Soft‐sensor development using correlation‐based just‐in‐time modeling

Soft-sensors have been widely used for estimating product quality or other key variables, but their estimation performance deteriorate when the process characteristics change. To cope with such changes, recursive PLS and Just-In-Time (JIT) modeling have been developed. However, recursive PLS does not always function well when process characteristics change abruptly and JIT modeling does not always achieve the high-estimation performance. In the present work, a new method for constructing soft-sensors based on a JIT modeling technique is proposed. In the proposed method, referred to as correlation-based JIT modeling (CoJIT), the samples used for local modeling are selected on the basis of the correlation among measured variables and the model can adapt to changes in process characteristics. The usefulness of the proposed method is demonstrated through a case study of a CSTR process, in which catalyst deactivation and recovery are taken into account. In addition, its industrial application to a cracked gasoline fractionator is reported. © 2009 American Institute of Chemical Engineers AIChE J, 2009

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

[2]  Manabu Kano,et al.  Inferential control system of distillation compositions using dynamic partial least squares regression , 1998 .

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

[4]  Yoshihiro Hashimoto,et al.  Nonlinear Systems Approximation Using a Piecewise Affine Model Based on a Radial Basis Functions Network , 2006 .

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

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

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

[8]  S. Skogestad,et al.  Estimation of distillation compositions from multiple temperature measurements using partial-least-squares regression , 1991 .

[9]  Manabu Kano,et al.  A new multivariate statistical process monitoring method using principal component analysis , 2001 .

[10]  Manabu Kano,et al.  Two-stage subspace identification for softsensor design and disturbance estimation , 2009 .

[11]  Manfred Morari,et al.  A clustering technique for the identification of piecewise affine systems , 2001, Autom..

[12]  N. L. Ricker.  The use of biased least-squares estimators for parameters in discrete-time pulse-response models , 1988 .

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

[14]  Jay H. Lee,et al.  Subspace identification based inferential control applied to a continuous pulp digester , 1999 .

[15]  Manabu Kano,et al.  Product Quality Estimation and Operating Condition Monitoring for Industrial Ethylene Fractionator , 2004 .

[16]  Morimasa Ogawa,et al.  Practice and Challenges in Chemical Process Control Applications in Japan , 2008 .

[17]  Manabu Kano,et al.  Statistical process monitoring based on dissimilarity of process data , 2002 .

[18]  Manabu Kano,et al.  Data-based process monitoring, process control, and quality improvement: Recent developments and applications in steel industry , 2008, Comput. Chem. Eng..

[19]  Ali Cinar,et al.  Statistical process monitoring and disturbance diagnosis in multivariable continuous processes , 1996 .

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

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

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