A Deep Learning Approach for Fault Detection and Localization in MT-VSC-HVDC System Utilizing Wavelet Scattering Transform

This study presents a novel algorithm for automatic fault detection in multi-terminal voltage source converter-based high voltage direct current (MT-VSCHVDC) systems. The approach integrates the wavelet scattering transform (WST) to extract low-variance feature vectors and a newly developed variable...

Full description

Saved in:
Bibliographic Details
Main Authors: Manohar Mishra, Debadatta Amaresh Gadanayak, Abha Pragati, Jai Govind Singh
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11015988/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850132643444686848
author Manohar Mishra
Debadatta Amaresh Gadanayak
Abha Pragati
Jai Govind Singh
author_facet Manohar Mishra
Debadatta Amaresh Gadanayak
Abha Pragati
Jai Govind Singh
author_sort Manohar Mishra
collection DOAJ
description This study presents a novel algorithm for automatic fault detection in multi-terminal voltage source converter-based high voltage direct current (MT-VSCHVDC) systems. The approach integrates the wavelet scattering transform (WST) to extract low-variance feature vectors and a newly developed variable batch size long-short-term-memory (VB-LSTM) network for accurate fault detection. The synthetic minority oversampling technique addresses class imbalance issues in fault and no-fault data. Utilizing a 5-fold cross-validation process, the study demonstrates that WST-based features, combined with the proposed VB-LSTM network and a hybrid training strategy, achieve 100% and 99.46% accuracy in classifying internal and external faults with no-noise and 20db noisy conditions respectively. The variable epoch size training enhances convergence speed, leading to more stable and consistent results. A secondary LSTM model with a similar layer architecture is also trained and evaluated on WST-based features to identify the fault location within internal faults. The proposed fault distance (WST-VB-LSTM) estimation model achieves excellent performance with an R-square of 0.9946 and MAE of 0.0135 without noise, and maintains robustness under noise with 30 dB (<inline-formula> <tex-math notation="LaTeX">$\text{R}^{2} =0.9903$ </tex-math></inline-formula>, MAE =0.0182) and 20 dB (<inline-formula> <tex-math notation="LaTeX">$\text{R}^{2} =0.9598$ </tex-math></inline-formula>, MAE =0.0364). Lastly, comparative performance analysis reveals that the proposed model outperforms recently published works and state-of-the-art techniques, exhibiting higher accuracy and significantly lower error metrics across varying noise conditions.
format Article
id doaj-art-2f41ff3d2ae14b82935eb4e14789c040
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-2f41ff3d2ae14b82935eb4e14789c0402025-08-20T02:32:10ZengIEEEIEEE Access2169-35362025-01-0113956479566410.1109/ACCESS.2025.357422211015988A Deep Learning Approach for Fault Detection and Localization in MT-VSC-HVDC System Utilizing Wavelet Scattering TransformManohar Mishra0https://orcid.org/0000-0003-2160-4703Debadatta Amaresh Gadanayak1https://orcid.org/0000-0001-7533-4441Abha Pragati2Jai Govind Singh3https://orcid.org/0000-0002-0162-3360Department of Electrical and Electronics Engineering, Siksha O Anusandhan (SOA) Deemed to be University, Bhubaneswar, Odisha, IndiaDepartment of Electrical and Electronics Engineering, Siksha O Anusandhan (SOA) Deemed to be University, Bhubaneswar, Odisha, IndiaDepartment of Electrical and Electronics Engineering, Siksha O Anusandhan (SOA) Deemed to be University, Bhubaneswar, Odisha, IndiaDepartment of Energy and Climate Change, School of Environmental Resource and Development, Asian Institute of Technology, Khlong Luang, Bangkok, Pathum Thani, ThailandThis study presents a novel algorithm for automatic fault detection in multi-terminal voltage source converter-based high voltage direct current (MT-VSCHVDC) systems. The approach integrates the wavelet scattering transform (WST) to extract low-variance feature vectors and a newly developed