R-PODID

Reliability improvement of industrial power converters and drives, increasing their lifespan, artificial Intelligence in digital industry for increase performance. Sustainable production, cost and energy savings, and CO2 emissions reduction

Project objectives:

R-PODID 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. Thereby, electrical, and mechanical faults of machines and of the power converters driving them will become predictable within a limited prediction horizon of 12-24h. This will enable a power-saving shutdown of a larger number of production machines during idle times, because a looming failure during the next power-on cycle can be reliably foreseen. It will also enable reliable mitigation of dangerous faults in applications using modern power-devices like silicon-carbide (SiC) and III/V-semiconductor devices like gallium-nitride (GaN).

The idea behind R-PODID is to bring AI augmented compact models to the endpoint devices inherently involved in the electrification process: the power converters. This is in line with the idea of “cognitive power electronics”.