Design optimization of permanent magnet synchronous linear motor by multi-SVM

Abstract

The thrust fluctuation is one of the most important problems to influence the performance of the permanent magnet linear motor, a method which optimizes the motor structure parameters to control the thrust ripple thoroughly was proposed. The multiple support vector machines was used to establish the non-linear relation model of motor structural parameters with cogging force harmonic characteristics, the non-linear model was then repeatedly used to optimize the motor structure parameters by decision-tree method. The simulation and experiment of a double secondary permanent magnet synchronous linear motor indicates that, with the use of this method, by optimize the motor structure parameters, the thrust fluctuation rate can be reduced.