Abstract
This paper presents an artificial-neural-network-based direct-self-control (ANN-DSC) scheme for an inverter-fed three-phase induction motor. In order to cope with the complex calculations required in direct self control (DSC), the proposed artificial-neural-network (ANN) system employs the individual training strategy with fixed-weight and supervised models. A computer simulation program is developed using Matlab/Simulink together with the Neural Network Toolbox. The simulated results obtained demonstrate the feasibility of ANN-DSC. Compared with the classical digital-signal-processor-based DSC, the proposed ANN-based scheme incurs much shorter execution times and, hence, the errors caused by control time delays are minimized.
Original language | English |
---|---|
Pages (from-to) | 1290-1298 |
Number of pages | 9 |
Journal | IEEE Transactions on Industry Applications |
Volume | 37 |
Issue number | 5 |
DOIs | |
Publication status | Published - 1 Sep 2001 |
Keywords
- Direct self control
- Induction motor drive
- Matlab/Simulink
- Neural networks
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Engineering (miscellaneous)