基于海林格距离加权关键主元的流程工业故障检测研究

doi:10.13543/j.bhxbzr.2022.03.013

PDF(4842 KB)

北京化工大学学报（自然科学版） ›› 2022, Vol. 49 ›› Issue (3) : 91-101. DOI: 10.13543/j.bhxbzr.2022.03.013

机电工程和信息科学

基于海林格距离加权关键主元的流程工业故障检测研究

赵成, 苏圣超

作者信息 +

A fault detection method based on Hellinger distance-weighted key principal components for the process industry

ZHAO Cheng, SU ShengChao

Author information +

文章历史 +

摘要

在采用主成分分析（principal component analysis，PCA）算法进行故障检测时，主元的选取及处理直接影响其故障检测的表现。对此，提出一种基于全变量表达（full variable expression，FVE）和海林格距离（Hellinger distance，HD）的故障检测方法。首先，利用FVE得到所有关键主元，即保留所有变量信息；然后考虑到与故障相关主元的重要性，定义基于海林格距离的变化率，用来衡量正常工况下主元与异常工况下主元的差异；对与故障发生更相关的主元进行加权，以突出与故障相关主元对于后续故障检测的影响；最后，考虑到降维后数据通常服从非高斯分布，利用改进的局部离群因子（local outlier factor，LOF）构建统计量，其相应控制限通过核密度估计（kernel density estimation，KDE）确定。数值实例及带钢热连轧实际生产数据验证了所提方法的有效性与优越性。

Abstract

When a principal components analysis (PCA) algorithm is used for fault detection, the selection of principal components and how to manage them directly affects the efficacy of fault detection. A new fault detection method based on full variable expression(FVE) and Hellinger distance(HD) is proposed in this work. All the key principal components are first obtained by FVE, and all the variable information is retained. The change rate based on Hellinger distance is then defined, considering the importance of fault-relevant principal components. This is used to measure the difference between the principal components under normal operation and abnormal operation. The principal components which are more relevant to the occurrence of faults are weighted in order to highlight the effect of fault-relevant principal components in subsequent fault detection. Finally, considering that the dimensionality reduction data often follow a non-Gaussian distribution, the improved local outlier factor (LOF) is used to construct the statistics and the corresponding control limit is determined by kernel density estimation(KDE). Finally, a numerical case and the actual data for a hot strip mill process have been used to verify the effectiveness and superiority of the proposed method in fault detection.

导出引用

赵成, 苏圣超. 基于海林格距离加权关键主元的流程工业故障检测研究[J]. 北京化工大学学报（自然科学版）, 2022, 49(3): 91-101 https://doi.org/10.13543/j.bhxbzr.2022.03.013

ZHAO Cheng, SU ShengChao. A fault detection method based on Hellinger distance-weighted key principal components for the process industry[J]. Journal of Beijing University of Chemical Technology, 2022, 49(3): 91-101 https://doi.org/10.13543/j.bhxbzr.2022.03.013

