Abstract
The major goal of this paper is the description of a fault detection and isolation system. Such a system is geared to the complex processes through the combination of the neural networks, Fisher discriminate analysis and the principal component analysis. The corner stone of this work is the application of a self-associative neural network to the nonlinear PCA for fault detection by starting with a various measurement multivariable matrix stemming from a complex industrial process. FDA and PLS are, then, used to identify the directions of the detected faults through the classification of the groups with and without faults. To isolate these faults is to recognize the variables that are the cause of these faults. This is attained by calculating the contribution; in other words, the variables having the largest contribution with regard to the others are considered defective. This statistical approach is authenticated on a pastry production process and gives good results. By comparing FDI with other methods, we can perceive that our approach gives more reliable results.
Similar content being viewed by others
References
Yan Liu & al, “Nonlinear dynamic quality-related process monitoring based on dynamic total kernel PLS”, Intelligent Control and Automation (WCICA) June 29 2014-July 4 2014
Zhou D, Li G (2010) “Total projection to latent structures for process monitoring”. AIChE J 56(1):168–178
Ines J (2015) “Online process monitoring using a new PCMD index”. Int J Adv Manuf Technol 80(5):947–957
Fard N, Xu H, Fan Y (2016) “A unique solution for principal component analysis-based multi-response optimization problems”. Int J Adv Manuf Technol 82(1):697–709
Jebril HC, Ouni K, Nabli L (2015) Detecting and analyzing QRS complex using automatic tools. Int J Biomed Eng Technol Inderscience. in press
Xu Y, Goodacre R (2012) “Multiblock principal component analysis: an efficient tool for analyzing metabolomics data which contain two influential factors”. Metabolomics (springer) 8(1):37–51
Molloy M, Martin EB “Application of multiway principal component analysis for identification of process improvements in pharmaceutical manufacture”, 10th IFAC International Symposium on Dynamics and Control of Process Systems, Mumbai, India, December 2013, 283–288
Hu Z et al (2014) Adaptive PCA based fault diagnosis scheme in imperial smelting process. Isa Trans ICCA 2013 53(5):1446–1455
Shengkun X, Sridhar K (2013) “Dynamic principal component analysis with nonoverlapping moving window and its applications to epileptic EEG classification”. Sci World J sHindawi 2014:1–10
Hu Z et al (2012) “A simplified recursive dynamic PCA based monitoring scheme for imperial smelting process”. Int J Innov Comput Inf Control 8(4):2551–2561
Jebril HC, Ouni K (2015) Nonlinear system monitoring using multiscaled principal components analysis based on neural network. Int J Model Identif Control. in press
Chakour C, Harkat MF, Djeghaba M (2015) New adaptive kernel principal component analysis for nonlinear dynamic process monitoring. Appl Math Inf Sci 9(4):1833–1845
Al-Ani MS, Al-Waisy AS (2011) Multi-view face detection based on kernel principal component analysis and kernel support vector techniques. Int J Soft Comp (IJSC) 2(2):1–13
Ramahaleomiarantsoa &al, “Performances of the PCA method in electrical machines diagnosis using Matlab”, INTECH (chapter 4, 2012), pp.69-87
Liu X et al (2011) “Application of nonlinear PCA for fault detection in polymer extrusion processes”. Sch Electron Electr Eng Comput Sci 20(6):1141–1148
Okba Taouali et al. (2015) New fault detection method based on reduced kernel principal component analysis (RKPCA). Int J Adv Manuf Technol. 1-6
Halligan GR, Jagannathan S (2011) PCA-based fault isolation and prognosis with application to pump. Int J Adv Manuf Technol 55(5):699–707
Miyajima H, Shigei S, Shii T. Numerical evaluation of clustering methods with kernel PCA, Chapter: convergence and hybrid information technology. Lect Notes Comput Sci 6935: 677–684
Gonzalez R, Huang B, Lau E (2015) “Process monitoring using kernel density estimation and Bayesian networking with an industrial case study”. ISA Trans 58:330–347
Elaissi I et al (2013) Online prediction model based on the SVD-KPCA method. ISA Trans 52(1):96–104
Qiu J et al (2012) “Neural network implementations for PCA and its extensions”. Hindawi Artif Intell 2012:1–19
Balas CE, Levent Koç M, Tür R (2010) “Artificial neural networks based on principal component analysis, fuzzy systems and fuzzy neural networks for preliminary design of rubble mound breakwaters”. Science Direct:Appl Ocean Res 32(4):425–433
Zhou J et al (2014) “Fault detection and identification spanning multiple processes by integrating PCA with neural network”. Science Direct:Appl Soft Comput 14:4–11
Tan KK et al (2010) “Adaptive multiple minor directions extraction in parallel using a PCA neural network”. ScienceDirect: Theor Comput Sci 411(48):4200–4215
Liu R, Li Z (2012) The application of the PCA based on neural network in modeling study of P-xylene oxidative side-reaction. ScienceDirect: Physics Procedia 25:407–414
Robert J and Ata kaban, “Compressed Fisher linear discriminant analysis: classification of randomly projected data”, Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining, New York, NY, USA ©2010, Pages 1119–1128
Lê Cao K-H, Boitard S, Besse P (2011) Sparse PLS discriminant analysis: biologically relevant feature selection and graphical displays for multiclass problems. BMC Bioinformatics. 1–16
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chaouch, H., Ouni, K. & Nabli, L. Exploiting neural PCA and Fisher discriminate analysis for FDI system. Int J Adv Manuf Technol 87, 1183–1191 (2016). https://doi.org/10.1007/s00170-016-8549-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-016-8549-9