Classification of voltage sags causes in industrial power networks using multivariate time‐series
Abstract Voltage sags are the most frequent and impactful disturbances in industrial power grids, leading to high financial losses for industrial clients. The identification of the cause and its relative location is crucial for the contractual relation between the energy provider and the industrial...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-04-01
|
Series: | IET Generation, Transmission & Distribution |
Subjects: | |
Online Access: | https://doi.org/10.1049/gtd2.12765 |
_version_ | 1797852075450695680 |
---|---|
author | Maria Veizaga Claude Delpha Demba Diallo Sophie Bercu Ludovic Bertin |
author_facet | Maria Veizaga Claude Delpha Demba Diallo Sophie Bercu Ludovic Bertin |
author_sort | Maria Veizaga |
collection | DOAJ |
description | Abstract Voltage sags are the most frequent and impactful disturbances in industrial power grids, leading to high financial losses for industrial clients. The identification of the cause and its relative location is crucial for the contractual relation between the energy provider and the industrial customers. This paper proposes a methodology to identify the origins of voltage sags based on instantaneous symmetrical components and dynamic time warping. Short‐Time Fourier and Fortescue transform are implemented in the pre‐processing step using the voltage and current waveforms. Then, a distance‐based classification strategy to identify the sources of voltage sags is used. It relies on a four‐dimension time‐series signature used as features. Moreover, a confidence index associated with the classification output is provided. The proposal offers an easy implementation in industrial applications with no previous recorded data. It has the benefit of using a reduced‐size reference database entirely composed of synthetic data. The main advantages of the proposed method are its generalization capabilities and the possibility of raising an alert based on the confidence index. The obtained classification accuracy on synthetic data with seven causes is 100%. The method reaches a classification F1‐score higher than 99% with field measurements representing five classes obtained from three different industrial sites. |
first_indexed | 2024-04-09T19:28:09Z |
format | Article |
id | doaj.art-c4764018d32248bdaa63d96cbb79ca0f |
institution | Directory Open Access Journal |
issn | 1751-8687 1751-8695 |
language | English |
last_indexed | 2024-04-09T19:28:09Z |
publishDate | 2023-04-01 |
publisher | Wiley |
record_format | Article |
series | IET Generation, Transmission & Distribution |
spelling | doaj.art-c4764018d32248bdaa63d96cbb79ca0f2023-04-05T05:48:27ZengWileyIET Generation, Transmission & Distribution1751-86871751-86952023-04-011771568158410.1049/gtd2.12765Classification of voltage sags causes in industrial power networks using multivariate time‐seriesMaria Veizaga0Claude Delpha1Demba Diallo2Sophie Bercu3Ludovic Bertin4Université Paris Saclay, CNRS, CentraleSupelec, L2S Gif Sur Yvette FranceUniversité Paris Saclay, CNRS, CentraleSupelec, L2S Gif Sur Yvette FranceUniversité Paris Saclay, CNRS, CentraleSupelec, GeePs Gif Sur Yvette FranceEDF Lab Saclay Palaiseau FranceEDF Lab Saclay Palaiseau FranceAbstract Voltage sags are the most frequent and impactful disturbances in industrial power grids, leading to high financial losses for industrial clients. The identification of the cause and its relative location is crucial for the contractual relation between the energy provider and the industrial customers. This paper proposes a methodology to identify the origins of voltage sags based on instantaneous symmetrical components and dynamic time warping. Short‐Time Fourier and Fortescue transform are implemented in the pre‐processing step using the voltage and current waveforms. Then, a distance‐based classification strategy to identify the sources of voltage sags is used. It relies on a four‐dimension time‐series signature used as features. Moreover, a confidence index associated with the classification output is provided. The proposal offers an easy implementation in industrial applications with no previous recorded data. It has the benefit of using a reduced‐size reference database entirely composed of synthetic data. The main advantages of the proposed method are its generalization capabilities and the possibility of raising an alert based on the confidence index. The obtained classification accuracy on synthetic data with seven causes is 100%. The method reaches a classification F1‐score higher than 99% with field measurements representing five classes obtained from three different industrial sites.https://doi.org/10.1049/gtd2.12765fault diagnosisfault locationpower distribution faultsPower Quality / Harmonicstime series |
spellingShingle | Maria Veizaga Claude Delpha Demba Diallo Sophie Bercu Ludovic Bertin Classification of voltage sags causes in industrial power networks using multivariate time‐series IET Generation, Transmission & Distribution fault diagnosis fault location power distribution faults Power Quality / Harmonics time series |
title | Classification of voltage sags causes in industrial power networks using multivariate time‐series |
title_full | Classification of voltage sags causes in industrial power networks using multivariate time‐series |
title_fullStr | Classification of voltage sags causes in industrial power networks using multivariate time‐series |
title_full_unstemmed | Classification of voltage sags causes in industrial power networks using multivariate time‐series |
title_short | Classification of voltage sags causes in industrial power networks using multivariate time‐series |
title_sort | classification of voltage sags causes in industrial power networks using multivariate time series |
topic | fault diagnosis fault location power distribution faults Power Quality / Harmonics time series |
url | https://doi.org/10.1049/gtd2.12765 |
work_keys_str_mv | AT mariaveizaga classificationofvoltagesagscausesinindustrialpowernetworksusingmultivariatetimeseries AT claudedelpha classificationofvoltagesagscausesinindustrialpowernetworksusingmultivariatetimeseries AT dembadiallo classificationofvoltagesagscausesinindustrialpowernetworksusingmultivariatetimeseries AT sophiebercu classificationofvoltagesagscausesinindustrialpowernetworksusingmultivariatetimeseries AT ludovicbertin classificationofvoltagesagscausesinindustrialpowernetworksusingmultivariatetimeseries |