Integrated soft sensor using just-in-time support vector regression and probabilistic analysis for quality prediction of multi-grade processes

Abstract Multi-grade processes have played an important role in the fine chemical and polymer industries. An integrated nonlinear soft sensor modeling method is proposed for online quality prediction of multi-grade processes. Several single least squares support vector regression (LSSVR) models are first built for each product grade. For online prediction of a new sample, a probabilistic analysis approach using the statistical property of steady-state grades is presented. The prediction can then be obtained using the corresponding LSSVR model if its probability of the special steady-state grade is large enough. Otherwise, the query sample is considered located in the transitional mode because it is not similar to any steady-state grade. In this situation, a just-in-time LSSVR (JLSSVR) model is constructed using the most similar samples around it. To improve the efficiency of searching for similar samples of JLSSVR, a strategy combined with the characteristics of multi-grade processes is proposed. Additionally, the similarity factor and similar samples of JLSSVR can be determined adaptively using a fast cross-validation strategy with low computational load. The superiority of the proposed soft sensor is first demonstrated through a simulation example. It is also compared with other soft sensors in terms of online prediction of melt index in an industrial plant in Taiwan.

[1]  Sirish L. Shah,et al.  Inferential sensors for estimation of polymer quality parameters: Industrial application of a PLS-based soft sensor for a LDPE plant , 2006 .

[2]  Haiqing Wang,et al.  Soft Chemical Analyzer Development Using Adaptive Least-Squares Support Vector Regression with Selective Pruning and Variable Moving Window Size , 2009 .

[3]  Luigi Fortuna,et al.  Soft Sensors for Monitoring and Control of Industrial Processes (Advances in Industrial Control) , 2006 .

[4]  Ping Li,et al.  Kernel classifier with adaptive structure and fixed memory for process diagnosis , 2006 .

[5]  S. Qin.  Recursive PLS algorithms for adaptive data modeling , 1998 .

[6]  Chonghun Han,et al.  Melt index modeling with support vector machines, partial least squares, and artificial neural networks , 2005 .

[7]  En Sup Yoon,et al.  Weighted support vector machine for quality estimation in the polymerization process , 2005 .

[8]  Tao Chen,et al.  Probabilistic contribution analysis for statistical process monitoring: A missing variable approach , 2009 .

[9]  Ping Li,et al.  Selective recursive kernel learning for online identification of nonlinear systems with NARX form , 2010 .

[10]  U. Kruger,et al.  Moving window kernel PCA for adaptive monitoring of nonlinear processes , 2009 .

[11]  Andrew W. Moore,et al.  Locally Weighted Learning , 1997, Artificial Intelligence Review.

[12]  Chonghun Han,et al.  Clustering-Based Hybrid Soft Sensor for an Industrial Polypropylene Process with Grade Changeover Operation , 2005 .

[13]  Bogdan Gabrys,et al.  Review of adaptation mechanisms for data-driven soft sensors , 2011, Comput. Chem. Eng..

[14]  Yeong-Koo Yeo,et al.  A recursive PLS-based soft sensor for prediction of the melt index during grade change operations in HDPE plant , 2009 .

[15]  Costas Kiparissides,et al.  Challenges in particulate polymerization reactor modeling and optimization: A population balance perspective , 2006 .

[16]  Zhiqiang Ge,et al.  Quality prediction for polypropylene production process based on CLGPR model , 2011 .

[17]  J. Berger.  Statistical Decision Theory and Bayesian Analysis , 1988 .

[18]  M. Birattari,et al.  Lazy learning for local modelling and control design , 1999 .

[19]  Xinggao Liu,et al.  Melt index prediction by weighted least squares support vector machines , 2006 .

[20]  Zengliang Gao,et al.  Just-in-time kernel learning with adaptive parameter selection for soft sensor modeling of batch processes , 2012 .

[21]  Jialin Liu,et al.  On-line soft sensor for polyethylene process with multiple production grades , 2007 .

[22]  Sirish L. Shah,et al.  Application of support vector regression for developing soft sensors for nonlinear processes , 2010 .

[23]  Jie Zhang,et al.  Inferential Estimation of Polymer Melt Index Using Sequentially Trained Bootstrap Aggregated Neural Networks , 2006 .

[24]  Tianhong Pan,et al.  Lazy learning-based online identification and adaptive PID control : A case study for CSTR process , 2007 .

[25]  Bogdan Gabrys,et al.  Data-driven Soft Sensors in the process industry , 2009, Comput. Chem. Eng..

[26]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[27]  Manabu Kano,et al.  Soft‐sensor development using correlation‐based just‐in‐time modeling , 2009 .

[28]  Luiz Augusto da Cruz Meleiro,et al.  ANN-based soft-sensor for real-time process monitoring and control of an industrial polymerization process , 2009, Comput. Chem. Eng..

[29]  Gavin C. Cawley,et al.  Preventing Over-Fitting during Model Selection via Bayesian Regularisation of the Hyper-Parameters , 2007, J. Mach. Learn. Res..

[30]  Xin Yang,et al.  Adaptive decentralized PID controllers design using JITL modeling methodology , 2012 .

[31]  Hiromasa Kaneko,et al.  Novel soft sensor method for detecting completion of transition in industrial polymer processes , 2011, Comput. Chem. Eng..

[32]  Hiromasa Kaneko,et al.  Development of Soft Sensor Models Based on Time Difference of Process Variables with Accounting for Nonlinear Relationship , 2011 .

[33]  M. Chiu,et al.  A new data-based methodology for nonlinear process modeling , 2004 .

[34]  Masahiro Ohshima,et al.  Quality control of polymer production processes , 2000 .

[35]  John R. Richards,et al.  Measurement and control of polymerization reactors , 2006, Comput. Chem. Eng..

[36]  Jie Yu,et al.  Online quality prediction of nonlinear and non-Gaussian chemical processes with shifting dynamics using finite mixture model based Gaussian process regression approach , 2012 .

[37]  Mudassir M. Rashid,et al.  A new dissimilarity method integrating multidimensional mutual information and independent component analysis for non-Gaussian dynamic process monitoring , 2012 .

[38]  Dale E. Seborg,et al.  Nonlinear internal model control strategy for neural network models , 1992 .

[39]  Morimasa Ogawa,et al.  The state of the art in chemical process control in Japan: Good practice and questionnaire survey , 2010 .

[40]  Min-Sen Chiu,et al.  Adaptive generalized predictive control based on JITL technique , 2009 .

[41]  Min-Sen Chiu,et al.  Nonlinear process monitoring using JITL-PCA , 2005 .

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

[43]  Bernhard Schölkopf,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.