Advertisement

Online fault detection and isolation of an AIR quality monitoring network based on machine learning and metaheuristic methods

  • Radhia Fazai
  • Khaoula Ben Abdellafou
  • Maroua Said
  • Okba Taouali
ORIGINAL ARTICLE

Abstract

The dynamic process monitoring is discussed in this paper. Kernel principal component analysis (KPCA) is a nonlinear monitoring method that cannot be applied for dynamic systems. Reduced online KPCA (OR-KPCA)is used for fault detection of dynamic processes, which is developed to built a dictionary according to the process status and then, it update the KPCA model and uses it for process monitoring. Also the Tabu search metaheuristic algorithm is used in order to determine the optimal parameter of the kernel function. In this paper, new approaches for online fault isolation, which is a challenging problem in nonlinear PCA, are formulated. An extension of partial PCA and the elimination sensor identification (ESI) to the case of nonlinear systems are presented in a feature space. The partial OR-KPCA and the elimination sensor identification (ESI-KPCA) are generated based on the OR-KPCA method and they consist of developing a set of sub-models. The sub-models are selected according to a pre-designed fault-to-residual structure matrix and by eliminating sequentially one variable from the set of the variables. The proposed fault isolation methods are applied for monitoring an air quality monitoring network. The simulation results show that the proposed fault isolation methods are effective for KPCA.

Keywords

Principal component analysis (PCA) Kernel PCA OR-KPCA Dynamic process Fault detection Fault isolation Partial OR-KPCA ESI-KPCA 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Notes

