Dynamic Neuro-Fuzzy Control of the Nonlinear Process
Abstract
This research combines the dynamic neural networks with the fuzzy associative memory (FAM) to find a better model for nonlinear control problems. The proposed model consists of three major parts: the action networks, the critic networks and the fuzzy membership adjustment procedure. The dynamic neural networks are used as the main controller of the system. The FAM determines the performance of the main controller and sends the correction signal back to the neural networks. The function of the fuzzy membership adjustment procedure is to improve the quality of the FAM output. The proposed model is tested on real-life processes, and satisfactory results are obtained. © 1997 Elsevier Science Ltd.
Recommended Citation
G. Sun et al., "Dynamic Neuro-Fuzzy Control of the Nonlinear Process," Computers and Industrial Engineering, vol. 33, no. 1 thru 2, pp. 413 - 416, Elsevier, Jan 1997.
The definitive version is available at https://doi.org/10.1016/s0360-8352(97)00125-3
Department(s)
Engineering Management and Systems Engineering
International Standard Serial Number (ISSN)
0360-8352
Document Type
Article - Journal
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2024 Elsevier, All rights reserved.
Publication Date
01 Jan 1997
