Integrating Snake Optimizer and SVR for Motor Rotor Temperature Forecasting

Motor rotor temperature is a critical parameter for ensuring reliable and safe operation of electric motors. Accurate temperature forecasting can help prevent thermal failures and provide valuable data for maintenance personnel. In this paper, a novel regression model that integrates Snake Optimizer (SO) with Support Vector Regression (SVR) is proposed to forecast the temperature of motor rotors. he principles of SO and SVR are introduced. The steps using SO to optimize the hyperparameters of SVR and the design process of fitness function are discussed in detail. Then, the hybrid model, SO-SVR, is established, which leads to improved prediction accuracy and robustness. To quantitatively evaluate the performance, experiments on public real-world data from a permanent magnet synchronous motor are conduct. The model is compared with other popular existing models, including MPA-ELM, WOA-RBF, and SSA-Elman, using Mean Absolute Error, Root Mean Square Error, and R-Squared. Results show that SO-SVR outperforms other models, achieving lower errors and higher robust. By accurately predicting motor rotor temperature, the developed model can reduce the occurrence of thermal failures and improve the reliability and safety of motor operation. The temperature data provided by the model also assists maintenance personnel in detecting and resolving potential issues before they become major problems.