References

  1. 1.
    Qin SJ (2012) Survey on data driven industrial process monitoring and diagnosis. Ann Rev Control 36(2):220–234CrossRefGoogle Scholar
  2. 2.
    Wang X, Kruger U, Irwin GW (2005) Process monitoring approach using fast moving window PCA. Ind Eng Chem Res 44(15):5691–5702CrossRefGoogle Scholar
  3. 3.
    Sheriff MZ, Mansouri M, Karim MN, Nounou H, Nounou M (2017) Fault detection using multiscale PCA-based moving window GLRT. J Process Control 54:47–64CrossRefGoogle Scholar
  4. 4.
    Wang H, Qian L, Dougherty E (2010) Inference of gene regulatory networks using S-system: a unified approach. IET Syst Biol 4(2):145–156CrossRefGoogle Scholar
  5. 5.
    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(7):2054–2063CrossRefGoogle Scholar
  6. 6.
    Lee JM, Qin SJ, Lee IB (2006) Fault detection and diagnosis based on modified independent component analysis. Aiche J 52(10):3501–3514CrossRefGoogle Scholar
  7. 7.
    Kano M, Tanaka S, Hasebe S, Hashimoto I, Ohno H (2003) Monotoring independent components for fault detection. Aiche J 49(4):969–976CrossRefGoogle Scholar
  8. 8.
    Chiang LH, Russell EL, Braatz RD (2000) Fault diagnosis in chemical processes using Fisher discriminant analysis, discriminant partial least squares, and principal component analysis. Chemometr Intell Lab Syst 50(2):243–252CrossRefGoogle Scholar
  9. 9.
    He QP, Qin SJ, Wang J (2005) A new faul diagnosis method using fault directions in Fisher discriminant analysis. Aiche J 51(2):555–571CrossRefGoogle Scholar
  10. 10.
    Yu J (2011) Localized Fisher discriminant analysis based complex chemical process monitoring. Aiche J 57(7):1817–1828CrossRefGoogle Scholar
  11. 11.
    Chen J, Liao CM (2002) Dynamic process fault monitoring based on neural network and PCA. J Process Control 12(2):277–289CrossRefGoogle Scholar
  12. 12.
    Shijian Z, Yongmao X (2005) Multivariate staistical process monitoring using robust nonlinear principal component analysis. Tsinghua Sci Technol 10(5):582–586CrossRefGoogle Scholar
  13. 13.
    Maulud A, Wang D, Romagnolti JA (2006) A multi-scale orthogonal nonlinear strategy for multi-variate statistical process monitoring. J Process Control 16(7):671–683CrossRefGoogle Scholar
  14. 14.
    Sheriff MZ, Karim MN, Nounou MN, Nounou H, Mansouri M (2017) Monitoring of chemical processes using improved multiscale KPCA. In: 4th International Conference on Control, Decision and Information Technologies (CODIT). IEEE, pp 0049–0054)Google Scholar
  15. 15.
    Baklouti R, Mansouri M, Nounou H, Nounou M, Slima MB, Hamida AB (2017) Fault detection of chemical processes using KPCA-based GLRT technique. In: International conference on Advanced Technologies for Signal and Image Processing (ATSIP). IEEE, pp 1-6Google Scholar
  16. 16.
    Mansouri M, Nounou M, Nounou H, Karim N (2016) Kernel PCA-based GLRT for nonlinear fault detection of chemical processes. J Loss Prev Process Ind 40:334–347CrossRefGoogle Scholar
  17. 17.
    Lee JM, Yoo C, Lee IB (2004) Fault detection of batch processes using multiway kernel principal component analysis. Comput Chem Eng 28(9):1837–1847CrossRefGoogle Scholar
  18. 18.
    Choi SW, Lee C, Lee JM, Park JH, Lee IB (2005) Fault detection and identification of nonlinear processes based on kernel PCA. Chemometr Intell Lab Syst 75(1):55–67CrossRefGoogle Scholar
  19. 19.
    Lee JM, Yoo C, Choi SW, Vanrolleghem PA, Lee IB (2004) Nonlinear process monitoring using kernel principal component analysis. Chem Eng Sci 59(1):223–234CrossRefGoogle Scholar
  20. 20.
    Cho JH, Lee JM, Choi SW, Lee D, Lee IB (2005) Fault identification for process monitoring using kernel principal component analysis. Chem Eng Sci 60(1):279–288CrossRefGoogle Scholar
  21. 21.
    Cui P, Li J, Wang G (2008) Improved kernel principal component analysis for fault detection. Expert Syst Appl 34(2):1210–1213CrossRefGoogle Scholar
  22. 22.
    Galiaskarov MR, Kurkina VV, Rusinov LA (2017) Online diangnostics of time varying nonlinear chemical processes using moving window kernel principal component analysis and Fisher discriminant analysis. J Chemom 31(8):e2866CrossRefGoogle Scholar
  23. 23.
    Khediri IB, Liman M, Weihs C (2011) Variable window adaptative kernel principal component analysis for nonlinear nonstationary process monitoring. Comput Ind Eng 61(3):437–446CrossRefGoogle Scholar
  24. 24.
    Jaffel I, Taouali O, Harkat MF, Messaoud H (2017) Kernel principal component analysis with reduced complexity for nonlinear dynamic process monitoring. Int J Adv Manuf Technol 88(9-12):3265–3279CrossRefGoogle Scholar
  25. 25.
    Fazai R, Taouali O, Harkat MF, Bouguila N (2016) A new fault detection method for nonlinear process monitoring. Int J Adv Manuf Technol 87(9-12):3425–3436CrossRefGoogle Scholar
