Real-time implementation of on-line trained neuro-controller for a BLDC motor

M.M. Salem; Y. Atia; M.B. Zahran; A.M. Zaki; ieee

doi:10.1109/ICMECH.2004.1364429

Back

Conference proceeding

Real-time implementation of on-line trained neuro-controller for a BLDC motor

M.M. Salem, Y. Atia, M.B. Zahran, A.M. Zaki and ieee

Proceedings of the IEEE International Conference on Mechatronics, 2004. ICM '04, pp.154-158

2004

DOI: https://doi.org/10.1109/ICMECH.2004.1364429

Abstract

Adaptive control

Artificial neural networks

Automatic control

Brushless DC motors

Control systems

Control theory

DC motors

Feedforward neural networks

Neural networks

Uncertainty

Implementation and experimental verification of a simple neuro-controller (SNC) as a speed controller for a BLDC motor is presented. The SNC with one weight and a linear hard limit activation function is trained on-line using the back propagation algorithm. A modified error function is used to ensure good performance during the on-line training, which has been used without previous off-line training. The SNC has been implemented using a computer-interface card mounted on a PC. The driving system performance has been investigated by a number of experimental tests for a variety of input reference speed trajectories.

Metrics

1 Record Views

Details

Title: Real-time implementation of on-line trained neuro-controller for a BLDC motor
Creators - without role: M.M. Salem - Electron
Y. Atia - Electron
M.B. Zahran - Electron
A.M. Zaki - Electron
ieee
Publication Details: Proceedings of the IEEE International Conference on Mechatronics, 2004. ICM '04, pp.154-158
Publisher: IEEE
Identifiers: 9917210008331
Academic Unit: Jazan University
Language: English
Resource Type: Conference proceeding