Discussion on Classification Methods for Lifetime Evaluation of a Lab-Scale SiC MOSFET Power Module
Résumé
This paper focuses on classification methods for evaluating the lifetime consumption (LC) of power electronics modules. The generalization of power electronics devices introduces new issues concerning the reliability of equipment, especially in the transportation field. To meet these expectations, this paper discusses an approach to evaluate the percentage of lifetime of a lab-scale SiC MOSFET power module, designed for an aircraft application. This module is based on a planar technology, and presents typical failure modes concerning the SiC MOSFET chip itself and its environment. The modules have been aged on a specific instrumented test bench to trigger the expected failure modes. Thanks to it, a large database of parameters have been obtained in order to find a relevant failure signature. Once the signature obtained, a comprehensive solution is required to classify the signatures into relevant classes related to the module LC. To meet the issue, three types of classification have been tested with learning data set: Support Vector Machine, k-Nearest Neighbors and neural network. The last contribution of this paper is a discussion on the evaluation of the percentage of lifetime consumption of a new test module thanks to the most promising models obtained from the learning data set.
Domaines
Sciences de l'ingénieur [physics]Origine | Fichiers produits par l'(les) auteur(s) |
---|