Supervised process monitoring and fault diagnosis based on machine learning methods
- 8 Downloads
Data-driven techniques have been receiving considerable attention in the industrial process monitoring field due to their major advantages of easy implementation and less requirement for the prior knowledge and process mechanism. Principal component analysis (PCA) method is known as a popular method for monitoring and fault detection in industrial systems but as it is basically a linear method. However, most practical systems are nonlinear. To make the extension to nonlinear systems, kernel PCA (KPCA) method has been proposed for process modeling and monitoring. We present in this paper an online reduced rank optimized KPCA (RR-KPCA) technique for fault detection in order to extend the advantages of the KPCA models to online processes. Following the fault detection, the identification of the variables correlated to the fault occurred is of great importance. For this purpose, it is proposed to extend the approaches of localization by partial PCA and by elimination in the linear case to the nonlinear case, by exploiting the solution of reduction of the dimension of the kernel matrix in the feature space. The partial RR-KPCA and the elimination sensor identification (ESI-RRKPCA) are generated based on the static RR-KPCA and the online RR-KPCA methods. The idea of these approaches is to generate partial RR-KPCA models with reduced sets of variables. In other words, their goal is to generate indices of fault detection sensitive to certain faults and insensitive to others. The proposed fault isolation methods are applied for monitoring an air quality monitoring network (AIRLOR) data.
KeywordsReduced rank KPCA Nonlinear process monitoring Fault detection Tabu search algorithm Air quality monitoring Fault isolation
Unable to display preview. Download preview PDF.
- 3.Mika S, Schölkopf B, Smola AJ, Müller KR, Scholz M, Rätsch G (1998, December) Kernel PCA and de-noising in feature spaces. In: NIPS, vol 11, pp 536–542Google Scholar
- 11.Chouaib C, Mohamed-Faouzi H, Messaoud D (2015) New adaptive kernel principal component analysis for nonlinear dynamic process monitoring. Appl Math Inf Sci 9(4):1833–1845Google Scholar
- 15.Ding C (2004) K -means clustering via principal component analysis, in the 21st Int Conf Mach Learn. Banff, CanadaGoogle Scholar
- 16.Dhillon IS (2004) Kernel k-means, spectral clustering and normalized cuts. Compute 78712:551–556Google Scholar
- 19.Gertler J, McAvoy T (1997) Principal component analysis and parity relations – a strong duality. IFAC Conference SAFEPROCESS, Hull, UK, pp. 837–842Google Scholar
- 20.Huang Y, Gertler J (1999) Fault isolation by partial PCA and partial NLPCA.. IFAC’99, 14th triennial world congress. P. R. China, Beijing, pp 545–550Google Scholar
- 37.Kallas M, Mourot G, Maquin D, Ragot J (2014) Diagnosis of nonlinear systems using kernel principal component analysis. In Journal of Physics: Conference Series (Vol. 570, No. 7, p. 072004). IOP PublishingGoogle Scholar
- 40.Jicong Fan S, Qin J, Wang Y (2014) Online monitoring of nonlinear multivariate industrial processes using filtering KICA–PCA. Control Eng Pract 22(2014):205–216Google Scholar
- 49.Jaffel I, Taouali O, Harkat MF, Messaoud H (2016) Kernel principal component analysis with reduced complexity for nonlinear dynamic process monitoring. Int J Adv Manuf Technol 88:3265(1–15). https://doi.org/10.1007/s00170-016-8987-4
- 51.Lahdhiri H, Taouali O, Elaissi I, Jaffel I, Harakat MF, Messaoud H (2017) A new fault detection index based on Mahalanobis distance and kernel method. Int J Adv Manuf Technol 91: 2799:1–11. https://doi.org/10.1007/s00170-016-9887-3
- 56.Lahdhiri H, Ben Abdellafou K, Taouali O, Mansouri M, Korbaa O (2018) New online kernel method with the Tabu search algorithm for process monitoring. Trans Inst Meas Control:1–12. https://doi.org/10.1177/0142331218807271