在线压缩核主元分析的自适应过程监控

doi:10.16183/j.cnki.jsjtu.2021.084

摘要/Abstract

摘要：

对于动态系统,传统的核主元分析(KPCA)方法处理的效果不理想.滑动窗口核主元分析方法能适应动态系统的正常参数漂移,但是该方法处理大量的样本时需要较长的运算时间.因此,提出一种在线压缩核主元分析的自适应过程监控方法.该方法在大量的样本中选定较小的训练集作为初始压缩集进行建模,对在线实时采集的数据进行分析,判断新的样本是否正常.若为正常样本,判断该样本是否加入压缩集中,在加入压缩集的同时自动更新在线KPCA模型.将该方法应用到数值例子和田纳西-伊斯曼(TE)过程,仿真结果验证了该方法的有效性.

关键词: 核主元分析, 在线压缩核主元分析, 滑动窗口, 过程监控

Abstract:

In the case of dynamic systems, the traditional kernel principal component analysis (KPCA) method does not perform well. The moving window kernel principal component analysis method can adapt to the normal parameter drift of dynamic systems, but it needs a longer computation time when processing large number of samples. Therefore, an adaptive process monitoring method for online reduced kernel principal component analysis is proposed. In this method, a small training set is selected as the initial reduced set in a large number of samples for modeling, and the online real-time collected data are analyzed to judge whether the new sample is normal or not. If it is a normal sample, the method judges whether the sample is added to the reduced set, and updates the online KPCA model automatically when adding to the reduced set. The proposed method is applied to a numerical example and the Tennessee-Eastman (TE) process. The simulation results show that the proposed method is effective and feasible.

Key words: kernel principal component analysis (KPCA), online reduced kernel principal component analysis (ORKPCA), moving window, process monitoring

中图分类号:

TP277

郭金玉, 李文涛, 李元. 在线压缩核主元分析的自适应过程监控[J]. 上海交通大学学报, 2022, 56(10): 1397-1408.

GUO Jinyu, LI Wentao, LI Yuan. Adaptive Process Monitoring of Online Reduced Kernel Principal Component Analysis[J]. Journal of Shanghai Jiao Tong University, 2022, 56(10): 1397-1408.

