| Abstract |
The design, simulation and DSP implementation of
AI-based speed estimator for applications in sensorless ac
electrical drives are described in the paper. Speed sensors are
mostly used to obtain rotor speed or position information in the
field of ac electrical drives. These sensors are sources of trouble,
and there exists some applications in industry, where they
cannot be used. The mentioned reasons lead to the development
of sensorless control techniques. In this paper ANN-based rotor
speed estimator is considered, which is based on a feedforward
artificial neural network. It is shown that the estimator, in
contrast to conventional model-based methods, does not depend
on knowledge of the motor under consideration. It is further
shown that accurate estimates can be obtained in situations of
varying load without the need for explicit load monitoring. The
estimator was implemented into DSP TMS 320C40, which
controls a drive with a 2.7 kW induction motor. |
