SiC MOSFET junction temperature estimation based on the principal components regressed model

Abstract

Listen

Translate article

The junction temperature estimation enables online health management and performance optimisation of SiC power modules. A multitude of temperature sensitive electrical parameters (TSEPs) is gaining increased attention due to their non-invasive nature for online measurements, but they are conventionally focused on certain individual TSEPs, which lack accuracy and robustness given the dynamic variations of operational conditions. This paper proposed a fusion method by combining the principal component analysis (PCA) and multiple linear regression (MLR) to estimate the junction temperature from a TSEP data set. The presented fusion method predicts temperature with better accuracy and higher noise immunisation compared with the single TSEP estimation method.