图/表 9

图1

图2

表1

图3

表2

表3

图4

图5

表4

参考文献 33

[1]	CHO J H, LEE J M, CHOI S W, et al. Fault identification for process monitoring using kernel principal component analysis[J]. Chemical Engineering Science, 2005, 60(1): 279-288. doi: 10.1016/j.ces.2004.08.007 URL
[2]	WANG G, YIN S. Quality-related fault detection approach based on orthogonal signal correction and modified PLS[J]. IEEE Transactions on Industrial Informatics, 2017, 11 (2): 398-405.
[3]	CHENG C Y, HSU C C, CHEN M C. Adaptive kernel principal component analysis (KPCA) for monitoring small disturbances of nonlinear processes[J]. Industrial & Engineering Chemistry Research, 2011, 49(5): 2254-2262. doi: 10.1021/ie900521b URL
[4]	AMAR M, GONDAL I, WILSON C. Vibration spectrum imaging: A novel bearing fault classification approach[J]. IEEE Transactions on Industrial Electronics, 2015, 62(1): 494-502. doi: 10.1109/TIE.2014.2327555 URL
[5]	COSTA J A, HERO A O. Geodesic entropic graphs for dimension and entropy estimation in manifold learning[J]. IEEE Transactions on Signal Processing, 2004, 52(8): 2210-2221. doi: 10.1109/TSP.2004.831130 URL
[6]	ZHU J L, GE Z Q, SONG Z H. Distributed parallel PCA for modeling and monitoring of large-scale plant-wide processes with big data[J]. IEEE Transactions on Industrial Informatics, 2017, 13(4): 1877-1885. doi: 10.1109/TII.2017.2658732 URL
[7]	PENG K, ZHANG K, LI G. Online contribution rate based fault diagnosis for nonlinear industrial processes[J]. Acta Automatica Sinica, 2014, 40 (3): 423-430. doi: 10.1016/S1874-1029(14)60005-7 URL
[8]	张成, 郭青秀, 李元, 等. 基于主元分析得分重构差分的故障检测策略[J]. 控制理论与应用, 2019, 36(5): 774-782.
	ZHANG Cheng, GUO Qingxiu, LI Yuan, et al. Fault detection strategy based on difference of score reconstruction associated with principal component analysis[J]. Control Theory & Applications, 2019, 36(5): 774-782.
[9]	KU W, STORER R H, GEORGAKIS C. Disturbance detection and isolation by dynamic principal component analysis[J]. Chemometrics and Intelligent Laboratory Systems, 1995, 30(1): 179-196. doi: 10.1016/0169-7439(95)00076-3 URL
[10]	LI W, YUE H H, VALLE C S, et al. Recursive PCA for adaptive process monitoring[J]. Journal of Process Control, 2000, 10(5): 471-486. doi: 10.1016/S0959-1524(00)00022-6 URL
[11]	XIAO W, HUANG X, HE F, et al. Online robust principal component analysis with change point detection[J]. IEEE Transactions on Multimedia, 2020, 22(1): 59-68. doi: 10.1109/TMM.2019.2923097 URL
[12]	CHOI S W, LEE C, LEE J M, et al. Fault detection and identification of nonlinear processes based on kernel PCA[J]. Chemometrics & Intelligent Laboratory Systems, 2005, 75(1): 55-67.
[13]	刘春燕, 于春梅. 基于改进核主元分析的TE故障诊断[J]. 计算机测量与控制, 2016, 24 (10): 36-41.
	LIU Chunyan, YU Chunmei. TE fault diagnosis based on improved kernel principal component analysis[J]. Computer Measurement & Control, 2016, 24 (10): 36-41.
[14]	GUO J, QI L, LI Y. Fault detection of batch process using dynamic multi-way orthogonal locality preserving projections[J]. Journal of Computational Information Systems, 2015, 11(2): 577-586.
[15]	HE F, WANG C, FAN S K S. Nonlinear fault detection of batch processes based on functional kernel locality preserving projections[J]. Chemometrics and Intelligent Laboratory Systems, 2018, 183: 79-89. doi: 10.1016/j.chemolab.2018.10.010 URL
[16]	CHANG P, WANG P, GAO X J. Batch process monitoring for microbial fermentation based on multi-way kernel entropy component analysis[J]. Journal of Chemical Engineering of Chinese Universities, 2015, 29(2): 395-399.
[17]	YANG Y H, LI X L, LIU X Z, et al. Wavelet kernel entropy component analysis with application to industrial process monitoring[J]. Neurocomputing, 2015, 147(5): 395-402. doi: 10.1016/j.neucom.2014.06.045 URL
[18]	SANG W C, LEE I B. Nonlinear dynamic process monitoring based on dynamic kernel PCA[J]. Chemical Engineering Science, 2004, 59(24): 5897-5908. doi: 10.1016/j.ces.2004.07.019 URL
[19]	谢磊, 王树青. 递归核PCA及其在非线性过程自适应监控中的应用[J]. 化工学报, 2007, 58(7): 1776-1782.
	XIE Lei, WANG Shuqing. Recursive kernel PCA and its application in adaptive monitoring of nonlinear processes[J]. CIESC Journal, 2007, 58(7): 1776-1782.
[20]	LIU X, KRUGER U, LITTLER T, et al. Moving window kernel PCA for adaptive monitoring of nonlinear processes[J]. Chemometrics & Intelligent Laboratory Systems, 2009, 96(2): 132-143.
[21]	CHOUAIB C, MOHAMED-FAOUZI H, MESSAOUD D. New adaptive kernel principal component analysis for nonlinear dynamic process monitoring[J]. Applied Mathematics & Information Sciences, 2015, 9(4): 1833-1845.
[22]	FAZAI R, TAOUALI O, HARKAT M F, et al. A new fault detection method for nonlinear process monitoring[J]. International Journal of Advanced Manufacturing Technology, 2016, 87(9/10/11/12): 3425-3436. doi: 10.1007/s00170-016-8745-7 URL
[23]	YANG G, GU X. Fault diagnosis of complex chemical processes based on enhanced naive bayesian method[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(7): 4649-4658. doi: 10.1109/TIM.2019.2954151 URL
[24]	LEE J M, LEE I B, YOO C K. Fault detection of batch processes using multiway kernel principal component analysis[J]. Computers & Chemical Engineering, 2004, 28 (9): 1837-1840. doi: 10.1016/j.compchemeng.2004.02.036 URL
[25]	JAFFEL I, TAOUALI O, HARKAT M F, et al. Kernel principal component analysis with reduced complexity for nonlinear dynamic process monitoring[J]. International Journal of Advanced Manufacturing Technology, 2017, 88(9/10/11/12): 3265-3279. doi: 10.1007/s00170-016-8987-4 URL
[26]	HAMROUNI I, LAHDHIRI H, ABDELLAFOU K B, et al. Fault detection of uncertain nonlinear process using reduced interval kernel principal component analysis (RIKPCA)[J]. International Journal of Advanced Manufacturing Technology, 2020, 106(9/10): 4567-4576. doi: 10.1007/s00170-019-04889-3 URL
[27]	HONEINE P. Approximation errors of online sparsification criteria[J]. IEEE Transactions on Signal Process, 2015, 63 (17): 4700-4709. doi: 10.1109/TSP.2015.2442960 URL
[28]	ISSAM B K, MOHAMED L, CLAUS W. Variable window adaptive kernel principal component analysis for nonlinear nonstationary process monitoring[J]. Computers & Industrial Engineering, 2011, 61(3): 437-446. doi: 10.1016/j.cie.2011.02.014 URL
[29]	DOWNS J, VOGEL A. A plant wide industrial process control problem[J]. Computers & Chemical Engineering, 1993, 17(3): 245-255. doi: 10.1016/0098-1354(93)80018-I URL
[30]	郭金玉, 王哲, 李元. 基于核熵独立成分分析的故障检测方法[J]. 化工学报, 2022, 73(8): 3647-3658.
	GUO Jinyu, WANG Zhe, LI Yuan. Fault detection method based on kernel entropy independent component analysis[J]. CIESC Journal, 2022, 73(8): 3647-3658.
[31]	ZHONG K, HAN M, QIU T, et al. Fault diagnosis of complex processes using sparse kernel local fisher discriminant analysis[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(5): 1581-1591. doi: 10.1109/TNNLS.2019.2920903 pmid: 31265419
[32]	DENG X, TIAN X, CHEN S, et al. Nonlinear process fault diagnosis based on serial principal component analysis[J]. IEEE Transactions on Neural Networks & Learning Systems, 2018, 29(3): 560-572.
[33]	林茂, 李颖晖, 朱喜华, 等. 基于改进核主元分析法的三电平逆变器故障检测[J]. 电网技术, 2016, 40(3): 972-977.
	LIN Mao, LI Yinghui, ZHU Xihua, et al. Fault detection for three-level inverter based on improved kernel principal component analysis method[J]. Power System Technology, 2016, 40(3): 972-977.

