Lumped Disturbance Compensation using Extended Kalman Filter for Permanent Magnet Linear Motor System

In this paper, an extended Kalman filter is designed and applied to a feed-forward based lumped disturbance compensator which consists of position dependent functions for a permanent magnet linear synchronous motor system. In our previous research, a lumped disturbance model including the force ripple and the Coulomb friction force was developed and utilized as a feed-forward controller. To improve the performance of that model, following two studies are conducted. First, an initial position estimator is designed to create synchronization between the model and real disturbance. This step is necessary because almost all linear motor systems are equipped with an incremental encoder for position measurement. Second, to cancel out a slight variation in real disturbance, an adaptive controller in the form of coefficients adaptation is designed. These two studies are combined by a sixth order extended Kalman filter. To make a comparison, a recursive least squares filter and disturbance observer and its modified version are prepared. The effectiveness of the proposed scheme is verified by the overall disturbance shape, RMS position error and FFT analysis on the position error.