An Efficient Multi-Objective Design Optimization Method for PMSLM Based on Extreme Learning Machine

This study focuses on the multi-objective design optimization of the permanent magnet synchronous linear motors (PMSLM), which are applied to high- precision laser engraving machine. A novel efficient multi-objective design optimization method for PMSLM is proposed to achieve optimal performance as indicated by high average thrust, low thrust ripple, and low total harmonic distortion (THD) at different running speeds. First, based on the finite element analysis (FEA) data, a regression machine learning algorithm, called extreme learning machine (ELM) is introduced to solve the calculation modeling problem by mapping out the nonlinear and complex relationship between input structural factors and output motor performances. Comparative simulation experiments conducted using the traditional analytical modeling method and another machine learning modeling method, i.e., support vector machine (SVM), confirm the superiority of ELM. Then, a new bionic intelligent optimization algorithm, called the grey wolf optimizer algorithm (GWOA), is applied to search the best optimization performance and structural parameters by performing iteration optimization calculation for multi-objective functions. Finally, FEA and prototype motor experiments prove the effectiveness and validity of the proposed method.