Deployment of ARX Models for Thermal Forecasting in Power Electronics Boards Using WBG Semiconductors

TL;DR

This paper demonstrates that ARX models can accurately forecast the thermal behavior of WBG semiconductor boards, offering a simpler alternative to FEM simulations and traditional thermal models by relying solely on experimental data.

Contribution

The study introduces the use of ARX parametric models for thermal forecasting in WBG semiconductor boards, simplifying system identification without detailed physical properties.

Findings

ARX models achieve high accuracy in thermal predictions.

ARX models outperform traditional thermal models in simplicity and reliability.

The approach reduces reliance on complex physical simulations.

Abstract

Facing the thermal management challenges of Wide Bandgap (WBG) semiconductors, this study highlights the use of ARX parametric models, which provide accurate temperature predictions without requiring detailed understanding of component thickness disparities or material physical properties, relying solely on experimental measurements. These parametric models emerge as a reliable alternative to FEM simulations and conventional thermal models, significantly simplifying system identification while ensuring high result accuracy.