Neuro Fuzzy Controller Based Direct Torque Control for SRM Drive

Abstract

The integration of neural networks and fuzzy inference system could be formatted into three main categories: cooperative, concurrent and integrated neuro-fuzzy models namely fuzzy associative memories fuzzy rules extraction using self-organizing maps and systems capable of learning fuzzy set parameters. Mamdani and Takagi-Sugeno type integrated neuro-fuzzy systems were further introduced with a focus on some of the salient features and advantages of the different types of integrated neuro-fuzzy models that have been evolved during last decade. This work focus on the implementation of integrated neuro-fuzzy systems also called hybrid controllers. The Mamdani and Sugeno hybrid controllers are incorporated along with direct torque control to generate more accurate voltage space vectors. This helps in controlling the torque ripple and reduce its amplitude to a great extend. The detail description is given in the following sections. MATLAB design is done with the help of MATLAB Compilers from Math works and the results prove the better control of SRM with reduced torque and flux ripples.