Skip to main content
Article
Soft chemical analyzer development using adaptive least-squares support vector regression with selective pruning and variable moving window size
Industrial and Engineering Chemistry Research (2009)
  • Yi Liu, Zhejiang University
  • Naiping Hu
  • Haiqing Wang, Zhejiang University
  • Ping Li, Zhejiang University
Abstract

Soft analyzers have been increasingly accepted as an alternative to physical ones in the chemical industry to infer and improve the product quality. In this study, an adaptive least-squares support vector regression (ALSSVR) algorithm is proposed for the issue of nonlinear multi-input-multi-output process modeling and applied to soft chemical analyzer development. The ALSSVR algorithm adopts the moving window scheme and a two-stage recursive learning framework to trace the time-varying dynamics of a process. The useless sample (i.e., a node of analyzer model), while not the oldest one, is selectively deleted from the model topology, using the fast leave-one-out cross-validation criterion. Consequently, the updated model can exhibit good generalization ability and trace the process characteristics effectively. Besides, a variable moving window is proposed, so its size can be adaptively adjusted, relative to process changes. The ALSSVR-based soft analyzer is then applied to an industrial fluidized catalytic cracking unit to predict its three key product yields. The obtained results show that the presented ALSSVR method is superior to conventional recursive least-squares support vector regression (RLSSVR) approaches. The maximal root-mean-square error (RMSE) of all product yields is <1.5 and the maximal relative prediction error (RE) is ∼7%, which can be acceptable in industrial practice for the intended objective of soft analyzers.

Keywords
  • soft analyzers; least-squares support vector regression; online modeling; recursive algorithm; cross validation; moving window
Publication Date
Summer June 17, 2009
Citation Information
Yi Liu, Naiping Hu, Haiqing Wang and Ping Li. "Soft chemical analyzer development using adaptive least-squares support vector regression with selective pruning and variable moving window size" Industrial and Engineering Chemistry Research Vol. 48 Iss. 12 (2009)
Available at: http://works.bepress.com/inter_liu/3/