A review of data-driven prognostic for IGBT remaining useful life

Abstract

Power converters with insulated gate bipolar transistor(IGBT) are widely used in diverse industrial applications such as traction systems. As the IGBT is one of the most fragile components in power electronics converter, remaining useful life(RUL) prognostic of IGBT is important to guarantee system reliability. This paper presents a review of data-driven prognostic for IGBT RUL. In this paper, common data-driven prognostic methods are summarized. Features of data-driven prognostic approaches of IGBT are discussed, and main approaches are compared to each other. Four common problems of these schemes are presented and discussed. In addition, some other desirable studies to improve IGBT RUL estimation are proposed.