Performance monitoring of non-gaussian chemical processes with modes-switching using globality-locality preserving projection
Xin Peng, Yang Tang, Wenli Du(), Feng Qian()
Key Laboratory of Advanced Control and Optimization for Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai 200237, China
In this paper, we propose a novel performance monitoring and fault detection method, which is based on modified structure analysis and globality and locality preserving (MSAGL) projection, for non-Gaussian processes with multiple operation conditions. By using locality preserving projection to analyze the embedding geometrical manifold and extracting the non-Gaussian features by independent component analysis, MSAGL preserves both the global and local structures of the data simultaneously. Furthermore, the tradeoff parameter of MSAGL is tuned adaptively in order to find the projection direction optimal for revealing the hidden structural information. The validity and effectiveness of this approach are illustrated by applying the proposed technique to the Tennessee Eastman process simulation under multiple operation conditions. The results demonstrate the advantages of the proposed method over conventional eigendecomposition-based monitoring methods.
. [J]. Frontiers of Chemical Science and Engineering, 2017, 11(3): 429-439.
Xin Peng, Yang Tang, Wenli Du, Feng Qian. Performance monitoring of non-gaussian chemical processes with modes-switching using globality-locality preserving projection. Front. Chem. Sci. Eng., 2017, 11(3): 429-439.
Normal condition: sample 1?100, mode 3 Faulty condition: sample 101?200, mode 3 IDV5: step change in condenser cooling water temperature Normal condition: sample 201?300, mode 2 Faulty condition: sample 301?400, mode 2 IDV12: random variation in condenser cooling water inlet temperature
Case 2
Normal condition: sample 1?100, mode 2 Faulty condition: sample 101?200, mode 2 IDV11: random variation in reactor cooling water temperature Normal condition: sample 201?300, mode 1 Faulty condition: sample 301?400, mode 1 IDV6: step change in A feed loss (stream 1)
Case 3
Normal condition: sample 1?100, mode 1 Faulty condition: sample 101?200, mode 1 IDV11: reactor cooling water inlet temperature Normal condition: sample 201?300, mode 2 Faulty condition: sample 301?400, mode 2 IDV13: slow drift in reaction kinetics
Tab.1
Fig.4
Fig.5
Fig.6
Monitoring method
Case 1
Case 2
Case 3
PCA mixture model
58.3
79.8
68.2
LPP mixture model
61.9
76
73.7
MSAGL mixture model
93.8
91.7
92.5
Tab.2
Monitoring method
Case 1
Case 2
Case 3
PCA
38.1
17.6
36.7
LPP
18.2
10.4
16.9
MSAGL
0.6
4.0
6.1
Tab.3
1
Yin S, Shi P, Yang H . Adaptive fuzzy control of strict-feedback nonlinear time-delay systems with unmodeled dynamics. IEEE Transactions on Cybernetics, 2016, 46(8): 1926–1938 https://doi.org/10.1109/TCYB.2015.2457894
2
Yin S, Zhu X P, Qiu J B, Gao H J. State estimation in nonlinear system using sequential evolutionary filter. IEEE Transactions on Industrial Electronics, 2016, 63(6): 3786–3794 https://doi.org/10.1109/TIE.2016.2522382
3
Yin S, Gao H, Qiu J , Kaynak O . Descriptor reduced-order sliding mode observers design for switched systems with sensor and actuator faults. Automatica, 2017, 76: 282–292 https://doi.org/10.1016/j.automatica.2016.10.025
4
Tong C D, Shi X H. Decentralized monitoring of dynamic processes based on dynamic feature selection and informative fault pattern dissimilarity. IEEE Transactions on Industrial Electronics, 2016, 63(6): 3804–3814 https://doi.org/10.1109/TIE.2016.2530047
5
Stubbs S, Zhang J, Morris J . Fault detection in dynamic processes using a simplified monitoring-specific CVA state space modelling approach. Computers & Chemical Engineering, 2012, 41: 77–87 https://doi.org/10.1016/j.compchemeng.2012.02.009
6
Nomikos P, MacGregor J F. Monitoring batch processes using multiway principal component analysis. AIChE Journal, 1994, 40(8): 1361–1375 https://doi.org/10.1002/aic.690400809
7
Xiao Z B, Wang H G, Zhou J W. Robust dynamic process monitoring based on sparse representation preserving embedding. Journal of Process Control, 2016, 40: 119–133 https://doi.org/10.1016/j.jprocont.2016.01.009
8
Qin S J. Statistical process monitoring: Basics and beyond. Journal of Chemometrics, 2003, 17(8-9): 480–502 https://doi.org/10.1002/cem.800
9
Ge Z Q, Song Z H, Gao F R. Review of recent research on data-based process monitoring. Industrial & Engineering Chemistry Research, 2013, 52(10): 3543–3562 https://doi.org/10.1021/ie302069q
10
Dong D, McAvoy T J. Nonlinear principal component analysis — based on principal curves and neural networks. Computers & Chemical Engineering, 1996, 20(1): 65–78 https://doi.org/10.1016/0098-1354(95)00003-K
11
Antory D, Irwin G W, Kruger U, McCullough G . Improved process monitoring using nonlinear principal component models. International Journal of Intelligent Systems, 2008, 23(5): 520–544 https://doi.org/10.1002/int.20281
12
Silva R G. Condition monitoring of the cutting process using a self-organizing spiking neural network map. Journal of Intelligent Manufacturing, 2010, 21(6): 823–829 https://doi.org/10.1007/s10845-009-0258-x
