Neuro Fuzzy Estimation of the Optimal Parameters for Prediction of Permanent Magnet Synchronous Motor (PMSM) Temperature

Abstract

Introduction: One of the most popular electric motors for traction drive applications is permanent magnet synchronous machine (PMSM). This is due to the high energy and power density of the PMSM. Also, assembly costs of the PMSM are moderate. However, temperature monitoring of the PMSM is very difficult to achieve due to complicated measurement devices for internal components of the PMSM. Materials and methods: Therefore, the main goal of the study was to establish regression models for estimation of the optimal parameters for the temperature prediction. The regression models will be created by input/output data pairs so there is no need-to-know internal physical knowledge of the PMSM. The main aim is to achieve predictive capable models for the temperature. Results: Also, according to the regression model’s precision one can determine the input parameters influence on the temperatures of the internal components of the PMSM. Hence one king of ranking process will be performed in order to select which factors have the most influence on the temperatures. Conclusion: The repression models will be created by neuro fuzzy logic procedure since the procedure could handle high nonlinearity between input and output data pairs.