A novel speed identification method of induction motor based ANFIS

Abstract

One of the most important technologies for electric vehicles is the drive control technology which does not require a position or speed sensor. In a sensorless vector controlled induction machine, the speed must be indentified from the system. Most of the sensorless control techniques are dependent on motor parameters, such as stator resistance, inductance, and torque constant. Thus, the performance suffers greatly in harsh and highly dynamic operating conditions, where the motor parameters are changing. Model Reference Adaptive System (MRAS) based techniques are one of the best methods to estimate the rotor speed due to its performances and straight forward stability approach. But, the performance of MRAS deteriorates during transients, speed variations and load variations due to integrator drift and sensitivity to parameter variation. In this paper, a novel strategy of adaptive network-based fuzzy inference system (ANFIS) sensorless observers based on model reference adaptive system (MRAS) is proposed. This strategy replaces the traditional model of MRAS adaptive architecture and adaptive machine with ANFIS controller which aims at well adapting to changes in parameters and states by making use of ANFIS adaptive ability and self-learning ability in non-linear system. Further, a detailed comparative simulation and experimental study is carried out for ANFIS and conventional MRAS observers. The experimental results demonstrate that the proposed strategy is effective and has practical value.