Authors: Abdel Ghani Aissaoui; Mohamed Abid; Ahmed Tahour; Ahmed Chaouki Megherbi
Addresses: IRECOM Laboratory, Faculty of Engineering, University Djillali Liabès, B.P 89, Sidi Bel Abbès, 22000, Algeria ' IRECOM Laboratory, Faculty of Engineering, University Djillali Liabès, B.P 89, Sidi Bel Abbès, 22000, Algeria ' Electrical Department, Faculty of Science and Technology, University of Mascara, route Mamounia, Mascara 29000, Algeria ' Electrical Department, Faculty of Science and Technology, University of Biskra, B.P. 145 R.P, Biskra 07000, Algeria
Abstract: The application of artificial intelligence has become an important topic in electrical machines control. This paper presents an application of neuro-fuzzy (NF) control for synchronous motor (SM) speed. The NF has the advantages of expert knowledge of the fuzzy inference system and the learning capabilities of neural networks. A neuro-fuzzy controller of the motor speed is then designed and simulated. An asymptotically stable observer is designed to overcome the problem of speed sensor and is obtained without affecting the overall system response. Digital simulation results show that the designed NF speed controller realises a good dynamic behaviour of the motor, a perfect speed tracking with no overshoot and a good rejection of load disturbances.
Keywords: neuro-fuzzy control; synchronous motors; speed control; speed observer; artificial intelligence; ANFIS; sliding mode observer; electrical machines; neural networks; fuzzy logic; fuzzy control; adaptive neuro-fuzzy inference system; simulation.
International Journal of Artificial Intelligence and Soft Computing, 2015 Vol.5 No.1, pp.3 - 22
Accepted: 10 Nov 2013
Published online: 12 Feb 2015 *