Abstract:
Permanent Magnet Synchronous Motor Drives are highly efficient, high speed drives which are used extensively in many applications. The main aim of this thesis is to develop an intelli-gent controller for the speed control of a permanent magnet synchronous motor(PMSM), which reduces the uncertainties and effect of load disturbances while maintaining the performance with respect to speed, torque and stator current.In order to achieve this level of intelligence, this thesis . investigates how to unify and hybridize many softcomputing techniques including Fuzzy logic,Neurocomputing, Genetic algorithms. First learning capabilities of neurocomputing are explored in interaction with environment and knowledge acquisition.An adaptive Neural Network based Model reference controller is proposed for the control of the parameters of the PMSM.Secondly knowledge tuning of fuzzy logic systems are developed through knowledge-based' and Neuro-fuzzy approaches. An Interval Type-2 Fuzzy Logic Controller(FLC) is pro-posed and adaptive Neuro Fuzzy Based Inference System(ANFIS) for the control of synchronous motor. Thirdly an hybrid approach in the learning of a fuzzy logic system is explored using Particle Swarm Optimization(PSO).These applications are analyzed for the PMSM using digi-tal simulation.The results of the application show the capabilities of the proposed algorithms, i.e., the type-2 FLC and PSO based optimizers in dealing with complex uncertain problems and robust, simple viable and visible solutions offered by soft computing techniques for such nonlinearities.