检测指标	KPCA	压缩KPCA	递归KPCA	MWKPCA	VMWKPCA	ORKPCA
FAR/%	9.25	11.67	4.63	6.38	3.25	3.25
FDR/%	76.57	82.05	91.00	88.71	95.00	100.00
ET/s	3.35	0.27	9.35	5.04	12.13	2.97

变量	变量描述	变量	变量描述	变量	变量描述
1	A进料	19	汽提器上部蒸汽流量	37	流11中D
2	D进料	20	压缩机功率	38	流11中E
3	E进料	21	反应器冷却水出口温度	39	流11中F
4	总进料	22	分离器冷却水出口温度	40	流11中G
5	再循环流量	23	流6中A	41	流11中H
6	反应器进料速度	24	流6中B	42	D进料量
7	反应器压力	25	流6中C	43	E进料量
8	反应器等级	26	流6中D	44	A进料量
9	反应器温度	27	流6中E	45	总进料量
10	排放速度	28	流6中F	46	压缩机再循环阀
11	产品分离器温度	29	流9中A	47	排放阀
12	产品分离器液位	30	流9中B	48	分离器灌液流量
13	产品分离器压力	31	流9中C	49	汽提器液体产品流量
14	产品分离器塔底流量	32	流9中D	50	汽提器蒸汽阀
15	汽提器等级	33	流9中E	51	反应器冷却水流量
16	汽提器压力	34	流9中F	52	冷凝器冷却水流量
17	汽提器塔底流量	35	流9中G	53	搅拌速度
18	汽提器温度	36	流9中H

故障编号	故障描述	故障类型
2	组分B含量发生变化, A/C进料流量比保持不变	阶跃
20	未知	未知

检测指标	KPCA		压缩KPCA		递归KPCA		MWKPCA		VMWKPCA		ORKPCA
检测指标	故障2	故障20	故障2	故障20	故障2	故障20	故障2	故障20	故障2	故障20	故障2	故障20
FAR/%	3.75	0	8.25	0.63	0.63	2.50	1.25	4.38	1.88	3.75	0	3.75
FDR/%	98.38	38.63	95.88	39.38	98.75	88.00	97.65	85.13	98.75	96.38	98.75	97.13
ET/s	2.34	2.29	0.17	0.13	5.51	7.13	3.09	4.74	4.18	3.05	0.91	0.56