Auxiliary Particle Filtering-Based Estimation of Remaining Useful Life of IGBT

Insulated gate bipolar transistor (IGBT) has been widely used in diverse power electronics systems. As IGBT is one of the most vulnerable components in power electronics converter, remaining useful life (RUL) estimation of this switch has become highlight of the research in recent years. This RUL estimation helps in schedule maintenance based on health status of IGBT to avoid the unexpected failure of converters. However, there has been commonly a large variance in RUL estimation due to presence of random noise, which leads to erroneous result in IGBT prognosis. To reduce this variance in RUL estimation, particle filter methods including sequential importance sampling and sequential importance resampling have been employed recently. Still, these methods lead to nonnegligible estimation variance due to degeneracy and impoverishment of samples. In this paper, RUL estimation approach based on auxiliary particle filter (APF) is proposed. The proposed method will sufficiently reduce estimation variance by increasing dimensionality of samples as well as by sustaining diversity in samples. In addition, a simple slope-based method is proposed to identify the region when the degradation is evident in IGBT. An APF method is applied when the IGBTs under test enter this region. This step is able to reduce variation in RUL estimation and computation cost. The performance of the proposed RUL estimation method is theoretically and experimentally verified.