Get access
Advertisement

Kernel classifier with adaptive structure and fixed memory for process diagnosis

Authors

  • Haiqing Wang,

    Corresponding author
    1. National Lab of Industrial Control Technology, Zhejiang University, Hangzhou, 310027, China
    2. Institute of Automatic Control and Computer Systems, University of Duisburg-Essen, Bismarckstr. 81, BB-511, 47057 Duisburg, Germany
    • National Lab of Industrial Control Technology, Zhejiang University, Hangzhou, 310027, China
    Search for more papers by this author
  • Ping Li,

    1. National Lab of Industrial Control Technology, Zhejiang University, Hangzhou, 310027, China
    Search for more papers by this author
  • Furong Gao,

    1. Dept. of Chemical Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong
    Search for more papers by this author
  • Zhihuan Song,

    1. National Lab of Industrial Control Technology, Zhejiang University, Hangzhou, 310027, China
    Search for more papers by this author
  • Steven X. Ding

    Corresponding author
    1. Institute of Automatic Control and Computer Systems, University of Duisburg-Essen, 47057 Duisburg, Germany
    • Institute of Automatic Control and Computer Systems, University of Duisburg-Essen, 47057 Duisburg, Germany
    Search for more papers by this author

Abstract

A unified least-square kernel (ULK) framework is formulated for both process modeling and fault diagnosis issues. As a specific algorithmic implementation of the ULK method, an adaptive kernel learning (AKL) network classifier is developed for process diagnosis, which is a two-stage online learning algorithm with a fixed-memory strategy. A new concept of space angle index is proposed to structure the growth of node and actively control the complexity of the network. The AKL network performs a backward decreasing for forgetting an old pattern and a forward increasing for incorporating a new online pattern. The recursive algorithms for both stages are derived for quick online updating. Applications of the AKL network to two numerical cases and the Tennessee Eastman process show good performance in comparison to other established methods, and new insights on the pattern recognition for fault diagnosis arising from this flexible classifier are highlighted. © 2006 American Institute of Chemical Engineers AIChE J, 2006

Get access to the full text of this article

Ancillary