Fault detection and diagnosis of chemical process using enhanced KECA

Abstract As the main concerns of abnormal event management in process engineering, fault detection and diagnosis have attracted more and more attention recently. A new monitoring method based on kernel entropy component analysis(KECA) is proposed for nonlinear chemical process. Then, an angle-based statistic is designed to express the distinct angular structure that KECA reveals, which is able to measure the similarity between probability density functions. Likewise, each KECA classifier is dedicated to a specific fault, which provides an expendable framework for incorporating new faults identified in the process. As to the fault features are submerged because of multi-scale property of process data, an enhanced KECA method for fault detection and diagnosis is developed, by adding multi-scale principal component analysis(MSPCA) for features extraction to improve the classification effect of KECA. The effectiveness of the proposed approach is demonstrated by applying to Tennessee Eastman process. The MSPCA based method essentially captures the fault-symptom correlation, whereas KECA can be an effective method for process fault diagnosis.

[1]  Robert Jenssen,et al.  Kernel Entropy Component Analysis , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Robert Jenssen,et al.  The Cauchy-Schwarz divergence and Parzen windowing: Connections to graph theory and Mercer kernels , 2006, J. Frankl. Inst..

[3]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[4]  Zhi-Huan Song,et al.  A novel fault diagnosis system using pattern classification on kernel FDA subspace , 2011, Expert Syst. Appl..

[5]  B. Bakshi.  Multiscale PCA with application to multivariate statistical process monitoring , 1998 .

[6]  C. Yoo,et al.  Nonlinear process monitoring using kernel principal component analysis , 2004 .

[7]  Jose A. Romagnoli,et al.  Robust multi-scale principal components analysis with applications to process monitoring , 2005 .

[8]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[9]  Ahmet Palazoglu,et al.  Improved ICA for process monitoring based on ensemble learning and Bayesian inference , 2014 .

[10]  E. F. Vogel,et al.  A plant-wide industrial process control problem , 1993 .

[11]  In-Beum Lee,et al.  Fault identification for process monitoring using kernel principal component analysis , 2005 .

[12]  Yingwei Zhang,et al.  Enhanced statistical analysis of nonlinear processes using KPCA, KICA and SVM , 2009 .

[13]  Christos Georgakis,et al.  Plant-wide control of the Tennessee Eastman problem , 1995 .

[14]  Xue-feng Yan,et al.  Fault detection in nonlinear chemical processes based on kernel entropy component analysis and angular structure , 2013, Korean Journal of Chemical Engineering.

[15]  Si-Zhao Joe Qin,et al.  Survey on data-driven industrial process monitoring and diagnosis , 2012, Annu. Rev. Control..

[16]  S. Joe Qin,et al.  Multivariate process monitoring and fault diagnosis by multi-scale PCA , 2002 .

[17]  Michael I. Jordan,et al.  Kernel independent component analysis , 2003 .

[18]  Yupu Yang,et al.  Fault diagnosis based on variable-weighted kernel Fisher discriminant analysis , 2008 .

[19]  Hassan Fathabadi,et al.  Novel filter based ANN approach for short-circuit faults detection, classification and location in power transmission lines , 2016 .

[20]  Chris Aldrich,et al.  Unsupervised Process Monitoring and Fault Diagnosis with Machine Learning Methods , 2013, Advances in Computer Vision and Pattern Recognition.

[21]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[22]  Steven X. Ding,et al.  Data-driven design of monitoring and diagnosis systems for dynamic processes: A review of subspace technique based schemes and some recent results , 2014 .

[23]  Mohd Azlan Hussain,et al.  Fault diagnosis of Tennessee Eastman process with multi- scale PCA and ANFIS , 2013 .

[24]  George Stephanopoulos,et al.  Compression of chemical process data by functional approximation and feature extraction , 1996 .

[25]  A. Rényi.  On Measures of Entropy and Information , 1961 .

[26]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part II: Qualitative models and search strategies , 2003, Comput. Chem. Eng..

[27]  Xin Gao,et al.  An improved SVM integrated GS-PCA fault diagnosis approach of Tennessee Eastman process , 2016, Neurocomputing.