Abstract
An artificial feedforward neural network is used for on-line control of a certain class of partially known single-input, single-output dynamic systems. The neural network's task is to provide an approximation of the unknown input-output behavior of the dynamic system to the controller in order to drive the system's behaviour according to specifications given by a reference model. The error correction-based learning algorithm used to update the weights of the single layer neural network used in the control scheme allows dynamic adjustment of their values to cope with varying signals coming from the dynamic plant.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 1453-1457 |
| Number of pages | 5 |
| Journal | Proceedings of the IEEE International Conference on Systems, Man and Cybernetics |
| Volume | 2 |
| State | Published - 1994 |
| Externally published | Yes |
| Event | Proceedings of the 1994 IEEE International Conference on Systems, Man and Cybernetics. Part 1 (of 3) - San Antonio, TX, USA Duration: Oct 2 1994 → Oct 5 1994 |
ASJC Scopus subject areas
- Control and Systems Engineering
- Hardware and Architecture