Title :
A comparison of nonlinear techniques for the identification of dynamic models
Author :
Holt, Bradley ; Gallagher, N.B. ; Lee, S.E.
Author_Institution :
Dept. of Chem. Eng., Washington Univ., Seattle, WA
Abstract :
A variety of nonlinear dynamic modeling techniques were tested on data from a real pilot scale apparatus. The models were tested for their ability to model the system, interpolate and extrapolate to regions outside the modeling set, and to function in the presence of noise. An artificial neural network with linear terms was found to perform as good or better than the other techniques on this data. An input transformation method using a genetic algorithm to select the transformation structure and regression to determine the parameters was able to perform equally well with less computation effort. The nonlinear biased regression techniques did not perform as well though they required less computation and the results were reproducible
Keywords :
feedforward neural nets; genetic algorithms; identification; least squares approximations; modelling; nonlinear systems; direct linear feed-through neural network; extrapolation; genetic algorithm; identification; input transformation; interpolation; nonlinear biased regression; nonlinear dynamic modeling; nonlinear systems; Artificial neural networks; Chemical technology; Feedforward neural networks; Genetic algorithms; Instruments; Least squares methods; Neural networks; Nonlinear dynamical systems; System testing; Training data;
Conference_Titel :
American Control Conference, Proceedings of the 1995
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-2445-5
DOI :
10.1109/ACC.1995.531210