Torque and speed estimator for induction motor using parallel neural networks and sensorless technology

Many electronic drivers for induction motor control are based on sensorless technologies. The proposal of this work is to present an efficient torque and speed estimator for induction motor steady state operations by using artificial neural networks. The proposed method is based on off-line training which considers different types of loads and a wide range of supply voltage. The inputs of the network are the induction motor RMS voltage and current. Besides, the estimation processing effort is reduced to a simple matrix solving after the neural network is trained. Simulation and experimental results are also presented to validate the proposed approach.