[1]郭金玉,于欢,李元.基于KPCA-SVM的相关和独立变量故障检测方法[J].深圳大学学报理工版,2023,40(1):14-21.[doi:10.3724/SP.J.1249.2023.01014]
　GUO Jinyu,YU Huan,and LI Yuan.Related and independent variable fault detection method based on KPCA-SVM[J].Journal of Shenzhen University Science and Engineering,2023,40(1):14-21.[doi:10.3724/SP.J.1249.2023.01014]
点击复制

基于KPCA-SVM的相关和独立变量故障检测方法()
分享到：

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第40卷
期数:
2023年第1期
页码:
14-21
栏目:
电子与信息科学
出版日期:
2023-01-06

文章信息/Info

Title:
Related and independent variable fault detection method based on KPCA-SVM
文章编号:
202301002
作者:
郭金玉; 于欢; 李元
沈阳化工大学信息工程学院，辽宁沈阳 110142
Author(s):
GUO Jinyu;  YU Huan;  and LI Yuan
College of Information Engineering, Shenyang University of Chemical Technology, Shenyang110142, Liaoning Province, P.R.China
关键词:
自动控制技术; 核主成分分析; 支持向量机; 故障检测; 相关变量; 独立变量
Keywords:
automatic control technology;  kernel principal component analysis;  support vector machine;  fault detection;  related variables;  independent variables
分类号:
TP277
DOI:
10.3724/SP.J.1249.2023.01014
文献标志码:
A
摘要:
实际工业过程中有一些独立于其他变量的过程变量，为能够分别检测独立变量与相关变量，提出一种基于核主成分分析（kernel principal component analysis， KPCA）和支持向量机（support vector machine， SVM）相结合的相关和独立变量故障检测方法，记为KPCA-SVM．首先，应用基于互信息的变量划分策略，通过计算变量之间的互信息将过程变量划分为相关变量和独立变量．然后，在相关变量空间和独立变量空间分别建立KPCA和SVM模型对测试数据进行监测．与传统KPCA和SVM算法相比，KPCA-SVM方法结合了KPCA在检测相关变量和SVM方法在检测独立变量上的优势，提高了KPCA和SVM方法的故障检测性能．最后，将KPCA-SVM方法应用于田纳西-伊斯曼（Tennessee-Eastman， TE）工业过程进行故障检测，并与 KPCA、核熵成分分析（kernel entropy component analysis，KECA）和SVM方法进行比较．仿真结果表明，KPCA-SVM方法具有较好的检测效果，对于多种故障的检测效果有所提升，其中对于微小故障5的检测效果有明显提升，进一步验证KPCA-SVM方法的有效性．
Abstract:
In the real industrial process, some process variables are independent of other variables, a fault detection method of related and independent variable based on kernel principal component analysis and support vector machine (KPCA-SVM) is proposed to detect these independent variables separately from related variables. Firstly, a variable division strategy based on mutual information is applied to divide the process variables into related variables and independent variables by calculating the mutual information between variables. Then, KPCA and SVM models are established in the related variable space and the independent variable space to monitor the test data. Compared with the traditional KPCA and SVM methods, the KPCA-SVM method combines the advantages of KPCA in detecting related variables and SVM methods in detecting independent variables, and improves the fault detection performance of KPCA and SVM methods. Finally, the KPCA-SVM method is applied to the Tennessee-Eastman (TE) industrial process for fault detection, and compared with KPCA, kernel entropy component analysis (KECA) and SVM methods. The results show that the proposed KPCA-SVM method has a good detection effect and improves the detection effect of multiple faults, among which the detection effect of minor fault 5 is significantly improved, which further verifies the effectiveness of the KPCA-SVM method.

参考文献/References:

