Discover the PCIM Europe


Machine Learning Approach to Model Junction Temperatures in Automotive Inverters

Young Engineer Award 2023_Cover


Download free whitepaper

This paper presents a machine-learning approach to model semiconductor junction temperatures.

Increasing power density of automotive inverters lead to an increasing demand for accurate lifetime and reliability models. As such models are closely dependent on junction temperatures, they benefit from accurate temperature estimation methods. The model presented in this paper was trained and evaluated with data from a test bench incorporating a 1200 V SiC power module. The data pipeline, model performance, benefits and limitations are shown and discussed.

The provider of this whitepaper

Mercedes-Benz Group AG

70546  Stuttgart

p-b-logo (Messago)

Power & Beyond - Mesago Messe Frankfurt GmbH

Rotebühlstr. 83-85
70178 Stuttgart

Phone : +49 00

Contact form
Young Engineer Award 2023_Cover


Download free whitepaper