Adaptive partitioning PCA model for improving fault detection and isolation

doi:10.1016/j.cjche.2014.09.052

Chin.J.Chem.Eng. ›› 2015, Vol. 23 ›› Issue (6): 981-991.DOI: 10.1016/j.cjche.2014.09.052

• PROCESS SYSTEMS ENGINEERING AND PROCESS SAFETY • Previous Articles Next Articles

Adaptive partitioning PCA model for improving fault detection and isolation

Kangling Liu¹, Xin Jin¹, Zhengshun Fei², Jun Liang¹

1 State Key Lab of Industrial Control Technology, Institute of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China;
2 School of Automation and Electrical Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, China

Received:2014-04-25 Revised:2014-09-05 Online:2015-07-09 Published:2015-06-28
Contact: Jun Liang
Supported by:
Support by theNational Natural Science Foundation of China (61174114), the Research Fund for the Doctoral Program of Higher Education in China (20120101130016) and Zhejiang Provincial Science and Technology Planning Projects of China (2014C31019).

Adaptive partitioning PCA model for improving fault detection and isolation

Kangling Liu¹, Xin Jin¹, Zhengshun Fei², Jun Liang¹

1 State Key Lab of Industrial Control Technology, Institute of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China;
2 School of Automation and Electrical Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, China

通讯作者: Jun Liang
基金资助:
Support by theNational Natural Science Foundation of China (61174114), the Research Fund for the Doctoral Program of Higher Education in China (20120101130016) and Zhejiang Provincial Science and Technology Planning Projects of China (2014C31019).

Abstract

Abstract: In chemical process, a large number of measured andmanipulated variables are highly correlated. Principal component analysis (PCA) iswidely applied as a dimension reduction technique for capturing strong correlation underlying in the process measurements. However, it is difficult for PCA based fault detection results to be interpreted physically and to provide support for isolation. Some approaches incorporating process knowledge are developed, but the information is always shortage and deficient in practice. Therefore, this work proposes an adaptive partitioning PCA algorithm entirely based on operation data. The process feature space is partitioned into several sub-feature spaces. Constructed sub-block models can not only reflect the local behavior of process change, namely to grasp the intrinsic local information underlying the process changes, but also improve the fault detection and isolation through the combination of local fault detection results and reduction of smearing effect. The method is demonstrated in TE process, and the results show that the new method is much better in fault detection and isolation compared to conventional PCA method.

Key words: Adaptive partitioning, Fault detection, Fault isolation, Principal component analysis

摘要： In chemical process, a large number of measured andmanipulated variables are highly correlated. Principal component analysis (PCA) iswidely applied as a dimension reduction technique for capturing strong correlation underlying in the process measurements. However, it is difficult for PCA based fault detection results to be interpreted physically and to provide support for isolation. Some approaches incorporating process knowledge are developed, but the information is always shortage and deficient in practice. Therefore, this work proposes an adaptive partitioning PCA algorithm entirely based on operation data. The process feature space is partitioned into several sub-feature spaces. Constructed sub-block models can not only reflect the local behavior of process change, namely to grasp the intrinsic local information underlying the process changes, but also improve the fault detection and isolation through the combination of local fault detection results and reduction of smearing effect. The method is demonstrated in TE process, and the results show that the new method is much better in fault detection and isolation compared to conventional PCA method.

关键词: Adaptive partitioning, Fault detection, Fault isolation, Principal component analysis

Kangling Liu, Xin Jin, Zhengshun Fei, Jun Liang. Adaptive partitioning PCA model for improving fault detection and isolation[J]. Chin.J.Chem.Eng., 2015, 23(6): 981-991.

Kangling Liu, Xin Jin, Zhengshun Fei, Jun Liang. Adaptive partitioning PCA model for improving fault detection and isolation[J]. Chinese Journal of Chemical Engineering, 2015, 23(6): 981-991.

