Performance monitoring of non-gaussian chemical processes with modes-switching using globality-locality preserving projection

Xin Peng , Yang Tang , Wenli Du , Feng Qian

Front. Chem. Sci. Eng. ›› 2017, Vol. 11 ›› Issue (3) : 429 -439.

PDF (531KB)
Front. Chem. Sci. Eng. ›› 2017, Vol. 11 ›› Issue (3) : 429 -439. DOI: 10.1007/s11705-017-1675-6
RESEARCH ARTICLE
RESEARCH ARTICLE

Performance monitoring of non-gaussian chemical processes with modes-switching using globality-locality preserving projection

Author information +
History +
PDF (531KB)

Abstract

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.

Keywords

non-Gaussian processes / subspace projection / independent component analysis / locality preserving projection / finite mixture model

Cite this article

Download citation ▾
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 DOI:10.1007/s11705-017-1675-6

登录浏览全文

4963

注册一个新账户 忘记密码

References

[1]

Yin SShi  PYang H . Adaptive fuzzy control of strict-feedback nonlinear time-delay systems with unmodeled dynamics. IEEE Transactions on Cybernetics201646(8): 1926–1938

[2]

Yin SZhu  X PQiu  J BGao  H J. State estimation in nonlinear system using sequential evolutionary filter. IEEE Transactions on Industrial Electronics201663(6): 3786–3794

[3]

Yin SGao  HQiu J Kaynak O . Descriptor reduced-order sliding mode observers design for switched systems with sensor and actuator faults. Automatica201776: 282–292

[4]

Tong C DShi  X H. Decentralized monitoring of dynamic processes based on dynamic feature selection and informative fault pattern dissimilarity. IEEE Transactions on Industrial Electronics201663(6): 3804–3814

[5]

Stubbs SZhang  JMorris J . Fault detection in dynamic processes using a simplified monitoring-specific CVA state space modelling approach. Computers & Chemical Engineering201241: 77–87

[6]

Nomikos PMacGregor  J F. Monitoring batch processes using multiway principal component analysis. AIChE Journal199440(8): 1361–1375

[7]

Xiao Z BWang  H GZhou  J W. Robust dynamic process monitoring based on sparse representation preserving embedding. Journal of Process Control201640: 119–133

[8]

Qin S J. Statistical process monitoring: Basics and beyond. Journal of Chemometrics200317(8-9): 480–502

[9]

Ge Z QSong  Z HGao  F R. Review of recent research on data-based process monitoring. Industrial & Engineering Chemistry Research201352(10): 3543–3562

[10]

Dong DMcAvoy  T J. Nonlinear principal component analysis — based on principal curves and neural networks. Computers & Chemical Engineering199620(1): 65–78

[11]

Antory DIrwin  G WKruger  UMcCullough G . Improved process monitoring using nonlinear principal component models. International Journal of Intelligent Systems200823(5): 520–544

[12]

Silva R G. Condition monitoring of the cutting process using a self-organizing spiking neural network map. Journal of Intelligent Manufacturing201021(6): 823–829

[13]

Wang BYan  X FJiang  Q C. Independent component analysis model utilizing de-mixing information for improved non-Gaussian process monitoring. Computers & Industrial Engineering201694: 188–200

[14]

Ge ZSong  Z. Process monitoring based on independent component analysis-principal component analysis (ICA-PCA) and similarity factors. Industrial & Engineering Chemistry Research200746(7): 2054–2063

[15]

Choi S WLee  I B. Nonlinear dynamic process monitoring based on dynamic kernel PCA. Chemical Engineering Science200459(24): 5897–5908

[16]

Zhang Y WAn  J YZhang  H L. Monitoring of time-varying processes using kernel independent component analysis. Chemical Engineering Science201388: 23–32

[17]

Kano MTanaka  SHasebe S Hashimoto I Ohno H. Monitoring independent components for fault detection. AIChE Journal200349(4): 969–976

[18]

Zhang YZhang  Y. Fault detection of non-Gaussian processes based on modified independent component analysis. Chemical Engineering Science201065(16): 4630–4639

[19]

Ge Z QXie  LKruger U Song Z H . Local ICA for multivariate statistical fault diagnosis in systems with unknown signal and error distributions. AIChE Journal201258(8): 2357–2372

[20]

Hsu C CChen  M CChen  L S. A novel process monitoring approach with dynamic independent component analysis. Control Engineering Practice201018(3): 242–253

[21]

Rashid M MYu  J. A new dissimilarity method integrating multidimensional mutual information and independent component analysis for non-Gaussian dynamic process monitoring. Chemometrics and Intelligent Laboratory Systems2012115: 44–58

[22]

Costa JHero  A O. Geodesic entropic graphs for dimension and entropy estimation in manifold learning. Signal Processing. IEEE Transactions on200452(8): 2210–2221

[23]

Lin TZha  H. Riemannian manifold learning. IEEE Transactions on Pattern Analysis and Machine Intelligence200830(5): 796–809

[24]

Tenenbaum J B de Silva V Langford J C . A global geometric framework for nonlinear dimensionality reduction. Science2000290(5500): 2319–2323

[25]

Roweis S TSaul  L K. Nonlinear dimensionality reduction by locally linear embedding. Science2000290(5500): 2323–2326

[26]

Zhang Z YZha  H Y. Principal manifolds and nonlinear dimensionality reduction via tangent space alignment. SIAM Journal on Scientific Computing200426(1): 313–338

[27]

He XNiyogi  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 Research201453(18): 7696–7705

[29]

Yu JQin  S J. Multimode process monitoring with Bayesian inference-based finite Gaussian mixture models. AIChE Journal200854(7): 1811–1829

[30]

Fan MGe  Z QSong  Z H. Adaptive Gaussian mixture model-based relevant sample selection for JITL soft sensor development. Industrial & Engineering Chemistry Research201453(51): 19979–19986

[31]

Yu J. A nonlinear kernel Gaussian mixture model based inferential monitoring approach for fault detection and diagnosis of chemical processes. Chemical Engineering Science201268(1): 506–519

[32]

Wen QGe  ZSong Z . Data-based linear Gaussian state-space model for dynamic process monitoring. AIChE Journal201258(12): 3763–3776

[33]

Ge ZKruger  ULamont L Xie LSong  Z. Fault detection in non-Gaussian vibration systems using dynamic statistical-based approaches. Mechanical Systems and Signal Processing201024(8): 2972–2984

[34]

Hyvarinen AOja  E. Independent component analysis: Algorithms and applications. Neural Networks200013(4-5): 411–430

[35]

Zhang M GGe  Z QSong  Z HFu  R W. Global-local structure analysis model and its application for fault detection and identification. Industrial & Engineering Chemistry Research201150(11): 6837–6848

[36]

Figueiredo M A T Jain A K . Unsupervised learning of finite mixture models. IEEE Transactions on Pattern Analysis and Machine Intelligence200224(3): 381–396

[37]

Te-Won LLewicki  M SSejnowski  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 Intelligence200022(10): 1078–1089

[38]

Downs J JVogel  E F. A plant-wide industrial process control problem. Computers & Chemical Engineering199317(3): 245–255

[39]

Lee J MQin  S JLee  I B. Fault detection and diagnosis based on modified independent component analysis. AIChE Journal200652(10): 3501–3514

RIGHTS & PERMISSIONS

Higher Education Press and Springer-Verlag Berlin Heidelberg

AI Summary AI Mindmap
PDF (531KB)

2499

Accesses

0

Citation

Detail

Sections
Recommended

AI思维导图

/