Neural Network Based Direct Adaptive Control of Permanent Magnet Synchronous Motor
Ashraf A. Hagras
electrical machines and drives
This paper proposes neural networks based direct adaptive state feedback control for the uncertain model of permanent magnet synchronous motor (PMSM). The proposed method used two types of neural networks (NN) to approximate the unknown model of PMSM; Backpropagation and Radial Basis Function (RBF) neural networks. Backpropagation (BP) and RBF neural network with single hidden layer were trained using MATLAB/NN Toolbox. The simulation results proved the effectiveness of the proposed method at various operating conditions. It exhibits considerable amount of torque ripples, adequate dynamic torque performance and improved speed response. Also, RBF neural network proved its superiority over backpropagation neural network in terms of faster speed and torque response at start up, steady state, step load disturbance and speed variations.
This article is written in Adobe PDF format ( .pdf file ).To view this article you need to download the file. Please rightclick on the link below and then select "Save
target as" to download the file to your harddrive.