Adaptive Model-Based Control of Non-Linear Dynamical Systems with a Neuro-Fuzzy-Genetic Approach
We describe in this paper different hybrid intelligent approaches for controlling non-linear dynamical systems in manufacturing applications. The hybrid approaches combine soft computing techniques and mathematical models to achieve the goal of controlling the manufacturing process to follow a desir...
Saved in:
| Published in: | International journal of smart engineering system design Vol. 4; no. 1; pp. 41 - 47 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
01.01.2002
|
| ISSN: | 1025-5818, 1607-8500 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | We describe in this paper different hybrid intelligent approaches for controlling non-linear dynamical systems in manufacturing applications. The hybrid approaches combine soft computing techniques and mathematical models to achieve the goal of controlling the manufacturing process to follow a desired production plan. We have developed several hybrid architectures that combine fuzzy logic, neural networks, and genetic algorithms, to compare the performance of each of these combinations and decide on the best one for our purpose. We consider the case of controlling non-linear electrochemical processes to test our hybrid approach for control. Electrochemical processes, like the ones used in battery formation, are complex and for this reason difficult to control. We have achieved good results using fuzzy logic for control, neural networks for modeling the process, and genetic algorithms for tuning the hybrid intelligent system. We have compared our neuro-fuzzy-genetic approach for control with the classical PID control, and our approach is clearly superior in controlling the non-linear dynamical process. |
|---|---|
| Bibliography: | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 |
| ISSN: | 1025-5818 1607-8500 |
| DOI: | 10.1080/10255810210626 |