# A Junction Temperature Prediction Method Based on Multivariate Linear Regression Using Current Fall Characteristics of SiC MOSFETs

## TL;DR

This paper introduces a new method to predict the junction temperature of SiC MOSFETs using current fall characteristics for better thermal monitoring in power systems.

## Contribution

A novel multivariate linear regression method using current fall time and loss as TSEPs for accurate junction temperature prediction in SiC MOSFETs.

## Key findings

- Current fall time and fall loss are effective temperature-sensitive electrical parameters for SiC MOSFETs.
- The proposed MLR method achieves high prediction accuracy in junction temperature estimation.
- The method shows superiority over traditional single TSEP approaches in thermal sensing applications.

## Abstract

The junction temperature (Tj) is a key parameter reflecting the thermal behavior of Silicon carbide (SiC) MOSFETs and is essential for condition monitoring and reliability assessment in power electronic systems. However, the limited temperature sensitivity of switching characteristics makes it difficult for traditional single temperature-sensitive electrical parameters (TSEPs) to achieve accurate estimation. To address this challenge and enable practical thermal sensing applications, this study proposes an accurate, application-oriented Tj estimation method based on multivariate linear regression (MLR) using turn-off current fall time (tfi) and fall loss (Efi) as complementary TSEPs. First, the feasibility of using current fall time and current fall energy loss as TSEPs is demonstrated. Then, a coupled junction temperature prediction model is developed based on multivariate linear regression using tfi and Efi. The proposed method is experimentally validated through comparative analysis. Experimental results demonstrate that the proposed method achieves high prediction accuracy, highlighting its effectiveness and superiority in MLR approach based on the current fall phase characteristics of SiC MOSFETs. This method offers promising prospects for enhancing the condition monitoring, reliability assessment, and intelligent sensing capabilities of power electronics systems.