Speed-Sensorless Vector Control Based on ANN MRAS for Induction Motor Drives

Abstract

In the speed-sensorless induction motor drives system, Model Reference Adaptive System (MRAS) is the most common strategy. However, speed estimation using reactive power based MRAS has the problem of instability in the regenerating mode of operation. Such estimation technique is simple and has several notable advantages, but is not suitable for induction motor drives. To overcome these problems, a suitable Artificial Neural Networks (ANN) is presented to replace the adjustable model to make the system stable when working at low speed and zero crossing. Simultaneously, in order to enhance the ANN convergence speed and avoid the trap of local minimum value of algorithm, we used the modified Particle Swarm Optimization (PSO) to optimize the weights and threshold values of neural networks. Then the ANN-based MRAS was used to identify the speed of motor in the indirect vector control system. The results of the simulation show that, by this method, the speed of motor can be identified accurately in different situations, and the result is reliable.