Temperature Prediction of Permanent Magnet Synchronous Motor Based on Data-driven Approach

In order to avoid the damage of permanent magnet synchronous motor caused by the high temperature, this paper proposes a method for predicting the temperature of permanent magnet synchronous motors based on XGBoost. The method mainly consists of three parts: first, normalize the data, then use Bayesian optimization to find the optimal hyperparameters for the model, and finally train the model using XGBoost Comparing with the training results of other artificial intelligence algorithms, the precision of the temperature estimation can be improved by the proposed method, which is verified by the experimental results.