A Convolutional Neural Network Regression Model for Periodic Magnetic Systems in MTSS

This paper proposes a predictive regression model based on Convolutional Neural Networks(CNN) for predicting the magnetic field peaks of periodic magnetic systems under different periods within a Multi-Physics Simulation System. By establishing a physical model of the magnetic system and setting parameters, combined with the CNN model, the magnetic field peaks under different periods are predicted. Simulation results show that the prediction accuracy of the CNN model can be controlled within 5% under different periods, demonstrating high prediction accuracy and generalization ability.