Kernel Principal Component Analysis （KPCA） and Sparrow Search Algorithm （SSA） which is used to optimize the parameters of Support Vector Machine is proposed. Firstly, KPCA algorithm is used to extract linear and nonlinear features of industrial data. Secondly, the data after feature extraction is used as training samples to establish a classification SVM model, and SSA algorithm is used to optimize the kernel parameter and penalty factor of SVM. Finally, the optimized SVM model is applied to test samples for fault detection. In this paper, in order to verify the classification effect of the proposed algorithm, KPCA-SSA-SVM is compared with SVM, KPCA-GA-SVM （Genetic Algorithm, GA） by using a set of nonlinear numerical examples and Tennessee Eastman chemical process data, and the efficiency and superiority of the proposed algorithm is verified.

Key words: kernel principal component analysis, sparrow search algorithm, support vector machine, nonlinear process, fault detection

中图分类号:

TP273

申志, 李元. 基于KPCA和SSA优化SVM的非线性过程故障检测[J]. 计算机与现代化, 2023, 0(06): 15-20.

SHEN Zhi, LI Yuan. Nonlinear Process Fault Detection Based on KPCA and SSA Optimized SVM[J]. Computer and Modernization, 2023, 0(06): 15-20.

参考文献

[1] 单帅帅,马清峰,谢雯鑫. 基于小波包能量谱和ICA的模拟电路故障特征提取方法[J]. 电子测量技术, 2021,44(18):19-23.
[2] HOU H, JI H.Improved multiclass support vector data description for planetary gearbox fault diagnosis[J]. Control Engineering Practice,2021,114(3). DOI: 10.1016/j.conengprac.2021.104867.
[3] 常玉清,康孝云,王福利,等. 基于贝叶斯网络的磨煤机过程异常工况诊断模型实时更新方法[J]. 仪器仪表学报, 2021,42(8):52-61.
[4] 赵亚楠,郭华玲,郑宾,等. 基于KPCA和LSSVM的表面缺陷深度识别[J]. 激光杂志, 2021,42(3):74-78.
[5] LEMOS T, CAMPOS L F, MELO A, et al.Echo state network based soft sensor for monitoring and fault detection of industrial processes[J]. Computers & Chemical Engineering, 2021,155:107512.
[6] 刘俊,章磊. 基于半导体激光干涉技术的电气设备状态检测研究[J]. 激光杂志, 2021,42(5):52-56.
[7] 李立力,刘纲,张亮亮,等. 加权PCA残差空间的加速度传感器故障诊断[J]. 振动、测试与诊断, 2021,41(5):1007-1013.
[8] RATO T, REIS M, SCHMITT E, et al.A systematic comparison of PCA-based statistical process monitoring methods for high-dimensional, time-dependent processes[J]. AIChE Journal, 2016,62(5):1478-1493.
[9] LEE J M, YOO C K, LEE I B.Fault detection of batch processes using multiway kernel principal component analysis[J]. Computers & Chemical Engineering, 2004,28(9):1837-1847.
[10] WANG X G, HUANG L W, ZHANG Y W.Modeling and monitoring of nonlinear multi-mode processes based on similarity measure-KPCA[J]. Journal of Central South University, 2017,24(3):665-674.
[11] BENCHEIKH F, HARKAT M F, KOUADRI A, et al.New reduced kernel PCA for fault detection and diagnosis in cement rotary kiln[J]. Chemometrics and Intelligent Laboratory Systems, 2020,204. DOI: 10.1016/j.chemolab.2020.104091.
[12] PANI A K.Non-linear process monitoring using kernel principal component analysis: A review of the basic and modified techniques with industrial applications[J]. Brazilian Journal of Chemical Engineering, 2022,39(2):327-344.
[13] LIU Y, ZHOU H.MSVM recognition model for dynamic process abnormal pattern based on multi-kernel functions[J]. Journal of Systems Science and Information, 2014,2(5):473-480.
[14] YAN K, SHEN W, MULUMBA T, et al.ARX model based fault detection and diagnosis for chillers using support vector machines[J]. Energy and Buildings, 2014,81:287-295.
[15] WU C H, TZENG G H, LIN R H.A Novel hybrid genetic algorithm for kernel function and parameter optimization in support vector regression[J]. Expert Systems with Applications, 2009,36(3):4725-4735.
[16] ZENG Z, ZHENG W, ZHAO R, et al.The comprehensive design and optimization of the post-fault grid-connected three-phase PWM rectifier[J]. IEEE Transactions on Industrial Electronics, 2016,63(3):1629-1642.
[17] LI W M, ZHOU X K, YANG C, et al.Multi-objective optimization algorithm based on characteristics fusion of dynamic social networks for community discovery[J]. Information Fusion, 2022,79(C):110-123.
[18] MUSIKAWAN P, KONGSOROT Y, SO-IN C, et al. An enhanced obstacle-aware deployment scheme with an opposition-based competitive swarm optimizer for mobile WSNs[J], Expert Systems with Applications, 2022,189: 116035.1-116035.14.
[19] KASHYAP A K, PARHI D R.Multi-objective trajectory planning of humanoid robot using hybrid controller for multi-target problem in complex terrain[J]. Expert Systems with Applications, 2021,179(1). DOI: 10.1016/j.eswa.2021.115110.
[20] WANG Y L, LI L S, HU Z.Swarm intelligence optimization algorithm[J]. Computer Technology and Development, 2008.
[21] 陈红岩,刘嘉豪,盛伟铭,等. 基于GWO的SVM在红外甲烷传感器测量误差分析中的应用[J]. 计量学报, 2021,42(9):1244-1249.
[22] 马砺,张鹏宇,郭睿智,等. 巷道火灾密闭过程烟气温度预测的GA-SVM模型[J]. 中国矿业大学学报, 2021,50(4):641-648.
[23] XUE J K, SHEN B.A novel swarm intelligence optimization approach: Sparrow search algorithm[J]. Systems Science & Control Engineering, 2020,8(1):22-34.
[24] WESOLKOWSKI S.Using kernel principal components for color image segmentation[C]// Proceedings of SPIE - The International Society for Optical Engineering. 2002,4790:1-10.
[25] YAN X F, GE H W, YAN Q S.SVM with RBF kernel and its application research[J]. Computer Engineering and Design, 2006.
[26] WANG Q, CHU L, PENG F, et al.Contribution of aquatic products consumption to total human exposure to PAHs in Eastern China: The source matters[J]. Environmental Pollution, 2020,266. DOI: 10.1016/j.envpol.2020.115339.
[27] ONEL M, KIESLICH C A, PISTIKOPOULOS E N.A nonlinear support vector machine-based feature selection approach for fault detection and diagnosis: Application to the tennessee eastman process[J]. AIChE Journal, 2019,65(3):992-1005.