References

[1] J. Liang, J. Qian, Multivariate statistical process monitoring and control: Recent developments and applications to chemical industry, Chin. J. Chem. Eng. 11 (2) (2003) 191-203.

[2] L. Wang, H. Shi, Improved kernel PLS-based fault detection approach for nonlinear chemical processes, Chin. J. Chem. Eng. 22 (6) (2014) 657-663.

[3] W. Dong, Y. Yao, F. Gao, Phase analysis and identification method for multiphase batch processes with partitioning multi-way principal component analysis (MPCA) Model, Chin. J. Chem. Eng. 20 (6) (2012) 1121-1127.

[4] S. Bezergianni, A. Kalogianni, Application of principal component analysis for monitoring and disturbance detection of a hydrotreating process, Ind. Eng. Chem. Res. 47 (18) (2008) 6972-6982.

[5] P.V.D. Kerkhof, J. Vanlaer, G. Gins, J.F. Van Impe, Analysis of smearing-out in contribution plot based fault isolation for Statistical Process Control, Chem. Eng. Sci. 104 (2013) (2013) 285-293.

[6] H. Zou, T. Hastie, Regularization and variable selection via the elastic net, J. R. Stat. Soc. Ser. B (Stat. Methodol.) 67 (2) (2005) 301-320.

[7] L. Xie, X. Lin, J. Zeng, Shrinking principal component analysis for enhanced process monitoring and fault isolation, Ind. Eng. Chem. Res. 52 (49) (2013) 17475-17486.

[8] S.J. Qin, S. Valle, M.J. Piovoso, On unifying multiblock analysis with application to decentralized process monitoring, J. Chemom. 15 (9) (2001) 715-742.

[9] J.J. Hong, J. Zhang, J. Morris, Progressive multi-block modelling for enhanced fault isolation in batch processes, J. Process Control 24 (1) (2014) 13-26.

[10] C. Tong, Y. Song, X. Yan, Distributed statistical process monitoring based on foursubspace construction and Bayesian inference, Ind. Eng. Chem. Res. 52 (29) (2013) 9897-9907.

[11] B.Wang, Q. Jiang, X. Yan, Fault detection and identification using a Kullback-Leibler divergence based multi-block principal component analysis and Bayesian inference, Korean J. Chem. Eng. (2014) 1-14.

[12] Z. Lv, Q. Jiang, X. Yan, Batch process monitoring based on multisubspace multiway principal component analysis and time-series Bayesian inference, Ind. Eng. Chem. Res. 53 (15) (2014) 6457-6466.

[13] C.-c. Huang, T. Chen, Y. Yao, Mixture discriminant monitoring: A hybrid method for statistical process monitoring and fault diagnosis/isolation, Ind. Eng. Chem. Res. 52 (31) (2013) 10720-10731.

[14] D.S. Lee, J.M. Park, P.A. Vanrolleghem, Adaptive multiscale principal component analysis for on-line monitoring of a sequencing batch reactor, J. Biotechnol. 116 (2) (2005) 195-210.

[15] C. Zhao, Y. Sun, Comprehensive subspace decomposition and isolation of principal reconstruction directions for online fault diagnosis, J. Process Control 23 (10) (2013) 1515-1527.

[16] P. Sedgwick, Pearson's correlation coefficient, BMJ 345 (2012).

[17] N.D. Tracy, J.C. Young, R.L. Mason, Multivariate control charts for individual observations, J. Qual. Technol. 24 (2) (1992) 88-95.

[18] P. Nomikos, J.F. Macgregor, Multivariate SPC charts for monitoring batch processes, Technometrics 37 (1) (1995) 41-59.

[19] C.F. Alcala, S.J. Qin, Reconstruction-based contribution for process monitoring, Automatica 45 (7) (2009) 1593-1600.

[20] J.J. Downs, E.F. Vogel, A plant-wide industrial process control problem, Comput. Chem. Eng. 17 (245) (1993).

[21] P.R. Lyman, C. Georgakis, Plant-wide control of the Tennessee Eastman problem, Comput. Chem. Eng. 19 (3) (1995) 321-331.

