Wavelet-based density estimation and application to process monitoring

Authors

  • A. A. Safavi,

    1. ICI Process Systems Engineering Laboratory, Dept. of Chemical Engineering, The University of Sydney, NSW 2006, Australia
    Search for more papers by this author
  • J. Chen,

    1. ICI Process Systems Engineering Laboratory, Dept. of Chemical Engineering, The University of Sydney, NSW 2006, Australia
    Search for more papers by this author
  • J. A. Romagnoli

    Corresponding author
    1. ICI Process Systems Engineering Laboratory, Dept. of Chemical Engineering, The University of Sydney, NSW 2006, Australia
    • ICI Process Systems Engineering Laboratory, Dept. of Chemical Engineering, The University of Sydney, NSW 2006, Australia
    Search for more papers by this author

Abstract

An application of wavelets and multiresolution analysis to density estimation and process monitoring is presented. Wavelet-based density-estimation techniques are developed as an alternative and superior method to other common density-estimation techniques. Also shown is the effectiveness of wavelet estimators when the observations are dependent. The resulting density estimators are then used in defining a normal operating region for the process under study so that any abnormal behavior by the process can be monitored. Results of applying these techniques to a typical multivariate chemical process are also presented.

Ancillary