PM Synchronous Motor Control Strategies With Their Neural Network Regression Functions

This paper proposes Surface Permanent Magnet Synchronous Motor (SPMSM) Control Strategies with Their Neural Network Regression Functions. Because the torque angle control provides a wide variety of control choices in the PMSM drive system. Vector control of PMSM allows for the implementation of several choices of control strategies while control over torque is retained. Each of these control strategies are described and analyzed in this paper. All motor characteristics for all control techniques are introduced in the form of comparisons with such corresponding ones at rated conditions. The required terminal voltage to drive the motor at any prescribed technique is predicted. Then a brief description about Artificial Neural Network ANN; is illustrated to be used for predicting the required voltage to drive the motor at the desired control techniques for set of relations at various frequencies values under the base one. This is done to use the ability of neural network for interpolation with suitable number of layers and neurons. Finally, algebraic equations for each neural network case are presented to be used without the need of turning the neural models at each time.