Mixed kernel canonical variate dissimilarity analysis for incipient fault monitoring in nonlinear dynamic processes

Abstract Incipient fault monitoring is becoming very important in large industrial plants, as the early detection of incipient faults can help avoid major plant failures. Recently, Canonical Variate Dissimilarity Analysis (CVDA) has been shown to be an efficient technique for incipient fault detection, especially under dynamic process conditions. CVDA can be extended to nonlinear processes by introducing kernel-based learning. Incipient fault monitoring requires kernels with both good interpolation and extrapolation abilities. However, conventional single kernels only exhibit one ability or the other, but not both. To overcome this drawback, this study presents a Mixed Kernel CVDA method for incipient fault monitoring in nonlinear dynamic processes. Due to the use of mixed kernels, both enhanced detection sensitivity and a better depiction of the growing fault severity in the monitoring charts are achieved. Looking ahead, this work takes a step towards understanding the impact of kernel behavior in process monitoring performance.

[1]  Yi Cao,et al.  Canonical Variate Dissimilarity Analysis for Process Incipient Fault Detection , 2018, IEEE Transactions on Industrial Informatics.

[2]  Zhenzhou Lu,et al.  Mixed kernel function support vector regression for global sensitivity analysis , 2017 .

[3]  Thomas J. McAvoy,et al.  Fault Detection and Diagnosis in Industrial Systems , 2002 .

[4]  Yi Cao,et al.  Kernel Canonical Variate Analysis for Nonlinear Dynamic Process Monitoring , 2015 .

[5]  Hassani Messaoud,et al.  Moving window KPCA with reduced complexity for nonlinear dynamic process monitoring. , 2016, ISA transactions.

[6]  Majdi Mansouri,et al.  Online reduced kernel principal component analysis for process monitoring , 2018 .

[7]  Huijun Gao,et al.  Data-Based Techniques Focused on Modern Industry: An Overview , 2015, IEEE Transactions on Industrial Electronics.

[8]  Qiang Liu,et al.  Dynamic concurrent kernel CCA for strip-thickness relevant fault diagnosis of continuous annealing processes , 2017, Journal of Process Control.

[9]  Rolf Isermann,et al.  Model-based fault-detection and diagnosis - status and applications , 2004, Annu. Rev. Control..

[10]  Jicong Fan,et al.  Fault detection and diagnosis of non-linear non-Gaussian dynamic processes using kernel dynamic independent component analysis , 2014, Inf. Sci..

[11]  Min Han,et al.  Multivariate time series prediction based on multiple kernel extreme learning machine , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

[12]  Marios M. Polycarpou,et al.  A robust detection and isolation scheme for abrupt and incipient faults in nonlinear systems , 2002, IEEE Trans. Autom. Control..

[13]  David Duvenaud,et al.  Automatic model construction with Gaussian processes , 2014 .

[14]  Zhiqiang Ge,et al.  Distributed predictive modeling framework for prediction and diagnosis of key performance index in plant-wide processes , 2017 .

[15]  Hanwen Zhang,et al.  Fault detection based on augmented kernel Mahalanobis distance for nonlinear dynamic processes , 2018, Comput. Chem. Eng..

[16]  Zhiqiang Ge,et al.  Large-scale plant-wide process modeling and hierarchical monitoring: A distributed Bayesian network approach , 2017 .

[17]  Plant-Wide Industrial Process Monitoring: A Distributed Modeling Framework , 2016, IEEE Transactions on Industrial Informatics.

[18]  Tiago J. Rato,et al.  Sensitivity enhancing transformations for monitoring the process correlation structure , 2014 .

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

[20]  Hazem Nounou,et al.  Kernel PLS-based GLRT method for fault detection of chemical processes , 2016 .

[21]  Zhiqiang Ge,et al.  Big data quality prediction in the process industry: A distributed parallel modeling framework , 2018, Journal of Process Control.

[22]  G. Rong,et al.  Learning a data-dependent kernel function for KPCA-based nonlinear process monitoring , 2009 .

[23]  Z. Zhong,et al.  Application of mixed kernels function (MKF) based support vector regression model (SVR) for CO2 - Reservoir oil minimum miscibility pressure prediction , 2016 .

[24]  Yi Cao,et al.  Process incipient fault detection using canonical variate analysis , 2017, 2017 23rd International Conference on Automation and Computing (ICAC).

