Sensorless vector control of three phase induction motor based on full neural estimator and controller

Abstract EN

Conventional vector control of A.C drives are widely used in industry and many other applications, where high dynamic performance is required, this type of controller usually needs costly speed sensor.

Sensor less vector control is strongly recommended in the dangerous sites and hostile environment, also to reduce cost and increase reliability.

In this way the rotor speed can be estimated from the terminal voltage and current by means of DSP microprocessor.

The DSP-estimator is very complex hardware, has many operation problems, and very sensitive to the electromagnetic interference (EMI).

This paper proposes using the Artificial Neural Network (ANN) to estimate the rotor speed, flux vector, torque, and unit vectors instead of DSP-estimator.

Also, the neural-based controller is proposed too.

The ordinary vector control with speed sensor and sensor less vector control based on DSP-estimator PI-controller are represented in this work as point of comparison.

Also, the mathematical representation and simulation of the three phase induction motor is illustrated in this paper.

The proposed method, neural based sensor less vector controller and estimator, gives superior performance in different speed with respect to DSP-estimator PI-controller.