Sensorless-speed control strategy of induction motor based on artificial neural networks

This paper presents a neural network adaptive PID controller for speed sensorless field-oriented control of induction motor. By measuring the phase voltages and currents in induction motor(IM) drive, the multi-step predictive control, neural networks based rotor flux components and speed identification method for IM are used. The proposed neural network adaptive PID controller includes two neural networks, one is used to identify rotor flux and speed, and the other is used to control the speed of IM. Using multi-step algorithm, on-line adaptive identification and control are realized. The simulation results show high accuracy of the control algorithms, and verify the usefulness of the algorithm.