R-PODID (Reliable POwerDown for Industrial Drivers) aims to develop an automated, cloudless, short-term fault-prediction for electric drives, power modules, and power devices, that can be integrated into power converters.

Project objectives:

1. Methodology for fault-prediction model generation from sparse training sets or system simulation.
2. Power systems with integrated support for embedded AI.
3. 24 h fault-prediction for Gallium Nitride (GaN) and Silicon Carbide (SiC) based power converters.
4. 24 h fault-prediction and fault mitigation for electric drives.
5. Sensors for reliability prediction in power modules.