Skip to main content
Top
Published in: Soft Computing 16/2020

20-01-2020 | Methodologies and Application

Performance-driven ensemble ICA chemical process monitoring based on fault-relevant models

Authors: Zhichao Li, Xuefeng Yan

Published in: Soft Computing | Issue 16/2020

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Independent component analysis has been widely used in non-Gaussian chemical process monitoring. However, using the normal operation data or adopting a certain independent component selection criteria alone to construct the monitoring model cannot achieve satisfactory monitoring performance. To address the problem effectively, a fault-relevant model selection combined with ensemble learning and the Bayesian inference method is developed in this study. First, numerous models are constructed on the basis of the randomly selected ICs. Second, the models with the highest fault detection rates for each fault are selected. Then, a screening algorithm based on the difference in detection results is adopted to reduce the redundancy of the selected models and thus improve the monitoring performance. Finally, Bayesian inference is adopted to combine the testing results of the retained models. Case studies containing numerical simulations and the Tennessee Eastman benchmark process illustrate the validity of the proposed approach.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Literature
go back to reference Back AD, Weigend AS (1997) A first application of independent component analysis to extracting structure from stock returns. Int J Neural Syst 8:473–484 Back AD, Weigend AS (1997) A first application of independent component analysis to extracting structure from stock returns. Int J Neural Syst 8:473–484
go back to reference Cai L, Tian X, Chen S (2015) Monitoring nonlinear and non-gaussian processes using gaussian mixture model-based weighted kernel independent component analysis. IEEE Trans Neural Netw Learn Syst 28:122–135 Cai L, Tian X, Chen S (2015) Monitoring nonlinear and non-gaussian processes using gaussian mixture model-based weighted kernel independent component analysis. IEEE Trans Neural Netw Learn Syst 28:122–135
go back to reference Chiang LH, Russell EL, Braatz RD (2001) Fault detection and diagnosis in industrial systems. Meas Sci Technol 12:1745MATH Chiang LH, Russell EL, Braatz RD (2001) Fault detection and diagnosis in industrial systems. Meas Sci Technol 12:1745MATH
go back to reference Downs JJ, Vogel EF (1993) A plant-wide industrial process control problem. Comput Chem Eng 17:245–255 Downs JJ, Vogel EF (1993) A plant-wide industrial process control problem. Comput Chem Eng 17:245–255
go back to reference Ge Z, Song Z (2007) Process monitoring based on independent component analysis—principal component analysis (ICA − PCA) and similarity factors. Ind Eng Chem Res 46:2054–2063 Ge Z, Song Z (2007) Process monitoring based on independent component analysis—principal component analysis (ICA − PCA) and similarity factors. Ind Eng Chem Res 46:2054–2063
go back to reference Ge Z, Song Z (2013) Performance-driven ensemble learning ICA model for improved non-Gaussian process monitoring. Chemometr Intell Lab Syst 123:1–8 Ge Z, Song Z (2013) Performance-driven ensemble learning ICA model for improved non-Gaussian process monitoring. Chemometr Intell Lab Syst 123:1–8
go back to reference Ge Z, Zhang M, Song Z (2010) Nonlinear process monitoring based on linear subspace and Bayesian inference. J Process Control 20:676–688 Ge Z, Zhang M, Song Z (2010) Nonlinear process monitoring based on linear subspace and Bayesian inference. J Process Control 20:676–688
go back to reference Ge Z, Song Z, Gao F (2013) Review of recent research on data-based process monitoring. Ind Eng Chem Res 52:3543–3562 Ge Z, Song Z, Gao F (2013) Review of recent research on data-based process monitoring. Ind Eng Chem Res 52:3543–3562
go back to reference Ghosh K, Ramteke M, Srinivasan R (2014) Optimal variable selection for effective statistical process monitoring. Comput Chem Eng 60:260–276 Ghosh K, Ramteke M, Srinivasan R (2014) Optimal variable selection for effective statistical process monitoring. Comput Chem Eng 60:260–276
go back to reference Hsu CC, Chen MC, Chen LS (2010) Integrating independent component analysis and support vector machine for multivariate process monitoring. Comput Ind Eng 59:145–156 Hsu CC, Chen MC, Chen LS (2010) Integrating independent component analysis and support vector machine for multivariate process monitoring. Comput Ind Eng 59:145–156
go back to reference Hyvrinen A (1999) Survey on independent component analysis. Neural Comput Surv 2:1527–1558 Hyvrinen A (1999) Survey on independent component analysis. Neural Comput Surv 2:1527–1558
go back to reference Jiang Q, Yan X (2013) Non-Gaussian chemical process monitoring with adaptively weighted independent component analysis and its applications. J Process Control 23:1320–1331 Jiang Q, Yan X (2013) Non-Gaussian chemical process monitoring with adaptively weighted independent component analysis and its applications. J Process Control 23:1320–1331
