Comparative study on monitoring schemes for non-Gaussian distributed processes

Abstract Traditional multivariate statistical process monitoring techniques usually assume measurements follow a multivariate Gaussian distribution so that T 2 can be used for monitoring. The assumption usually does not hold in practice. Many efforts have been spent on redefining a proper boundary of control region for non-Gaussian distributed processes. These efforts lead to new models such as independent component analysis (ICA), statistical pattern analysis (SPA), and new techniques such as kernel density estimation (KDE), support vector data description (SVDD). However, it has not been stated clearly how a latent structure will affect monitoring performance. In this paper, most of main stream methods for non-Gaussian process monitoring are recalled and categorized. The essential problem formulation of process monitoring is summarized from a general case and then explained in both Gaussian and non-Gaussian distribution, respectively. According to this formulation, KDE and SVDD methods are effective but time-consuming to extract proper control region of non-Gaussian distributed processes. Dimension reduction models are more beneficial to overcome the curse of dimensionality, rather than extracting non-Gaussian data structure. Besides, the monitoring of non-Gaussian processes can be converted into the monitoring of Gaussian processes according to central limitation theorem.

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

[2]  Uwe Kruger,et al.  Regularised kernel density estimation for clustered process data , 2004 .

[3]  Michèle Basseville,et al.  On-board Component Fault Detection and Isolation Using the Statistical Local Approach , 1998, Autom..

[4]  Steven X. Ding,et al.  A Review on Basic Data-Driven Approaches for Industrial Process Monitoring , 2014, IEEE Transactions on Industrial Electronics.

[5]  Canbing Li,et al.  Comprehensive review of renewable energy curtailment and avoidance: A specific example in China , 2015 .

[6]  Zhi-huan Song,et al.  Process Monitoring Based on Independent Component Analysis - Principal Component Analysis ( ICA - PCA ) and Similarity Factors , 2007 .

[7]  Jin Wang,et al.  Multivariate Statistical Process Monitoring Based on Statistics Pattern Analysis , 2010 .

[8]  Zhiqiang Ge,et al.  Sensor fault identification and isolation for multivariate non-Gaussian processes , 2009 .

[9]  Jian Huang,et al.  Angle-Based Multiblock Independent Component Analysis Method with a New Block Dissimilarity Statistic for Non-Gaussian Process Monitoring , 2016 .

[10]  Wencong Su,et al.  Stochastic Energy Scheduling in Microgrids With Intermittent Renewable Energy Resources , 2014, IEEE Transactions on Smart Grid.

[11]  Barry M. Wise,et al.  A comparison of principal component analysis, multiway principal component analysis, trilinear decomposition and parallel factor analysis for fault detection in a semiconductor etch process , 1999 .

[12]  Zhiqiang Ge,et al.  A distribution-free method for process monitoring , 2011, Expert Syst. Appl..

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

[14]  Moisès Graells,et al.  A semi-supervised approach to fault diagnosis for chemical processes , 2010, Comput. Chem. Eng..

[15]  Furong Gao,et al.  Batch process monitoring based on support vector data description method , 2011 .

[16]  Junichi Mori,et al.  A Gaussian mixture copula model based localized Gaussian process regression approach for long-term wind speed prediction , 2013 .

[17]  J. Marron,et al.  Smoothed cross-validation , 1992 .

[18]  David J. Sandoz,et al.  The application of principal component analysis and kernel density estimation to enhance process monitoring , 2000 .

[19]  Lei Liang-yu.  Research of Machine Fault Diagnosis Based on PCA and SVDD , 2006 .

[20]  Lei Xie,et al.  Statistical‐based monitoring of multivariate non‐Gaussian systems , 2008 .

[21]  Zhiqiang Ge,et al.  Bagging support vector data description model for batch process monitoring , 2013 .

[22]  S. Joe Qin,et al.  Process data analytics in the era of big data , 2014 .

[23]  ChangKyoo Yoo,et al.  Statistical process monitoring with independent component analysis , 2004 .

[24]  Jin Hyun Park,et al.  Process monitoring using a Gaussian mixture model via principal component analysis and discriminant analysis , 2004, Comput. Chem. Eng..

[25]  Richard A. Johnson,et al.  Applied Multivariate Statistical Analysis , 1983 .

[26]  Ping Zhang,et al.  A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process , 2012 .

[27]  Zhiqiang Ge,et al.  Fault detection in non-Gaussian vibration systems using dynamic statistical-based approaches , 2010 .

[28]  S. Qin,et al.  Multimode process monitoring with Bayesian inference‐based finite Gaussian mixture models , 2008 .

[29]  Dirk P. Kroese,et al.  Kernel density estimation via diffusion , 2010, 1011.2602.

[30]  Robert P. W. Duin,et al.  Support Vector Data Description , 2004, Machine Learning.

[31]  Zhiqiang Ge,et al.  Local ICA for multivariate statistical fault diagnosis in systems with unknown signal and error distributions , 2012 .

[32]  Manabu Kano,et al.  Monitoring independent components for fault detection , 2003 .

[33]  Zhiqiang Ge,et al.  Maximum-likelihood mixture factor analysis model and its application for process monitoring , 2010 .

[34]  Uwe Kruger,et al.  Improved principal component monitoring using the local approach , 2007, Autom..

[35]  Jin Wang,et al.  Statistics pattern analysis: A new process monitoring framework and its application to semiconductor batch processes , 2011 .