13
Wang B, Yan X F, Jiang Q C. Independent component analysis model utilizing de-mixing information for improved non-Gaussian process monitoring. Computers & Industrial Engineering, 2016, 94: 188–200 https://doi.org/10.1016/j.cie.2016.01.021
14
Ge Z, Song Z. Process monitoring based on independent component analysis-principal component analysis (ICA-PCA) and similarity factors. Industrial & Engineering Chemistry Research, 2007, 46(7): 2054–2063 https://doi.org/10.1021/ie061083g
15
Choi S W, Lee I B. Nonlinear dynamic process monitoring based on dynamic kernel PCA. Chemical Engineering Science, 2004, 59(24): 5897–5908 https://doi.org/10.1016/j.ces.2004.07.019
16
Zhang Y W, An J Y, Zhang H L. Monitoring of time-varying processes using kernel independent component analysis. Chemical Engineering Science, 2013, 88: 23–32 https://doi.org/10.1016/j.ces.2012.11.008
17
Kano M, Tanaka S, Hasebe S , Hashimoto I , Ohno H. Monitoring independent components for fault detection. AIChE Journal, 2003, 49(4): 969–976 https://doi.org/10.1002/aic.690490414
18
Zhang Y, Zhang Y. Fault detection of non-Gaussian processes based on modified independent component analysis. Chemical Engineering Science, 2010, 65(16): 4630–4639 https://doi.org/10.1016/j.ces.2010.05.010
19
Ge Z Q, Xie L, Kruger U , Song Z H . Local ICA for multivariate statistical fault diagnosis in systems with unknown signal and error distributions. AIChE Journal, 2012, 58(8): 2357–2372 https://doi.org/10.1002/aic.12760
20
Hsu C C, Chen M C, Chen L S. A novel process monitoring approach with dynamic independent component analysis. Control Engineering Practice, 2010, 18(3): 242–253 https://doi.org/10.1016/j.conengprac.2009.11.002
21
Rashid M M, Yu J. A new dissimilarity method integrating multidimensional mutual information and independent component analysis for non-Gaussian dynamic process monitoring. Chemometrics and Intelligent Laboratory Systems, 2012, 115: 44–58 https://doi.org/10.1016/j.chemolab.2012.04.008
22
Costa J, Hero A O. Geodesic entropic graphs for dimension and entropy estimation in manifold learning. Signal Processing. IEEE Transactions on, 2004, 52(8): 2210–2221 https://doi.org/10.1109/TSP.2004.831130
23
Lin T, Zha H. Riemannian manifold learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(5): 796–809 https://doi.org/10.1109/TPAMI.2007.70735
24
Tenenbaum J B , de Silva V , Langford J C . A global geometric framework for nonlinear dimensionality reduction. Science, 2000, 290(5500): 2319–2323 https://doi.org/10.1126/science.290.5500.2319
Zhang Z Y, Zha H Y. Principal manifolds and nonlinear dimensionality reduction via tangent space alignment. SIAM Journal on Scientific Computing, 2004, 26(1): 313–338 https://doi.org/10.1137/S1064827502419154
27
He X, Niyogi P. Locality preserving projections. In: Proceedings of the Neural Information Processing Systems. Neural Information Processing Systems Foundation. Cambridge: MIT Press, 2004, 153
28
Luo L. Process monitoring with global-local preserving projections. Industrial & Engineering Chemistry Research, 2014, 53(18): 7696–7705 https://doi.org/10.1021/ie4039345
29
Yu J, Qin S J. Multimode process monitoring with Bayesian inference-based finite Gaussian mixture models. AIChE Journal, 2008, 54(7): 1811–1829 https://doi.org/10.1002/aic.11515
30
Fan M, Ge Z Q, Song Z H. Adaptive Gaussian mixture model-based relevant sample selection for JITL soft sensor development. Industrial & Engineering Chemistry Research, 2014, 53(51): 19979–19986 https://doi.org/10.1021/ie5029864
31
Yu J. A nonlinear kernel Gaussian mixture model based inferential monitoring approach for fault detection and diagnosis of chemical processes. Chemical Engineering Science, 2012, 68(1): 506–519 https://doi.org/10.1016/j.ces.2011.10.011
32
Wen Q, Ge Z, Song Z . Data-based linear Gaussian state-space model for dynamic process monitoring. AIChE Journal, 2012, 58(12): 3763–3776 https://doi.org/10.1002/aic.13776
33
Ge Z, Kruger U, Lamont L , Xie L, Song Z. Fault detection in non-Gaussian vibration systems using dynamic statistical-based approaches. Mechanical Systems and Signal Processing, 2010, 24(8): 2972–2984 https://doi.org/10.1016/j.ymssp.2010.03.015
Zhang M G, Ge Z Q, Song Z H, Fu R W. Global-local structure analysis model and its application for fault detection and identification. Industrial & Engineering Chemistry Research, 2011, 50(11): 6837–6848 https://doi.org/10.1021/ie102564d
36
Figueiredo M A T , Jain A K . Unsupervised learning of finite mixture models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(3): 381–396 https://doi.org/10.1109/34.990138
37
Te-Won L, Lewicki M S, Sejnowski T J. ICA mixture models for unsupervised classification of non-Gaussian classes and automatic context switching in blind signal separation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(10): 1078–1089 https://doi.org/10.1109/34.879789
Lee J M, Qin S J, Lee I B. Fault detection and diagnosis based on modified independent component analysis. AIChE Journal, 2006, 52(10): 3501–3514 https://doi.org/10.1002/aic.10978