Adaptive neuro-fuzzy current control for multilevel inverter fed induction motor

Abstract

Purpose - The paper aims to propose an adaptive and robust on-line trained neuro-fuzzy current controller based on indirect field oriented control (IFOC) for the current control of multilevel inverter fed induction motor (IM). Design/methodology/approach - Torque current of IM is controlled with Sugeno type neuro-fuzzy controller (NFC) which has the ability of self tuning against parameter variations and load disturbance. Input variables of the neuro-fuzzy current controller are chosen error and integral of error in order to eliminate steady state error. The consequent parameters of neuro-fuzzy current controller are trained on-line through backpropagation learning algorithm. Findings - The validity of proposed current control algorithm is shown with experimental results carried out under different speed commands, parameter variations and load disturbances. The experimental results show that control performance of NFC in the current control of IMs is satisfactory because of its adaptive and robust structure. Originality/value - This paper presents the design of an on-line trained neuro-fuzzy current control to improve the current control performance. The performance of the current controller largely depends on using converter systems. In this study, a multilevel inverter is used to obtain less harmonic distortion and near sinusoidal form of output voltage and current waveforms of the converter.