Numerical Investigation of the Online Parameter Estimation Techniques for Interior Permanent Magnet Synchronous Machines

Abstract

This paper presents a new method to identify online four parameters of the interior permanent magnet synchronous motors (IPMSM), including stator resistance, d- axis inductance, q-axis inductance and permanent magnet. The proposed method is based on the neural network with the training data taken from experiments. The input data taken from experimental measurement were preprocessed before feeding to the input of the neural network model. The proposed online parameters estimation method is evaluated by comparing the estimation accuracy with other conventional online methods, such as Extended Kalman Filter, Recursive Least Square and the Adaline Neural Network. Extensive numerical simulations have been conducted to verify the effectiveness and the accuracy of the proposed method