go back to reference Jiang Q, Yan X, Tong C (2013) Double-weighted independent component analysis for non-gaussian chemical process monitoring. Ind Eng Chem Res 52:14396–14405 Jiang Q, Yan X, Tong C (2013) Double-weighted independent component analysis for non-gaussian chemical process monitoring. Ind Eng Chem Res 52:14396–14405
go back to reference Jiang Q, Yan X, Lv Z, Guo M (2014) Independent component analysis-based non-Gaussian process monitoring with preselecting optimal components and support vector data description. Int J Prod Res 52:3273–3286 Jiang Q, Yan X, Lv Z, Guo M (2014) Independent component analysis-based non-Gaussian process monitoring with preselecting optimal components and support vector data description. Int J Prod Res 52:3273–3286
go back to reference Jiang Q, Wang B, Yan X (2015) Multiblock independent component analysis integrated with Hellinger distance and Bayesian inference for non-Gaussian plant-wide process monitoring. Ind Eng Chem Res 54:2497–2508 Jiang Q, Wang B, Yan X (2015) Multiblock independent component analysis integrated with Hellinger distance and Bayesian inference for non-Gaussian plant-wide process monitoring. Ind Eng Chem Res 54:2497–2508
go back to reference Kano M, Tanaka S, Hasebe S, Hashimoto I, Ohno H (2003) Monitoring independent components for fault detection. AIChE J 49:969–976 Kano M, Tanaka S, Hasebe S, Hashimoto I, Ohno H (2003) Monitoring independent components for fault detection. AIChE J 49:969–976
go back to reference Ketelaere BD, Hubert M, Schmitt E (2015) Overview of PCA-based statistical process monitoring methods for time-dependent, high-dimensional data. J Qual Technol 47:318–335 Ketelaere BD, Hubert M, Schmitt E (2015) Overview of PCA-based statistical process monitoring methods for time-dependent, high-dimensional data. J Qual Technol 47:318–335
go back to reference Lee JM, Yoo CK, Lee IB (2004) Statistical process monitoring with independent component analysis. J Process Control 14:467–485 Lee JM, Yoo CK, Lee IB (2004) Statistical process monitoring with independent component analysis. J Process Control 14:467–485
go back to reference Lee JM, Qin SJ, Lee IB (2006) Fault detection and diagnosis based on modified independent component analysis. AIChE J 52:3501–3514 Lee JM, Qin SJ, Lee IB (2006) Fault detection and diagnosis based on modified independent component analysis. AIChE J 52:3501–3514
go back to reference Lee J, Qin SJ, Lee I (2008) Fault detection of non-linear processes using kernel independent component analysis. Can J Chem Eng 85:526–536 Lee J, Qin SJ, Lee I (2008) Fault detection of non-linear processes using kernel independent component analysis. Can J Chem Eng 85:526–536
go back to reference Lee J, Kang B, Kang SH (2011) Integrating independent component analysis and local outlier factor for plant-wide process monitoring. J Process Control 21:1011–1021 Lee J, Kang B, Kang SH (2011) Integrating independent component analysis and local outlier factor for plant-wide process monitoring. J Process Control 21:1011–1021
go back to reference Li RF, Wang XZ (2002) Dimension reduction of process dynamic trends using independent component analysis. Comput Chem Eng 26:467–473 Li RF, Wang XZ (2002) Dimension reduction of process dynamic trends using independent component analysis. Comput Chem Eng 26:467–473
go back to reference Li N, Yang Y (2015) Ensemble Kernel principal component analysis for improved nonlinear process monitoring. Ind Eng Chem Res 54:318–329 Li N, Yang Y (2015) Ensemble Kernel principal component analysis for improved nonlinear process monitoring. Ind Eng Chem Res 54:318–329
go back to reference Odiowei PP, Cao Y (2010) State-space independent component analysis for nonlinear dynamic process monitoring. Chemometr Intell Lab Syst 103:59–65 Odiowei PP, Cao Y (2010) State-space independent component analysis for nonlinear dynamic process monitoring. Chemometr Intell Lab Syst 103:59–65
go back to reference Rashid MM, Yu J (2012) A new dissimilarity method integrating multidimensional mutual information and independent component analysis for non-Gaussian dynamic process monitoring. Chemometr Intell Lab Syst 115:44–58 Rashid MM, Yu J (2012) A new dissimilarity method integrating multidimensional mutual information and independent component analysis for non-Gaussian dynamic process monitoring. Chemometr Intell Lab Syst 115:44–58
go back to reference Shen Y, Huang Z (2015) Performance monitoring for vehicle suspension system via fuzzy positivistic C-means clustering based on accelerometer measurements. IEEE/ASME Trans Mechatron 20:2613–2620 Shen Y, Huang Z (2015) Performance monitoring for vehicle suspension system via fuzzy positivistic C-means clustering based on accelerometer measurements. IEEE/ASME Trans Mechatron 20:2613–2620
go back to reference Tong C, Palazoglu A, Yan X, Tong C, Palazoglu A, Yan X (2014) Improved ICA for process monitoring based on ensemble learning and Bayesian inference. Chemometr Intell Lab Syst 135:141–149 Tong C, Palazoglu A, Yan X, Tong C, Palazoglu A, Yan X (2014) Improved ICA for process monitoring based on ensemble learning and Bayesian inference. Chemometr Intell Lab Syst 135:141–149
