Applied AI for Prognostics and Health Management

Important results from the project

** Denna text är maskinöversatt ** In this project, we have applied deep learning techniques to prognosticate the remaining useful life and state of health of electronic components. The project aimed to address the gap in AI for prognostics between Sweden and the USA. Deep learning techniques were developed and applied to a large dataset of power electronics from run-to-failure experiments. The main focus is to enable remaining useful life estimation of complex systems with resource constraints using deep learning models.

Expected long term effects

** Denna text är maskinöversatt ** The project resulted in a publication and established the basis for further collaboration between the project parties. At least one further publication based on the results is planned.

Approach and implementation

** Denna text är maskinöversatt ** The grant for individual mobility provided an opportunity for collaboration and exchange of skills between 2 complementary parties. A visiting researcher has visited RISE for 6 weeks to apply deep learning algorithms for remaining lifetime estimation of electronic components.