Self adaptive learning scheme for early diagnosis of simple and multiple switch faults in multicellular power converters
| Autor: | Houari Toubakh, Mohamed Djemai, Moamar Sayed-Mouchaweh, Mohammed Benmiloud, Michael Defoort |
|---|---|
| Přispěvatelé: | Ecole nationale supérieure Mines-Télécom Lille Douai (IMT Lille Douai), Institut Mines-Télécom [Paris] (IMT), Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201 (LAMIH), Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-INSA Institut National des Sciences Appliquées Hauts-de-France (INSA Hauts-De-France) |
| Rok vydání: | 2019 |
| Předmět: |
Scheme (programming language)
0209 industrial biotechnology Computer science Feature vector Real-time computing 02 engineering and technology Fault (power engineering) [SPI.AUTO]Engineering Sciences [physics]/Automatic [SPI]Engineering Sciences [physics] 020901 industrial engineering & automation Machine learning 0202 electrical engineering electronic engineering information engineering Isolation (database systems) Electrical and Electronic Engineering Instrumentation Data mining Fault diagnosis computer.programming_language Drift-like fault monitoring Multicellular power converters Applied Mathematics 020208 electrical & electronic engineering Converters Computer Science Applications Power (physics) Control and Systems Engineering Unsupervised learning computer Degradation (telecommunications) |
| Zdroj: | ISA Transactions ISA Transactions, 2021, 113, pp.222-231. ⟨10.1016/j.isatra.2020.03.025⟩ |
| ISSN: | 1879-2022 |
| Popis: | IF=4.34; International audience; This paper proposes a scheme based on the use of unsupervised machine learning approach and a drift detection mechanism in order to perform an early fault diagnosis of simple and multiple stuck-opened/stuck-closed switches in multicellular converters. Only the data samples representing the normal operation conditions are used in order to be adapted to the case where no data is available about faulty behaviors. A health indicator measuring the dissimilarity between normal and current operation conditions is built in order to detect a drift (degradations) in early stage. When a degradation (fault) is detected, the isolation is achieved by taking into account the discrete dynamics of switches. The features related to the latter are extracted in order to build a feature space allowing to separate the faulty behavior (zone or class) of the different switches. The proposed scheme is evaluated using real data samples representing different normal/simple/multiple switch fault scenarios issued from a test rig. © 2020 ISA |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect