Adaptive Speed Control of PMSM Based on Wavelet Neural Network

There are many difficulties in control of permanent magnet synchronous motor (PMSM) owing to its highly nonlinearity and multivariable characteristics. If using the conventional controller, the uncertainty factors such as the variation of motor parameter and the load disturbance will influence the control precision. To solve this problem, this paper presents an approach of adaptive speed control for PMSM based on wavelet neural network (WNN). This approach takes advantage of the wavelet function with its approximating ability and fast convergence property. It constructs speed controller by the network that has been trained off-line and regulates network´s parameters in the course of controlling in order to adapt to the change of the environment. In addition, the system constructs another wavelet network to offer gradient parameters by on-line identification, which is used by the control network for its on-line study. The experiment results prove that this approach has lots of advantages such as fast response speed, high control precision and strong robustness.