[25]  Bin Luo,et al.  A local-global mixed kernel with reproducing property , 2015, Neurocomputing.

[26]  Dong Dong,et al.  Nonlinear principal component analysis-based on principal curves and neural networks , 1994, Proceedings of 1994 American Control Conference - ACC '94.

[27]  Frank L. Lewis,et al.  Intelligent Fault Diagnosis and Prognosis for Engineering Systems , 2006 .

[28]  Ning Wang,et al.  The optimization of the kind and parameters of kernel function in KPCA for process monitoring , 2012, Comput. Chem. Eng..

[29]  Orestes Llanes-Santiago,et al.  Enhanced dynamic approach to improve the detection of small-magnitude faults , 2016 .

[30]  Yi Yang,et al.  Mixed kernel based extreme learning machine for electric load forecasting , 2018, Neurocomputing.

[31]  Hui Peng,et al.  SVM with multiple kernels based on manifold learning for Breast Cancer diagnosis , 2013, 2013 IEEE International Conference on Information and Automation (ICIA).

[32]  Alexander J. Smola,et al.  Regularization with Dot-Product Kernels , 2000, NIPS.

[33]  Zi Huang,et al.  Dimensionality reduction by Mixed Kernel Canonical Correlation Analysis , 2012, Pattern Recognition.

[34]  Cristobal Ruiz-Carcel,et al.  Statistical process monitoring of a multiphase flow facility , 2015 .

[35]  J. Golinval,et al.  Fault detection based on Kernel Principal Component Analysis , 2010 .

[36]  ChangKyoo Yoo,et al.  Fault detection of batch processes using multiway kernel principal component analysis , 2004, Comput. Chem. Eng..

[37]  Z. Zeng,et al.  Displacement prediction of landslide based on PSOGSA-ELM with mixed kernel , 2013, 2013 Sixth International Conference on Advanced Computational Intelligence (ICACI).

[38]  Jin Hyun Park,et al.  Fault detection and identification of nonlinear processes based on kernel PCA , 2005 .

[39]  Donghua Zhou,et al.  Exponential Smoothing Reconstruction Approach for Incipient Fault Isolation , 2018 .

[40]  Raphael Tari Samuel.  Nonlinear dynamic process monitoring using kernel methods , 2016 .

[41]  Chun-Chin Hsu,et al.  Adaptive Kernel Principal Component Analysis (KPCA) for Monitoring Small Disturbances of Nonlinear Processes , 2010 .

[42]  Richard D. Braatz,et al.  Locality preserving discriminative canonical variate analysis for fault diagnosis , 2018, Comput. Chem. Eng..

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

[44]  Mahmood Shafiee.  Modelling and analysis of availability for critical interdependent infrastructures , 2016 .

[45]  Zhiqiang Ge,et al.  Distributed Parallel PCA for Modeling and Monitoring of Large-Scale Plant-Wide Processes With Big Data , 2017, IEEE Transactions on Industrial Informatics.

[46]  Timothy R. Carr,et al.  Dew point pressure prediction based on mixed-kernels-function support vector machine in gas-condensate reservoir , 2018, Fuel.

[47]  Sheng Chen,et al.  Monitoring Nonlinear and Non-Gaussian Processes Using Gaussian Mixture Model-Based Weighted Kernel Independent Component Analysis , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[48]  Tong Zhang,et al.  An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods , 2001, AI Mag..

[49]  Bin Liu,et al.  A Mixture of Variational Canonical Correlation Analysis for Nonlinear and Quality-Relevant Process Monitoring , 2018, IEEE Transactions on Industrial Electronics.

[50]  Yingwei Zhang,et al.  Process Monitoring, Fault Diagnosis and Quality Prediction Methods Based on the Multivariate Statistical Techniques , 2010 .

[51]  Yi Cao,et al.  Nonlinear Dynamic Process Monitoring Using Canonical Variate Analysis and Kernel Density Estimations , 2010, IEEE Transactions on Industrial Informatics.

[52]  Zhiqiang Ge,et al.  Review on data-driven modeling and monitoring for plant-wide industrial processes , 2017 .

[53]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[54]  Furong Gao,et al.  Review of Recent Research on Data-Based Process Monitoring , 2013 .

[55]  Jian Hou,et al.  Recent advances on SVM based fault diagnosis and process monitoring in complicated industrial processes , 2016, Neurocomputing.