Three-Level NPC Inverter Incipient Fault Detection and Classification using Output Current Statistical Analysis
This paper deals with open switch Fault Detection and Diagnosis (FDD) in three-level Neutral Point Clamped (NPC) inverter for electrical drives. The approach is based on the already available phase current time series measurements for different operating conditions (motor speed, load, and environmen...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-04-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/12/7/1372 |
_version_ | 1811301449668231168 |
---|---|
author | Mehdi Baghli Claude Delpha Demba Diallo Abdelhamid Hallouche David Mba Tianzhen Wang |
author_facet | Mehdi Baghli Claude Delpha Demba Diallo Abdelhamid Hallouche David Mba Tianzhen Wang |
author_sort | Mehdi Baghli |
collection | DOAJ |
description | This paper deals with open switch Fault Detection and Diagnosis (FDD) in three-level Neutral Point Clamped (NPC) inverter for electrical drives. The approach is based on the already available phase current time series measurements for different operating conditions (motor speed, load, and environment noise). Both fault detection and classification are studied and the efficiency performances of the proposed selected features are shown. For the fault detection, we focus on the first four statistical moments and the extracted features and then the Cumulative Sum (CUSUM) algorithm as the feature analysis technique to improve the performances. For the classification study, we propose to couple the knowledge on the faulty system brought by the statistical moments and the Kullback-Leibler divergence particularly suitable for the detection of incipient changes. The Principal Component Analysis (PCA) is then used to perform the classification. A 2D framework is obtained, which allows the faults to be classified efficiently within the considered operating conditions for all the selected fault durations. |
first_indexed | 2024-04-13T07:09:07Z |
format | Article |
id | doaj.art-6459673e4cc042a6bdea757b17f6c9e6 |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-04-13T07:09:07Z |
publishDate | 2019-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-6459673e4cc042a6bdea757b17f6c9e62022-12-22T02:56:55ZengMDPI AGEnergies1996-10732019-04-01127137210.3390/en12071372en12071372Three-Level NPC Inverter Incipient Fault Detection and Classification using Output Current Statistical AnalysisMehdi Baghli0Claude Delpha1Demba Diallo2Abdelhamid Hallouche3David Mba4Tianzhen Wang5Laboratoire IRECOM, University Djillali Liabès, 22000 Sidi Bel Abbes, AlgeriaL2S, UMR 8506, CNRS, CentraleSupélec, Univ. Paris Sud, Université Paris Saclay, 91190 Saint-Aubin, FranceGeePs, UMR 8507, CNRS, CentraleSupélec, Univ. Paris Sud, Université Paris Saclay, Sorbonne Univ, 75006 Paris, FranceLaboratoire IRECOM, University Djillali Liabès, 22000 Sidi Bel Abbes, AlgeriaFaculty of Computer Engineering and Media, De Montfort University, Leicester LE1 9BH, UKShanghai Maritime University, Department of Electrical Automation, Shanghai 201306, ChinaThis paper deals with open switch Fault Detection and Diagnosis (FDD) in three-level Neutral Point Clamped (NPC) inverter for electrical drives. The approach is based on the already available phase current time series measurements for different operating conditions (motor speed, load, and environment noise). Both fault detection and classification are studied and the efficiency performances of the proposed selected features are shown. For the fault detection, we focus on the first four statistical moments and the extracted features and then the Cumulative Sum (CUSUM) algorithm as the feature analysis technique to improve the performances. For the classification study, we propose to couple the knowledge on the faulty system brought by the statistical moments and the Kullback-Leibler divergence particularly suitable for the detection of incipient changes. The Principal Component Analysis (PCA) is then used to perform the classification. A 2D framework is obtained, which allows the faults to be classified efficiently within the considered operating conditions for all the selected fault durations.https://www.mdpi.com/1996-1073/12/7/1372three-level neutral point clamped (NPC) inverteropen switch fault (OSF)intermittent fault monitoringincipient fault detection and diagnosis (FDD)cumulated sum (CUSUM)kullback-Leibler divergence (KLD)principal component analysis (PCA) |
spellingShingle | Mehdi Baghli Claude Delpha Demba Diallo Abdelhamid Hallouche David Mba Tianzhen Wang Three-Level NPC Inverter Incipient Fault Detection and Classification using Output Current Statistical Analysis Energies three-level neutral point clamped (NPC) inverter open switch fault (OSF) intermittent fault monitoring incipient fault detection and diagnosis (FDD) cumulated sum (CUSUM) kullback-Leibler divergence (KLD) principal component analysis (PCA) |
title | Three-Level NPC Inverter Incipient Fault Detection and Classification using Output Current Statistical Analysis |
title_full | Three-Level NPC Inverter Incipient Fault Detection and Classification using Output Current Statistical Analysis |
title_fullStr | Three-Level NPC Inverter Incipient Fault Detection and Classification using Output Current Statistical Analysis |
title_full_unstemmed | Three-Level NPC Inverter Incipient Fault Detection and Classification using Output Current Statistical Analysis |
title_short | Three-Level NPC Inverter Incipient Fault Detection and Classification using Output Current Statistical Analysis |
title_sort | three level npc inverter incipient fault detection and classification using output current statistical analysis |
topic | three-level neutral point clamped (NPC) inverter open switch fault (OSF) intermittent fault monitoring incipient fault detection and diagnosis (FDD) cumulated sum (CUSUM) kullback-Leibler divergence (KLD) principal component analysis (PCA) |
url | https://www.mdpi.com/1996-1073/12/7/1372 |
work_keys_str_mv | AT mehdibaghli threelevelnpcinverterincipientfaultdetectionandclassificationusingoutputcurrentstatisticalanalysis AT claudedelpha threelevelnpcinverterincipientfaultdetectionandclassificationusingoutputcurrentstatisticalanalysis AT dembadiallo threelevelnpcinverterincipientfaultdetectionandclassificationusingoutputcurrentstatisticalanalysis AT abdelhamidhallouche threelevelnpcinverterincipientfaultdetectionandclassificationusingoutputcurrentstatisticalanalysis AT davidmba threelevelnpcinverterincipientfaultdetectionandclassificationusingoutputcurrentstatisticalanalysis AT tianzhenwang threelevelnpcinverterincipientfaultdetectionandclassificationusingoutputcurrentstatisticalanalysis |