A systematic approach for soft sensor development

This paper presents a systematic approach based on robust statistical techniques for development of a data-driven soft sensor, which is an important component of the process analytical technology (PAT) and is essential for effective quality control. The data quality is obviously of essential significance for a data-driven soft sensor. Therefore, preprocessing procedures for process measurements are described in detail. First, a template is defined based on one or more key process variables to handle missing data related to severe operation interruptions. Second, a univariate, followed by a multivariate principal component analysis (PCA) approach, is used to detect outlying observations. Then, robust regression techniques are employed to derive an inferential model. A dynamic partial least squares (DPLS) model is implemented to address the issue of auto-correlation in process data and thus to provide smoother estimation than using a static regression model. The proposed methodology is illustrated through applications to a cement kiln system for estimation of variables related to product quality, i.e., free lime, and to emission quality, i.e., nitrogen oxides (NOx) emission. The case studies reveal the effectiveness of the systematic framework in deriving data-driven soft sensors that provide reasonably reliable one-step-ahead predictions.

[1]  S. J. Devlin,et al.  Robust Estimation of Dispersion Matrices and Principal Components , 1981 .

[2]  P. A. Taylor,et al.  Missing data methods in PCA and PLS: Score calculations with incomplete observations , 1996 .

[3]  Ana Casali,et al.  Particle size distribution soft-sensor for a grinding circuit , 1998 .

[4]  Babu Joseph,et al.  Inferential control of processes: Part I. Steady state analysis and design , 1978 .

[5]  J. E. Jackson,et al.  Control Procedures for Residuals Associated With Principal Component Analysis , 1979 .

[6]  Yu-Hong Zhao.  A soft sensor based on nonlinear principal component analysis , 2003, Proceedings of the 2003 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.03EX693).

[7]  Theodora Kourti,et al.  The Process Analytical Technology initiative and multivariate process analysis, monitoring and control , 2006, Analytical and bioanalytical chemistry.

[8]  B. Bequette,et al.  Product property and production rate control of styrene polymerization , 2002 .

[9]  Leo H. Chiang,et al.  Exploring process data with the use of robust outlier detection algorithms , 2003 .

[10]  Dirk C Hinz,et al.  Process analytical technologies in the pharmaceutical industry: the FDA’s PAT initiative , 2006, Analytical and bioanalytical chemistry.

[11]  Scott C. James,et al.  ON-LINE ESTIMATION IN BIOREACTORS: A REVIEW , 2000 .

[12]  Dale E. Seborg,et al.  Optimal selection of soft sensor inputs for batch distillation columns using principal component analysis , 2005 .

[13]  S. Qin,et al.  Self-validating inferential sensors with application to air emission monitoring , 1997 .

[14]  Ronald K. Pearson,et al.  Outliers in process modeling and identification , 2002, IEEE Trans. Control. Syst. Technol..

[15]  J. Macgregor,et al.  Development of inferential process models using PLS , 1994 .

[16]  J. P. Park.  The Identification Of Multiple Outliers , 2000 .

[17]  R. Ratcliff.  Methods for dealing with reaction time outliers. , 1993, Psychological bulletin.

[18]  Barry M. Wise,et al.  Adapting Multivariate Analysis for Monitoring and Modeling of Dynamic Systems , 1991 .

[19]  Denis Dochain,et al.  Dynamical modelling, analysis, monitoring and control design for nonlinear bioprocesses , 1997 .

[20]  Thomas J. McAvoy.  Intelligent “control” applications in the process industries , 2000 .

[21]  Dong Dong,et al.  Emission monitoring using multivariate soft sensors , 1995, Proceedings of 1995 American Control Conference - ACC'95.

[22]  Thomas Mc Avoy.  Intelligent “control” applications in the process industries , 2002 .

[23]  Abdul Rahman Mohamed,et al.  Neural networks for the identification and control of blast furnace hot metal quality , 2000 .

[24]  Amit Gupta,et al.  Estimating Missing Values Using Neural Networks , 1996 .

[25]  Thomas J. McAvoy,et al.  Nonlinear PLS Modeling Using Neural Networks , 1992 .

[26]  Chonghun Han,et al.  A nonlinear soft sensor based on multivariate smoothing procedure for quality estimation in distillation columns , 2000 .