Optimized DTC by genetic speed controller and inverter based neural networks SVM for PMSM

A optimised speed controller for permanent magnet synchronous motor (PMSM) is investigated in this paper, in which genetic algorithm (GA), direct torque control (DTC) concept, and neural networks space vector modulation (NNSVM) are integrated to achieve high performance. A GA is integrated to optimize the proportional integral (PI) controller. While NNSVM is contributed to reduce more the ripples of mechanical speed and torque of PMSM, like that combination elements of artificial intelligence, proposed control reacts as, ensemble of intelligent human is gathered to solve a mathematical or physical problem in a little time than one of them. Simulation results show that the proposed controller provides high-performance dynamic characteristics and is robust with regard to plant parameter variations. Furthermore, comparing with the other controller, the harmonic ripples is much reduced by the proposed controller.