Abstract
This study presents a neural controller consisting of memory neurons for the purpose of real-time control problems in a class of linear systems. A rule is provided which updates weights of interconnections in the network. The dynamics of the memory neurons are subject to change; the resulting changes in system behavior are investigated. Simulation results show that neurocontroller performance varies with different desired output set-points. Furthermore, the dynamic neurocontroller containing memory neurons exhibits a greater step disturbance rejection capability than a static neurocontroller.
| Original language | English (US) |
|---|---|
| Pages | 643-648 |
| Number of pages | 6 |
| State | Published - 1992 |
| Externally published | Yes |
| Event | Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 - St.Louis, MO, USA Duration: Nov 15 1992 → Nov 18 1992 |
Other
| Other | Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 |
|---|---|
| City | St.Louis, MO, USA |
| Period | 11/15/92 → 11/18/92 |