基于KPCA和SSA优化SVM的非线性过程故障检测

Nonlinear Process Fault Detection Based on KPCA and SSA Optimized SVM

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	卢磊, 贺智明, 黄志成. 基于多策略改进的麻雀搜索算法[J]. 计算机与现代化, 2023, 0(10): 23-31.
[2]	杨孙哲, 孙爱珍. 基于HSV颜色与LBP纹理特征的水稻氮素营养诊断[J]. 计算机与现代化, 2023, 0(07): 86-92.
[3]	尹建丰, 卫鑫, 顾雄伟, 黄凯, 魏敏捷. 基于图像阈值优化及改进SVM的电表数字识别[J]. 计算机与现代化, 2023, 0(05): 106-110.
[4]	赵延平, 王芳, 夏杨. 基于支持向量机的短文本分类方法[J]. 计算机与现代化, 2022, 0(02): 92-96.
[5]	赵聪慧, 冯庆胜. 基于DT-CWT和SVM的踏面旋转不变纹理提取算法[J]. 计算机与现代化, 2021, 0(12): 85-90.
[6]	陈翔, 邹庆年, 谢绍宇, 陈翠琼. 基于迁移学习策略的压板开关状态识别[J]. 计算机与现代化, 2021, 0(05): 120-126.
[7]	王文蔚, 肖军弼, 程鹏, 张悦. 基于SDN的DDoS攻击防御系统[J]. 计算机与现代化, 2021, 0(02): 117-121.
[8]	郭锦平, 边若鹏. MATLAB环境下数据驱动故障检测工具箱设计[J]. 计算机与现代化, 2021, 0(01): 81-86.
[9]	张文华，张志俊. 基于SVM的新能源公交车运营里程核查方法[J]. 计算机与现代化, 2020, 0(05): 39-.
[10]	郑沫利1,赵艳轲1,闫敏2,孙俊2,刘雍容1. 基于RDPSO-SVM的粮食产后储藏环节损耗智能评估方法[J]. 计算机与现代化, 2020, 0(03): 72-.
[11]	刘树艺，李静，胡春，王伟. 基于卷积神经网络与集成学习的交通标志识别[J]. 计算机与现代化, 2019, 0(12): 67-.
[12]	张开延1,2，潘杨3，娄季朝4. 基于ANP-SVM算法的智能变电站过程层网络故障分类[J]. 计算机与现代化, 2019, 0(07): 72-.
[13]	周国华,商俊燕. 一种抗噪的钢印打码字符识别方法[J]. 计算机与现代化, 2018, 0(12): 106-.
[14]	曹雪，王建林，韩锐，邱科鹏，刘伟旻. 基于PARAFAC2时段划分的间歇过程故障检测[J]. 计算机与现代化, 2018, 0(11): 23-.
[15]	王芮1，韩锐2，贾玉祥1. 基于Spark的分布式大数据机器学习算法[J]. 计算机与现代化, 2018, 0(11): 119-.