Adaptive partitioning PCA model for improving fault detection and isolation

Adaptive partitioning PCA model for improving fault detection and isolation

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Xiongzhuo Zhu, Dali Gao, Chong Yang, Chunjie Yang. A blast furnace fault monitoring algorithm with low false alarm rate: Ensemble of greedy dynamic principal component analysis-Gaussian mixture model [J]. Chinese Journal of Chemical Engineering, 2023, 57(5): 151-161.
[2]	Fangyuan Ma, Cheng Ji, Jingde Wang, Wei Sun. Early identification of process deviation based on convolutional neural network [J]. Chinese Journal of Chemical Engineering, 2023, 56(4): 104-118.
[3]	Yiming Bai, Shuaiyu Xiang, Feifan Cheng, Jinsong Zhao. A dynamic-inner LSTM prediction method for key alarm variables forecasting in chemical process [J]. Chinese Journal of Chemical Engineering, 2023, 55(3): 266-276.
[4]	Jiaxin Zhang, Wenjia Luo, Yiyang Dai, Yuman Yao. Cycle temporal algorithm-based multivariate statistical methods for fault diagnosis in chemical processes [J]. Chinese Journal of Chemical Engineering, 2022, 47(7): 54-70.
[5]	Yuan Li, Dongsheng Yang. Local component based principal component analysis model for multimode process monitoring [J]. Chinese Journal of Chemical Engineering, 2021, 34(6): 116-124.
[6]	Muhammad Nawaz, Abdulhalim Shah Maulud, Haslinda Zabiri, Syed Ali Ammar Taqvi, Alamin Idris. Improved process monitoring using the CUSUM and EWMA-based multiscale PCA fault detection framework [J]. Chinese Journal of Chemical Engineering, 2021, 29(1): 253-265.
[7]	Cen Guo, Wenkai Hu, Fan Yang, Dexian Huang. Deep learning technique for process fault detection and diagnosis in the presence of incomplete data [J]. Chinese Journal of Chemical Engineering, 2020, 28(9): 2358-2367.
[8]	Liangliang Sun, Jianghua Wu, Haiqi Jia, Xuebin Liu. Research on fault detection method for heat pump air conditioning system under cold weather [J]. Chin.J.Chem.Eng., 2017, 25(12): 1812-1819.
[9]	Fan Wang, Honglin Zhu, Shuai Tan, Hongbo Shi. Orthogonal nonnegative matrix factorization based local hidden Markov model for multimode process monitoring [J]. , 2016, 24(7): 856-860.
[10]	Guozhu Wang, Jianchang Liu, Yuan Li, Cheng Zhang. Fault diagnosis of chemical processes based on partitioning PCA and variable reasoning strategy [J]. , 2016, 24(7): 869-880.
[11]	Zhengshun Fei, Kangling Liu. Online process monitoring for complex systems with dynamic weighted principal component analysis [J]. Chin.J.Chem.Eng., 2016, 24(6): 775-786.
[12]	Yuan Xu, Ying Liu, Qunxiong Zhu. Multivariate time delay analysis based local KPCA fault prognosis approach for nonlinear processes [J]. , 2016, 24(10): 1413-1422.
[13]	Yawei Yang, Yuxin Ma, Bing Song, Hongbo Shi. An aligned mixture probabilistic principal component analysis for fault detection of multimode chemical processes [J]. Chin.J.Chem.Eng., 2015, 23(8): 1357-1363.
[14]	Bing Song, Yuxin Ma, Hongbo Shi. Improved performance of process monitoring based on selection of key principal components [J]. Chin.J.Chem.Eng., 2015, 23(12): 1951-1957.
[15]	Shijin Ren, Zhihuan Song, Maoyun Yang, Jianguo Ren . A novel multimode processmonitoring method integrating LCGMMwith modified LFDA [J]. Chin.J.Chem.Eng., 2015, 23(12): 1970-1980.