Share Email Print
cover

Proceedings Paper

Comparative analysis of two evolved neural networks used for the identification and control of a nonlinear plant
Author(s): Hector Erives; Wiley E. Thompson
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents a comparative analysis of two evolved neural networks for control. Traditionally, the structure of Radial Basis Functions Networks (RBFNs) and Multilayer Feedforward Networks (MFNs) are found by a trial-and-error process. This process consists on finding an appropriate network structure such that the unknown nonlinearities of the plant can be estimated to some desired accuracy. In general, a neural network is composed of two elements: structural and learning parameters. The structural parameters are all those elements that determine the size of the network. The learning parameters are all those elements that determine learning and convergence of the network. The approach presented in this work uses a Genetic Algorithm (GA) to evolve the structure, and uses a gradient descent algorithm to adjust the weights in the network. An analysis of the evolution of RBFNs and MFNs by means of a GA is examined in detail. It is shown that the networks can be encoded in a chromosome for their evolution. Experimental results show the performance of Evolved Radial Basis Functions Networks and Evolved Multilayer Feedforward Networks in the identification and control of a nonlinear plant.

Paper Details

Date Published: 28 July 1997
PDF: 8 pages
Proc. SPIE 3068, Signal Processing, Sensor Fusion, and Target Recognition VI, (28 July 1997); doi: 10.1117/12.280816
Show Author Affiliations
Hector Erives, Opto-Knowledge Systems, Inc. (United States)
Wiley E. Thompson, New Mexico State Univ. (United States)


Published in SPIE Proceedings Vol. 3068:
Signal Processing, Sensor Fusion, and Target Recognition VI
Ivan Kadar, Editor(s)

© SPIE. Terms of Use
Back to Top