参考文献

[1] CHEN H T, JIANG B, DING S X, et al. Data-driven fault diagnosis for traction systems in high-speed trains:a survey, challenges, and perspectives[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(3):1700-1716.
[2] YIN S, DING S X, XIE X C, et al. A review on basic data-driven approaches for industrial process monitoring[J]. IEEE Transactions on Industrial Electronics, 2014, 61(11):6418-6428.
[3] QU L, LI L, ZHANG Y, et al. PPCA-based missing data imputation for traffic flow volume:a systematical approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2009, 10(3):512-522.
[4] LUO K W, LI S L, DENG R, et al. Multivariate statistical kernel PCA for nonlinear process fault diagnosis in military barracks[J]. International Journal of Hybrid Information Technology, 2016, 9(1):195-206.
[5] KU W F, 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.
[6] MALINOWSKI E R. Factor analysis in chemistry[M]. 2nd ed. New York:Wiley & Sons. Inc., 1991.
[7] VALLE S, LI W H, QIN S J. Selection of the number of principal components:the variance of the reconstruction error criterion with a comparison to other methods[J]. Industrial & Engineering Chemistry Research, 1999, 38(11):4389-4401.
[8] KAISER H F. The application of electronic computers to factor analysis[J]. Educational and Psychological Measurement, 1960, 20(1):141-151.
[9] JOLLIFFE I T. A note on the use of principal components in regression[J]. Applied Statistics, 1982, 31(3):300-303.
[10] TOGKALIDOU T, BRAATZ R D, JOHNSON B K, et al. Experimental design and inferential modeling in pharmaceutical crystallization[J]. AIChE Journal, 2001, 47(1):160-168.
[11] TAO Y, WANG F, SHI H B, et al. Principal component selection algorithm based on ReliefF and its application in process monitoring[J]. CIESC Journal, 2017, 68(4):1525-1532. (in Chinese) 陶阳, 王帆, 侍洪波, 等. 基于ReliefF的主元挑选算法在过程监控中的应用[J]. 化工学报, 2017, 68(4):1525-1532.
[12] JIANG Q C, YAN X F, ZHAO W X. Fault detection and diagnosis in chemical processes using sensitive principal component analysis[J]. Industrial & Engineering Chemistry Research, 2013, 52(4):1635-1644.
[13] CANG W T, YANG H Z. A process monitoring method based on informative principal component subspace reconstruction[J]. CIESC Journal, 2018, 69(3):1114-1120. (in Chinese) 仓文涛, 杨慧中. 基于主元子空间富信息重构的过程监测方法[J]. 化工学报, 2018, 69(3):1114-1120.
[14] SONG B, MA Y Y, SHI H B. Improved performance of process monitoring based on selection of key principal components[J]. Chinese Journal of Chemical Engineering, 2015, 23(12):1951-1957.
[15] JIANG Q C, WANG B, YAN X F. Multiblock independent component analysis integrated with Hellinger distance and Bayesian inference for non-Gaussian plant-wide process monitoring[J]. Industrial & Engineering Chemistry Research, 2015, 54(9):2497-2508.
[16] HARROU F, MADAKYARU M, SUN Y. Improved nonlinear fault detection strategy based on the Hellinger distance metric:plug flow reactor monitoring[J]. Energy and Buildings, 2017, 143:149-161.
[17] CHEN H T, JIANG B, LU N Y. A newly robust fault detection and diagnosis method for high-speed trains[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(6):2198-2208.
[18] BREUNIG M M, KRIEGEL H P, NG R T, et al. LOF:identifying density-based local outliers[C]//ACM Sigmod International Conference on Management of Data. Dallas, 2000:93-104.
[19] LEE J, KANG B, KANG S H. Integrating independent component analysis and local outlier factor for plant-wide process monitoring[J]. Journal of Process Control, 2011, 21(7):1011-1021.
[20] DENG X G, WANG L. Modified kernel principal component analysis using double-weighted local outlier factor and its application to nonlinear process monitoring[J]. ISA Transactions, 2018, 72:218-228.
[21] FENG L W, LI Y, ZHANG C, et al. Time-space neighborhood standardization-local outlier factor based fault detection for complex process[J]. Control Theory and Applications, 2020, 37(3):651-657. (in Chinese) 冯立伟, 李元, 张成, 等. 基于时空近邻标准化和局部离群因子的复杂过程故障检测[J]. 控制理论与应用, 2020, 37(3):651-657.
[22] QIN S J. Statistical process monitoring:basics and beyond[J]. Journal of Chemometrics, 2003, 17:480-502.
[23] BASSEVILLE M. Divergence measures for statistical data processing-an annotated bibliography[J]. Signal Processing, 2013, 93(4):621-633.
[24] DITZLER G, POLIKAR R. Hellinger distance based drift detection for nonstationary environments[C]//2011 IEEE Symposium on Computational Intelligence in Dynamic and Uncertain Environments (CIDUE). Paris, 2011:41-48.
[25] LI C, HUANG B, QIAN F. Hellinger distance based probability distribution approach to performance monitoring of nonlinear control systems[J]. Chinese Journal of Chemical Engineering, 2015, 23(12):1945-1950.
[26] TONG W. On the establishment of Lebesgue's measure[J]. Bulletin des Sciences Mathematics, 1988(3):38-41. (in Chinese) 童武. 谈谈Lebesgue测度概念的建立[J]. 数学通报, 1988(3):38-41.
[27] MA H H, HU Y, SHI H B. A novel local neighborhood standardization strategy and its application in fault detection of multimode processe[J]. Chemometrics and Intelligent Laboratory Systems, 2012, 118(1):287-300.
[28] ZHANG K, DING S X, SHARDT Y A W, et al. Assessment of T2-and Q-statistics for detecting additive and multiplicative faults in multivariate statistical process monitoring[J]. Journal of the Franklin Institute, 2017, 354(2):668-688.
[29] HAN M, ZHANG Z K. Fault detection method based on weighted kernel independent component analysis[J]. Control and Decision, 2016, 31(2):242-248. (in Chinese) 韩敏, 张占奎. 基于加权核独立成分分析的故障检测方法[J]. 控制与决策, 2016, 31(2):242-248.
[30] LEE J M, YOO C K, LEE I B. Statistical process monitoring with independent component analysis[J]. Journal of Process Control, 2004, 14(5):467-485.
[31] JIANG Q C, YAN X F, HUANG B. Performance-driven distributed PCA process monitoring based on fault-relevant variable selection and Bayesian inference[J]. IEEE Transactions on Industrial Electronics, 2016, 63(1):377-386.
[32] GU B B, XIONG W L, SHI X D. Multi-block PCA process monitoring based on fault sensitive principal components[J]. Journal of Chemical Engineering of Chinese Universities, 2019, 33(6):1499-1508. (in Chinese) 顾炳斌, 熊伟丽, 史旭东. 基于故障敏感主元的多块PCA故障监测方法[J]. 高校化学工程学报, 2019, 33(6):1499-1508.

基金

国家自然科学基金（61603241）；上海工业控制系统安全创新功能型平台开放课题项目（TICPSH202103003-ZC）

PDF(4842 KB)

1155

Accesses

Citation

Detail

段落导航

摘要
Abstract
关键词
Key words
引用本文
参考文献
基金

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

{{custom_fnGroup.title_cn}}

脚注

基金

联系我们

收稿日期
2021-10-21
发布日期
2022-06-24

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

{{custom_fnGroup.title_cn}}

脚注

基金

联系我们