Sensorless induction motor drive with neural network

Abstract

The development and DSP implementation of AI-based speed estimator for applications in sensorless AC electrical drives are described in the paper. Rotor position and speed sensors are mostly required for vector control of induction motor. But there exist some applications in industry, where these sensors cannot be used. In the situations sensorless control technique should be used. In this paper rotor speed estimator are considered, which is based on a feedforward artificial neural network. It is demonstrated that such estimator, in contrast to conventional model-based approaches, does not depend on a knowledge of machine parameters. It is further shown that accurate estimates can be obtained in situation of varying load without the need for explicit load monitoring.