A Novel Regression Modeling Method for PMSLM Structural Design Optimization Using a Distance-Weighted KNN Algorithm

This paper investigates the modeling methods for the structural design optimization of permanent magnet synchronous linear motors (PMSLMs), which are applied to linear motion machines. First, an initial PMSLM model is established by finite element analysis (FEA), and the data space is obtained for subsequent rapid regression modeling. Second, a powerful regression machine learning method, that is, distance-weighted K-nearest neighbor algorithm (DW-KNNA), is introduced to establish a calculation model by grasping the nonlinear relationships between input structural parameters and output motor performances. Model comparison experiments among analytical method, response surface method, K-nearest neighbor algorithm, and DW-KNNA demonstrate the superiority of the DW-KNNA. Finally, the differential evolution algorithm is used to determine the best combination of structural parameters and performances. The FEA and prototype motor experiments proved the validity and advantages of the proposed method.