Application of adaptive neuro-fuzzy controller (ANFIS) for voltage source inverter fed induction motor drive

Abstract

The fuzzy logic controllers with their inherent advantages are implemented for various applications. This paper describes the application of adaptive neuro-fuzzy logic based speed control of induction motor drive. The Conventional PI/PID controller is replaced by fuzzy controller in speed control loop. Adaptive neuro-fuzzy inference system (ANFIS) which tunes the fuzzy inference system with a backpropagation algorithm based on collection of input-output data is implemented. This enables the fuzzy system to learn. This training is given from a standard response data of the system and membership functions are suitably modified. The design of this ANFIS based fuzzy controller is presented. Simulation study indicates the superiority of fuzzy controllers over the conventional control method. The modified ANFIS controller is implemented using DSP. The test results are presented. The major advantage of the ANFIS based FLC system is to improve the system robustness.