A diagonally recurrent neural network approach to sensorless operation of the permanent magnet synchronous motor

Rotor position sensorless control of the permanent magnet synchronous motor (PMSM) typically requires knowledge of the PMSM structure and parameters, which in some situations are not readily available or may be difficult to obtain. Due to this limitation, an alternative approach to rotor position sensorless control of the PMSM using a diagonally recurrent neural network (DRNN) is considered. The DRNN is a dynamic mapping, requires fewer neurons, and converges quickly compared to feedforward and fully recurrent neural networks. Experimental results of the proposed neural observer to PMSM rotor estimation are presented