Fault detection based on orthogonal local slow features

doi:10.16511/j.cnki.qhdxxb.2020.25.026

Download: PDF(1270 KB)
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract A local time-space regularized slow feature extraction method was developed to improve data-driven fault detection in the chemical industry based on the process dynamics of closed-loop control systems and the local information contained in the data manifold. An objective function was defined based on the local time-space term to obtain a projection matrix and the pre-extraction feature, S. The span of S contains the static information, while the first derivative of the span of S contains the dynamic information. An independent component analysis was used to obtain statistics for S² and SPE for both spaces for real-time fault detection. A case study on the Tennessee Eastman process shows the validity of this method.

Keywords fault detection process dynamics local similarity slow feature independent component analysis (ICA) Tennessee Eastman (TE) process

Issue Date: 17 June 2020

	Service

	E-mail this article
	E-mail Alert
	RSS
	Articles by authors

	ZHANG Zhanbo
	WANG Zhenlei
	WANG Xin

Cite this article:

ZHANG Zhanbo,WANG Zhenlei,WANG Xin. Fault detection based on orthogonal local slow features[J]. Journal of Tsinghua University(Science and Technology), 2020, 60(8): 693-700.

URL:

http://jst.tsinghuajournals.com/EN/10.16511/j.cnki.qhdxxb.2020.25.026 OR http://jst.tsinghuajournals.com/EN/Y2020/V60/I8/693

[1] DENG X G, TIAN X M, CHEN S, et al. Nonlinear process fault diagnosis based on serial principal component analysis[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(3):560-572.
[2] YIN S, XIE X C, SUN W. A nonlinear process monitoring approach with locally weighted learning of available data[J]. IEEE Transactions on Industrial Electronics, 2017, 64(2):1507-1516.
[3] YIN S, ZHU X P, KAYNAK O. Improved PLS focused on key-performance-indicator-related fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2015, 62(3):1651-1658.
[4] CAI L F, TIAN X M, CHEN S. Monitoring nonlinear and non-Gaussian processes using Gaussian mixture model-based weighted kernel independent component analysis[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(1):122-135.
[5] CHEN H T, JIANG B, LU N Y, et al. Deep PCA based real-time incipient fault detection and diagnosis methodology for electrical drive in high-speed trains[J]. IEEE Transactions on Vehicular Technology, 2018, 67(6):4819-4830.
[6] LI W H, QIN S J. Consistent dynamic PCA based on errors-in-variables subspace identification[J]. Journal of Process Control, 2001, 11(6):661-678.
[7] LI G, LIU B S, QIN S J, et al. Dynamic latent variable modeling for statistical process monitoring[J]. IFAC Proceedings Volumes, 2011, 44(11):12886-12891.
[8] ZHAO H T. Dynamic graph embedding for fault detection[J]. Computers & Chemical Engineering, 2018, 117(2):359-371.
[9] DENG X G, TIAN X M, HU X Y. Nonlinear process fault diagnosis based on slow feature analysis[C]//Proceedings of the 10th World Congress on Intelligent Control and Automation. Beijing, China:IEEE, 2012:3152-3156.
[10] TURNER R, SAHANI M. A maximum-likelihood interpretation for slow feature analysis[J]. Neural Computation, 2007, 19(4):1022-1038.
[11] GUO F H, SHANG C, HUANG B, et al. Monitoring of operating point and process dynamics via probabilistic slow feature analysis[J]. Chemometrics and Intelligent Laboratory Systems, 2016, 151(15):115-125.
[12] GU S M, LIU Y L, ZHANG N. Fault diagnosis in Tennessee Eastman process using slow feature principal component analysis[J]. Recent Innovations in Chemical Engineering, 2016, 9(1):49-61.
[13] ROWEIS S T, SAUL L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000, 290(5500):2323-2326.
[14] HE X F, NIYOGI P. Locality preserving projections[J]. Advances in Neural Information Processing Systems, 2003, 16(1):186-197.
[15] HE X F, CAI D, YAN S C, et al. Neighborhood preserving embedding[C]//Tenth IEEE International Conference on Computer Vision. Beijing, China:IEEE, 2005:1208-1213.
[16] MIAO A M, GE Z Q, SONG Z H, et al. Time neighborhood preserving embedding model and its application for fault detection[J]. Industrial & Engineering Chemistry Research, 2013, 52(38):13717-13729.
[17] TONG C D, LAN T, SHI X H, et al. Statistical process monitoring based on nonlocal and multiple neighborhoods preserving embedding model[J]. Journal of Process Control, 2018, 65:34-40.
[18] SPREKELER H. On the relation of slow feature analysis and Laplacian eigenmaps[J]. Neural Computation, 2011, 23(12):3287-3302.
[19] CAI D, HE X F, HAN J W, et al. Orthogonal laplacianfaces for face recognition[J]. IEEE Transactions on Image Processing, 2006, 15(11):3608-3614.
[20] BOTEV Z I, GROTOWSKI J F, KROESE D P. Kernel density estimation via diffusion[J]. The Annals of Statistics, 2010, 38(5):2916-2957.
[21] LYMAN P R, GEORGAKIS C. Plant-wide control of the Tennessee Eastman problem[J]. Computers & Chemical Engineering, 1995, 19(3):321-331.
[22] DU Y C, DU D P. Fault detection and diagnosis using empirical mode decomposition based principal component analysis[J]. Computers & Chemical Engineering, 2018, 115(12):1-21.