Partial Least Squares

  • Evan L. Russell
  • Leo H. Chiang
  • Richard D. Braatz
Part of the Advances in Industrial Control book series (AIC)

Abstract

Partial Least Squares (PLS), also known as Projection to Latent Structures, is a dimensionality reduction technique for maximizing the covariance between the predictor (independent) matrix X and the predicted (dependent) matrix Y for each component of the reduced space [61, 235]. A popular application of PLS is to select the matrix Y to contain only product quality data which can even include off-line measurement data, and the matrix X to contain all other process variables [144]. Such inferential models (also known as soft sensors) can be used for the on-line prediction of the product quality data [149, 155, 156], for incorporation into process control algorithms [106, 181, 182], as well as for process monitoring [144, 181, 182]. Discriminant PLS selects the matrix X to contain all process variables and selects the Y matrix to focus PLS on the task of fault diagnosis [26].

Keywords

Covariance 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag London 2000

Authors and Affiliations

  • Evan L. Russell
    • 1
  • Leo H. Chiang
    • 2
  • Richard D. Braatz
    • 2
  1. 1.Exxon Production Research CompanyHoustonUSA
  2. 2.Department of Chemical EngineeringUniversity of Illinois at Urbana-ChampaignUrbanaUSA

Personalised recommendations