Kohonen's Self Organizing Map method of estimation of optimal parameters of a Permanent Magnet Synchronous Motor drive

PMSM drives are the upcoming drives nowadays as these have many advantages such as high efficiency, high speed, high torque to inertia ratio, high torque to current ratio etc., The estimation of PMSM drive parameters is an important consideration in their field. Many methods are available for this. However the optimal way to estimate the parameters is normally preferred making use of neural networks is one of the best ways to achieve this. This paper proposes an unsupervised learning method i.e., Kohonen's Self Organizing Feature Map method of estimation of PMSM drives is presented. Since the method makes use of `winner takes all' of a neuron, the values obtained by this, will be the optimal values. The drive is first simulated and the parameters obtained are used for training the ANN. The Unsupervised learning method is the Kohonen's Self Organizing Feature Map method, which is used for the estimation of the PMSM drive. The parameters estimated are the currents and fluxes in the two axis model which are further used for the estimation of torque, fluxes and the unit vectors. Because of the unsupervised learning, it can be stated that the estimated values are the best or the optimal values. MATLAB/Simulink is used for the simulation and the results are shown.