Junction Temperature Estimation in IGBT Modules using Machine Learning based Fine-Tuning for Domain Adaptation

Key Points

• The aim is to improve the accuracy of junction temperature estimation in IGBT modules using machine learning techniques.
• Utilized machine learning algorithms for estimating junction temperature.
• Applied domain adaptation strategies for better prediction accuracy.
• Implemented fine-tuning processes on existing models.
• Achieved higher accuracy in temperature estimation compared to traditional methods.
• Demonstrated significant improvement in performance metrics.
• Enhanced generalizability across different operating conditions.