Open AccessHealth Monitoring of IGBTs with a Rule-Based Sub-safety Recognition Model Using Neural Networks
Author(s) -
Linghui Meng,
Michael Pecht,
Jie Liu,
Yuanhang Wang,
Keqiang Cheng
Publication year - 2020
Publication title -
journal of prognostics and health management
Language(s) - English
Resource type - Journals
ISSN - 2563-6685
DOI - 10.22215/jphm.v1i1.1349
Subject(s) - artificial neural network , aerospace , computer science , state (computer science) , power (physics) , electronics , power grid , reliability engineering , engineering , artificial intelligence , electrical engineering , aerospace engineering , physics , algorithm , quantum mechanics
IGBTs are used everywhere ranging from aerospace, to transportation systems to the grid but it’s the most fragile device in power electronics. So it’s very critical to evaluate the health state and take advanced and active maintenance measures to avoid the accidents. This paper develops a rule-based sub-safety recognition model using neural networks to evaluate the degradation degree of the IGBTs and determine the health state. The model was validated with two groups of experimental data.