z-logo
Premium
Hybrid neural network models for environmental process control (The 1998 Hunter Lecture)
Author(s) -
De Veaux Richard D.,
Bain Rod,
Ungar Lyle H.
Publication year - 1999
Publication title -
environmetrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.68
H-Index - 58
eISSN - 1099-095X
pISSN - 1180-4009
DOI - 10.1002/(sici)1099-095x(199905/06)10:3<225::aid-env356>3.0.co;2-1
Subject(s) - artificial neural network , computer science , unobservable , extrapolation , interpolation (computer graphics) , a priori and a posteriori , hybrid system , process (computing) , stability (learning theory) , nonparametric statistics , mathematical optimization , machine learning , econometrics , artificial intelligence , mathematics , statistics , epistemology , operating system , motion (physics) , philosophy
A model that includes both first principles differential equations and an artificial neural network is used to forecast and control an environmental process. The inclusion of the first principles knowledge in this hybrid model is shown to improve substantially the stability of the model predictions in spite of the unmeasurability of some of the key parameters. The hybrid model estimates the unobservable parameters, and because of the constraints provided by the first principles equations, provides sensible extrapolations to the model. Thus, it can be used for process optimization as well as prediction. The hybrid model is compared with both a simple neural network with no a priori information, as well as some standard modern nonparametric statistical methods. For a variety of simulated parameter values, the hybrid model is shown to be comparable in predictive ability when used for interpolation and far superior when used for extrapolation. Copyright © 1999 John Wiley & Sons, Ltd.

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here