variable batch size long-short-term-memory (VB-LSTM) network for accurate fault detection. The synthetic minority oversampling technique addresses class imbalance issues in fault and no-fault data. Utilizing a 5-fold cross-validation process, the study demonstrates that WST-based features, combined with the proposed VB-LSTM network and a hybrid training strategy, achieve 100% and 99.46% accuracy in classifying internal and external faults with no-noise and 20db noisy conditions respectively. The variable epoch size training enhances convergence speed, leading to more stable and consistent results. A secondary LSTM model with a similar layer architecture is also trained and evaluated on WST-based features to identify the fault location within internal faults. The proposed fault distance (WST-VB-LSTM) estimation model achieves excellent performance with an R-square of 0.9946 and MAE of 0.0135 without noise, and maintains robustness under noise with 30 dB (<inline-formula> <tex-math notation="LaTeX">$\text{R}^{2} =0.9903$ </tex-math></inline-formula>, MAE =0.0182) and 20 dB (<inline-formula> <tex-math notation="LaTeX">$\text{R}^{2} =0.9598$ </tex-math></inline-formula>, MAE =0.0364). Lastly, comparative performance analysis reveals that the proposed model outperforms recently published works and state-of-the-art techniques, exhibiting higher accuracy and significantly lower error metrics across varying noise conditions.https://ieeexplore.ieee.org/document/11015988/HVDC protectionScatterNet application in HVDC protectionwavelet scattering transform for HVDC protectionfault recognition in HVDCfault location in HVDC
spellingShingle Manohar Mishra
Debadatta Amaresh Gadanayak
Abha Pragati
Jai Govind Singh
A Deep Learning Approach for Fault Detection and Localization in MT-VSC-HVDC System Utilizing Wavelet Scattering Transform
IEEE Access
HVDC protection
ScatterNet application in HVDC protection
wavelet scattering transform for HVDC protection
fault recognition in HVDC
fault location in HVDC
title A Deep Learning Approach for Fault Detection and Localization in MT-VSC-HVDC System Utilizing Wavelet Scattering Transform
title_full A Deep Learning Approach for Fault Detection and Localization in MT-VSC-HVDC System Utilizing Wavelet Scattering Transform
title_fullStr A Deep Learning Approach for Fault Detection and Localization in MT-VSC-HVDC System Utilizing Wavelet Scattering Transform
title_full_unstemmed A Deep Learning Approach for Fault Detection and Localization in MT-VSC-HVDC System Utilizing Wavelet Scattering Transform
title_short A Deep Learning Approach for Fault Detection and Localization in MT-VSC-HVDC System Utilizing Wavelet Scattering Transform
title_sort deep learning approach for fault detection and localization in mt vsc hvdc system utilizing wavelet scattering transform
topic HVDC protection
ScatterNet application in HVDC protection
wavelet scattering transform for HVDC protection
fault recognition in HVDC
fault location in HVDC
url https://ieeexplore.ieee.org/document/11015988/
work_keys_str_mv AT manoharmishra adeeplearningapproachforfaultdetectionandlocalizationinmtvschvdcsystemutilizingwaveletscatteringtransform
AT debadattaamareshgadanayak adeeplearningapproachforfaultdetectionandlocalizationinmtvschvdcsystemutilizingwaveletscatteringtransform
AT abhapragati adeeplearningapproachforfaultdetectionandlocalizationinmtvschvdcsystemutilizingwaveletscatteringtransform
AT jaigovindsingh adeeplearningapproachforfaultdetectionandlocalizationinmtvschvdcsystemutilizingwaveletscatteringtransform
AT manoharmishra deeplearningapproachforfaultdetectionandlocalizationinmtvschvdcsystemutilizingwaveletscatteringtransform
AT debadattaamareshgadanayak deeplearningapproachforfaultdetectionandlocalizationinmtvschvdcsystemutilizingwaveletscatteringtransform
AT abhapragati deeplearningapproachforfaultdetectionandlocalizationinmtvschvdcsystemutilizingwaveletscatteringtransform
AT jaigovindsingh deeplearningapproachforfaultdetectionandlocalizationinmtvschvdcsystemutilizingwaveletscatteringtransform