  26. 26.
    Jaffel I, Taouali O, Harkat MF, Messaoud H (2016) Moving window KPCA with reduced complexity for nonlinear dynamic process monitoring. ISA Trans 64:184–192CrossRefGoogle Scholar
  27. 27.
    Fezai R, Mansouri M, Taouali O, Harkat MF, Bouguila N (2018) Online reduced kernel principal component analysis for process monitoring. J Process Control 61:1–11CrossRefGoogle Scholar
  28. 28.
    Alcala CF, Qin SJ (2010) Reconstruction-based contribution for process monitoring with kernel principal component analysis. Ind Eng Chem Res 49(17):7849–7857CrossRefGoogle Scholar
  29. 29.
    Kallas M, Mourot G, maquin D, Ragot J (2015) Fault estimation of nonlinear processes using kernel principal component analysis. In: control Conference (ECC), European, IEEE, pp 3197–3202)Google Scholar
  30. 30.
    Dunia R, Qin SJ, Edgar TF, McAovy TJ (1996) Identification of faulty sensors using principal component analysis. Aiche J 42(10):2797–2812CrossRefGoogle Scholar
  31. 31.
    Gertler J, Cao J (2005) Desiggn of optimal strucured residuals from partial principal component models for fault diagnosis in linear systems. J Process Control 15(5):585–603CrossRefGoogle Scholar
  32. 32.
    Huang Y, Gertler J, McAvoy TJ (2000) Sensor and actuator fault isolation by structured partial PCA with nonlinear extensions. J Process Control 10(5):459–469CrossRefGoogle Scholar
  33. 33.
    Gertler J, Li W, Huang Y, McAvoy T (1999) Isolation enhanced principal component analysis. Aiche J 45(2):323–334CrossRefGoogle Scholar
  34. 34.
    Huang Y, Gertler J, McAvoy TJ (1999) Fault isolation by partial PCA and partial NLPCA. IFAC Proc Vol 32(2):7647–7652CrossRefGoogle Scholar
  35. 35.
    Said M, Fazai R, Adellafou KB, Taouali O (2018) Decentralized fault detection and isolation using bond graph and PCA methods. The International Journal of Advanced Manufaturing Technology, pp 1–13.  https://doi.org/10.1007/s00170-018-2526-4
  36. 36.
    Stork CL, Veltkamp DJ, Kowalski BR (1997) Identification of multiple sensor disturbances during process monitoring. Anal Chem 69(24):5031–5036CrossRefGoogle Scholar
  37. 37.
    Cristianini N, Shawe Taylor J (2000) An introduction to support vector machines and other kernel based learning methods. Cambridge university press, CambridgeCrossRefGoogle Scholar
  38. 38.
    Taouali O, Jaffel I, Lahdhiri H, Harkat MF, Messouad H (2016) New fault detection method based on reduced kernel principal component analysis (RKPCA). Int J Adv Manuf Technol 85(5-8):1547–1552CrossRefGoogle Scholar
  39. 39.
    Honeine P (2015) Approximation errors of online sparsification criteria, IEEE Trans. Signal Process 63(17):4700–4709MathSciNetzbMATHGoogle Scholar
  40. 40.
    Honeine P (2012) Online kernel principal component analysis: reduced order model. IEEE Transactions on Patern Analysis and Machine Intelligence 34(9):1814–1826CrossRefGoogle Scholar
  41. 41.
    Gao W, Chen J, Richard C, Huang J (2014) Online dictionary learning for kernel LMS. IEEE Trans Signal Process 62(11):2765–2777MathSciNetCrossRefGoogle Scholar
  42. 42.
    Honeine P (2015) Analyzing sparse dictionaries for online learning with kernels. IEEE Trans Signal Process 63(23):6343–6353MathSciNetCrossRefGoogle Scholar
  43. 43.
    Harkat MF, Mourot G, Ragot J (2006) An improved PCA scheme for sensor FDI: application to an air quality monitoring network. J Process Control 16(6):625–634CrossRefGoogle Scholar
  44. 44.
    Harkat MF, Mourot G, Ragot J (2009) Multiple sensor fault detection and isolation of an air quality monitoring network using RBF-NLPCA model. IFAC Proc Vol 42(8):828–833CrossRefGoogle Scholar
  45. 45.
    Downs JJ, Vogel EF (1993) A plant wide industrial process control problem. Comput Chem Eng 17(3):245–255CrossRefGoogle Scholar
  46. 46.
    Rato T, Reis M, Schmitt E, Hubert M, De Ketelare B (2016) A systematic comparison of PCA based Statistical Process Monitoring methods for high-dimensional, time dependent Processes. AIChE J 62(5):1478–1493CrossRefGoogle Scholar
  47. 47.
    Harkat MF, Mansouri M, Nounou M, Nounou H (2018) Enhanced data validation strategy of air quality monitoring network. Environ Res 160:183–194CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  • Radhia Fazai
    • 1
  • Khaoula Ben Abdellafou
    • 2
  • Maroua Said
    • 1
  • Okba Taouali
    • 1
  1. 1.Research Laboratory of Automation, Signal Processing and Image (LARATSI), National School of Engineering of MonastirUniversity of MonastirMonastirTunisia
  2. 2.MARS (Modeling of Automated Reasoning Systems) Research Lab LR17ES05, Higher Institute of Computer Sciences and Communication Technologies (ISITCom)University of SousseSousseTunisia

Personalised recommendations