MRAS-Based Sensorless Control of a Five-Phase Induction Motor Drive With a Predictive Adaptive Model

Multi-phase ac motor drives are nowadays considered for various applications, due to numerous advantages that they offer when compared to their three-phase counterparts. Variable speed induction motor drives without mechanical speed sensors at the motor shaft have the attractions of low cost and high reliability. This paper analyses operation of a Model Reference Adaptive System (MRAS)-based sensorless control of vector controlled five-phase induction machine. A linear neural network is designed and trained online by means of back propagation network (BPN) algorithm. Moreover, the neural adaptive model is employed here in prediction mode and in simulation mode. The ANN-MRAS-based sensorless operation of a three-phase induction machine is well established and the same principle is extended in this paper for a five-phase induction machine. Performance, obtainable with hysteresis current control, is illustrated for a number of operating conditions on the basis of simulation results. The results obtained with prediction and simulation mode are compared on the basis of various parameters. Full decoupling of rotor flux control and torque control is realised in both predictive and simulation mode. However, predictive method is shown to provide better dynamics.