Partial least squares regression for recursive system identification

Industrial processes usually involve a large number of variables, many of which vary in a correlated manner. To identify a process model which has correlated variables, an ordinary least squares approach demonstrates ill-conditioned problem and the resulting model is sensitive to changes in sampled data. In this paper, a recursive partial least squares (PLS) regression is used for online system identification and circumventing the ill-conditioned problem. The partial least squares method is used to remove the correlation by projecting the original variable space to an orthogonal latent space. Application of the proposed algorithm to a chemical processing modeling problem is discussed.<<ETX>>

[1]  K. Helland,et al.  Recursive algorithm for partial least squares regression , 1992 .

[2]  U. Schulze Math.operationsforsch.u.statist.,ser.statist , 1984 .

[3]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[4]  Barry M. Wise,et al.  THE EFFECT OF BIASED REGRESSION ON THE IDENTIFICATION OF FIR AND ARX MODELS , 1990 .

[5]  C. R. Cutler,et al.  Dynamic matrix control¿A computer control algorithm , 1979 .

[6]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[7]  M. Stone Continuum regression: Cross-validated sequentially constructed prediction embracing ordinary least s , 1990 .

[8]  R. Manne Analysis of two partial-least-squares algorithms for multivariate calibration , 1987 .

[9]  G. L. Ritter,et al.  Partial Least-Squares Quantitative Analysis of Infrared Spectroscopic Data. Part I: Algorithm Implementation , 1988 .

[10]  Svante Wold,et al.  Partial least-squares method for spectrofluorimetric analysis of mixtures of humic acid and lignin sulfonate , 1983 .

[11]  A. Höskuldsson PLS regression methods , 1988 .

[12]  L. Ljung,et al.  Issues in system identification , 1991, IEEE Control Systems.

[13]  S. Wold,et al.  The Collinearity Problem in Linear Regression. The Partial Least Squares (PLS) Approach to Generalized Inverses , 1984 .

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

[15]  M. Stone Cross-validation:a review 2 , 1978 .

[16]  E. V. Thomas,et al.  Partial least-squares methods for spectral analyses. 1. Relation to other quantitative calibration methods and the extraction of qualitative information , 1988 .

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