［1］ TAO Yang, SHI Hongbo, SONG Bing, et al. A novel dynamic weight principal component analysis method and hierarchical monitoring strategy for process fault detection and diagnosis [J]. IEEE Transactions on Industrial Electronics, 2020, 67(9): 7994-8004.
［2］ LAN Ting, TONG Chudong, YU Haizhen, et al. Nonlinear process monitoring based on decentralized generalized regression neural networks [J]. Expert Systems with Applications, 2020, 150: 113273.
［3］ GE Zhiqiang. Review on data-driven modeling and monitoring for plant-wide industrial processes [J]. Chemometrics and Intelligent Laboratory Systems, 2017, 171: 16-25.
［4］ HE Q P, WANG Jin. Statistical process monitoring as a big data analytics tool for smart manufacturing [J]. Journal of Process Control, 2018, 67: 35-43.
［5］ WANG Youqing, SI Yabin, HUANG Biao, et al. Survey on the theoretical research and engineering applications of multivariate statistics process monitoring algorithms: 2008—2017 [J]. The Canadian Journal of Chemical Engineering, 2018, 96(10): 2073-2085.
［6］ LI Ning, GUO Shaojun, WANG Youqing. Weighted preliminary-summation-based principal component analysis for non-Gaussian processes [J]. Control Engineering Practice, 2019, 87: 122-132.
［7］ 张成，郭青秀，冯立伟，等．基于局部保持投影-加权k近邻规则的多模态间歇过程故障检测策略［J］．控制理论与应用，2019，36（10）：1682-1689．
ZHANG Cheng, GUO Qingxiu, FENG Liwei, et al. Fault detection strategy based on locality preserving projections-weighted k nearest neighbors in multimodal batch processes [J]. Control Theory & Applications, 2019, 36(10): 1682-1689.(in Chinese)
［8］ SCH?LKOPF B, SMOLA A, M?LLER K R. Nonlinear component analysis as a kernel eigenvalue problem [J]. Neural Computation, 1998, 10(5): 1299-1319.
［9］ LEE J M, YOO C K, CHOI S W, et al. Nonlinear process monitoring using kernel principal component analysis [J]. Chemical Engineering Science, 2004, 59(1): 223-234.
［10］ CHOI S W, LEE C, LEE J M, et al. Fault detection and identification of nonlinear processes based on kernel PCA [J]. Chemometrics and Intelligent Laboratory Systems, 2005, 75(1): 55-67.
［11］ ZHANG Yingwei, LI Shuai, HU Zhiyong. Improved multi-scale kernel principal component analysis and its application for fault detection [J]. Chemical Engineering Research and Design, 2012, 90(9): 1271-1280.
［12］ FAN Jicong, QIN S J, WANG Youqing. Online monitoring of nonlinear multivariate industrial processes using filtering KICA–PCA [J]. Control Engineering Practice, 2014, 22: 205-216.
［13］ JENSSEN R. Kernel entropy component analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5): 847-860.
［14］ DENG Xiaogang, CAI Peipei, CAO Yuping, et al. Two-step localized kernel principal component analysis based incipient fault diagnosis for nonlinear industrial processes [J]. Industrial & Engineering Chemistry Research, 2020, 59(13): 5956-5968.
［15］ 邓晓刚，邓佳伟，曹玉苹，等．基于双层局部KPCA的非线性过程微小故障检测方法［J］．化工学报，2018，69（7）：3092-3100．
DENG Xiaogang, DENG Jiawei, CAO Yuping, et al. Double-level local KPCA method for incipient fault detection in nonlinear process [J]. CIESC Journal, 2018, 69(7): 3092-3100.(in Chinese)
［16］ HU Kunlun, YUAN Jingqi. Multivariate statistical process control based on multiway locality preserving projections [J]. Journal of Process Control, 2008, 18(7/8): 797-807.
［17］ ZHANG Muguang, GE Zhiqiang, SONG Zhihuan, et al. Global–local structure analysis model and its application for fault detection and identification [J]. Industrial & Engineering Chemistry Research, 2011, 50(11): 6837-6848.
［18］ VAPNIK V N. An overview of statistical learning theory [J]. IEEE Transactions on Neural Networks, 1999, 10(5): 988-999.
［19］ 郭金玉，李涛，李元．基于DW-ICA-SVM的工业过程故障检测算法［J］．河北科技大学学报，2021，42（4）：369-379．
GUO Jinyu, LI Tao, LI Yuan. Fault detection algorithm of industrial process based on DW-ICA-SVM [J]. Journal of Hebei University of Science and Technology, 2021, 42(4): 369-379.(in Chinese)
［20］ XUE Yangtao, ZHANG Li, WANG Bangjun, et al. Nonlinear feature selection using Gaussian kernel SVM-RFE for fault diagnosis [J]. Applied Intelligence, 2018, 48(10): 3306-3331.
［21］ HUANG Jian, YAN Xuefeng. Related and independent variable fault detection based on KPCA and SVDD [J]. Journal of Process Control, 2016, 39: 88-99.
［22］ LYMAN P R, GEORGAKIS C. Plant-wide control of the Tennessee Eastman problem [J]. Computers & Chemical Engineering, 1995, 19(3): 321-331.

备注/Memo

备注/Memo:
Received: 2022-04-24; Accepted: 2022-10-09; Online (CNKI): 2022-12-16
Foundation: National Natural Science Foundation of China (62273242)
Corresponding author: Associate professor GUO Jinyu. E-mail: shandong401@sina.com
Citation: GUO Jinyu, YU Huan, LI Yuan. Related and independent variable fault detection method based on KPCA-SVM [J]. Journal of Shenzhen University Science and Engineering, 2023, 40(1): 14-21.(in Chinese)
基金项目：国家自然科学基金资助项目（62273242）
作者简介：郭金玉（1975—），沈阳化工大学副教授、博士．研究方向：故障诊断、生物特征识别算法及应用． E-mail: 969554959@qq.com
引文：郭金玉，于欢，李元.基于KPCA-SVM的相关和独立变量故障检测方法［J］.深圳大学学报理工版，2023，40（1）：14-21.
更新日期/Last Update: 2023-01-30