go back to reference Tong C, Lan T, Shi X (2017a) Double-layer ensemble monitoring of non-gaussian processes using modified independent component analysis. ISA Trans 68:181 Tong C, Lan T, Shi X (2017a) Double-layer ensemble monitoring of non-gaussian processes using modified independent component analysis. ISA Trans 68:181
go back to reference Tong C, Lan T, Shi X (2017b) Ensemble modified independent component analysis for enhanced non-Gaussian process monitoring. Control Eng Pract 58:34–41 Tong C, Lan T, Shi X (2017b) Ensemble modified independent component analysis for enhanced non-Gaussian process monitoring. Control Eng Pract 58:34–41
go back to reference Wang L, Shi H (2010) Multivariate statistical process monitoring using an improved independent component analysis. Chem Eng Res Des 88:403–414 Wang L, Shi H (2010) Multivariate statistical process monitoring using an improved independent component analysis. Chem Eng Res Des 88:403–414
go back to reference Wang J, Zhang Y, Cao H, Zhu W (2012) Dimension reduction method of independent component analysis for process monitoring based on minimum mean square error. J Process Control 22:477–487 Wang J, Zhang Y, Cao H, Zhu W (2012) Dimension reduction method of independent component analysis for process monitoring based on minimum mean square error. J Process Control 22:477–487
go back to reference Wang B, Yan X, Jiang Q (2016) Independent component analysis model utilizing de-mixing information for improved non-Gaussian process monitoring. Comput Ind Eng 94:188–200 Wang B, Yan X, Jiang Q (2016) Independent component analysis model utilizing de-mixing information for improved non-Gaussian process monitoring. Comput Ind Eng 94:188–200
go back to reference Xie L, Li Z, Zeng J, Kruger U (2016) Block adaptive kernel principal component analysis for nonlinear process monitoring. AIChEe J 62:4334–4345 Xie L, Li Z, Zeng J, Kruger U (2016) Block adaptive kernel principal component analysis for nonlinear process monitoring. AIChEe J 62:4334–4345
go back to reference Yang WA (2016) Simultaneous monitoring of mean vector and covariance matrix shifts in bivariate manufacturing processes using hybrid ensemble learning-based model. J Intell Manuf 27:845–874 Yang WA (2016) Simultaneous monitoring of mean vector and covariance matrix shifts in bivariate manufacturing processes using hybrid ensemble learning-based model. J Intell Manuf 27:845–874
go back to reference Yin S, Ding SX, Xie X, Luo H (2014a) A review on basic data-driven approaches for industrial process monitoring. IEEE Trans Industr Electron 61:6418–6428 Yin S, Ding SX, Xie X, Luo H (2014a) A review on basic data-driven approaches for industrial process monitoring. IEEE Trans Industr Electron 61:6418–6428
go back to reference Yin S, Gao H, Kaynak O (2014b) Data-driven control and process monitoring for industrial applications—part II. IEEE Trans Industr Electron 62(1):583–586 Yin S, Gao H, Kaynak O (2014b) Data-driven control and process monitoring for industrial applications—part II. IEEE Trans Industr Electron 62(1):583–586
go back to reference Yin S, Gao H, Kaynak O (2015a) Data-driven control and process monitoring for industrial applications—part I. IEEE Trans Industr Electron 61:6356–6359 Yin S, Gao H, Kaynak O (2015a) Data-driven control and process monitoring for industrial applications—part I. IEEE Trans Industr Electron 61:6356–6359
go back to reference Yin S, Li X, Gao H, Kaynak O (2015b) Data-based techniques focused on modern industry: an overview. IEEE Trans Industr Electron 62:657–667 Yin S, Li X, Gao H, Kaynak O (2015b) Data-based techniques focused on modern industry: an overview. IEEE Trans Industr Electron 62:657–667
go back to reference Zhang Y, An J, Zhang H (2013) Monitoring of time-varying processes using kernel independent component analysis. Chem Eng Sci 88:23–32 Zhang Y, An J, Zhang H (2013) Monitoring of time-varying processes using kernel independent component analysis. Chem Eng Sci 88:23–32
go back to reference Zhou ZH (2012) Ensemble methods: foundations and algorithms. Taylor & Francis, Routledge Zhou ZH (2012) Ensemble methods: foundations and algorithms. Taylor & Francis, Routledge
go back to reference Zhu J, Ge Z, Song Z (2014) Robust modeling of mixture probabilistic principal component analysis and process monitoring application. AIChE J 60:2143–2157 Zhu J, Ge Z, Song Z (2014) Robust modeling of mixture probabilistic principal component analysis and process monitoring application. AIChE J 60:2143–2157
Metadata
Title
Performance-driven ensemble ICA chemical process monitoring based on fault-relevant models
Authors
Zhichao Li
Xuefeng Yan
Publication date
20-01-2020
Publisher
Springer Berlin Heidelberg
Published in
Soft Computing / Issue 16/2020
Print ISSN: 1432-7643
Electronic ISSN: 1433-7479
DOI
https://doi.org/10.1007/s00500-020-04673-6

Other articles of this Issue 16/2020

Soft Computing 16/2020 Go to the issue

Premium Partner