Open-Circuit Fault Detection in a 5-Level Cascaded H-Bridge Inverter Using 1D CNN and LSTM

Chouaib Djaghloul, Kambiz Tehrani () and François Vurpillot
Additional contact information
Chouaib Djaghloul: Department of Scientific Instrumentation, Group of Physics of Materials (GPM), UMR 6634, CNRS, INSA Rouen Normandie, University of Rouen Normandie, Normandie University, 76000 Rouen, France
Kambiz Tehrani: Department of Electrical Engineering, Institut Pascal, CNRS, Clermont Auvergne INP, University of Clermont Auvergne, 63000 Clermont-Ferrand, France
François Vurpillot: Department of Scientific Instrumentation, Group of Physics of Materials (GPM), UMR 6634, CNRS, INSA Rouen Normandie, University of Rouen Normandie, Normandie University, 76000 Rouen, France

Energies, 2025, vol. 18, issue 18, 1-20

Abstract: It is well known that power converters have the highest failure rate in the energy conversion chain in different industrial applications. This could definitely affect the reliability of the system. The reliability of converters in power conversion systems is crucial, as failures can lead to critical consequences and damage other system components. Therefore, it is important to predict and detect failures and take corrective actions to prevent them. One of the most common types of failure in power converters is semiconductor failure, which can manifest as an open circuit or a short circuit. This paper focuses on single and double open-circuit switch failures in a 5-level cascaded H-bridge inverter, for which a fast, precise method is required. A data-driven approach is employed here, using the output voltage and voltages across each H-bridge as diagnostic signals. A 1D-CNN LSTM neural network is trained to accurately detect and localize open-circuit faults, providing a reliable, practical solution.

Keywords: power converters reliability; multilevel inverter; fault diagnosis; switch fault diagnosis; open-circuit fault detection; neural network; 1D-CNN LSTM network (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/18/5004/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/18/5004/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:18:p:5004-:d:1753950

Access Statistics for this article

Energies is currently edited by Ms. Cassie Shen

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().