ANFIS based Field Oriented Control for Matrix Converter fed Induction Motor

This paper presents a novel Adaptive Neural Fuzzy Inference System (ANFIS) based Matrix Converter for speed control of Induction Motor. The proposed ANFIS consists of fuzzy logic controller algorithm with a five layer Artificial Neural Network. The ANFIS system tunes the fuzzy system with hybrid learning algorithm and hence generates the reference voltage. The reference voltage is used to generate the duty cycle for matrix converter switches. The matrix converter is designed using Venturini algorithm and results are shown under different switching frequencies. The ANFIS based Field Oriented Controller circuit is designed using MATLAB/SIMULINK and its performance is investigated under different reference speed and torque conditions. The conventional PI controller based matrix converter drive and ANFIS controller based matrix converter drive is designed. Their speed and torque performance are compared. The simulation study indicates the robustness and suitability of ANFIS controller based matrix converter drive for high performance applications.