Intelligent Sensors for dc Fault Location Scheme Based on Optimized Intelligent Architecture for HVdc Systems
We develop a probabilistic model for determining the location of dc-link faults in MT-HVdc networks using discrete wavelet transforms (DWTs), Bayesian optimization, and multilayer artificial neural networks (ANNs) based on local information. Likewise, feedforward neural networks (FFNNs) are trained...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/24/9936 |
_version_ | 1797455294170660864 |
---|---|
author | Muhammad Zain Yousaf Muhammad Faizan Tahir Ali Raza Muhammad Ahmad Khan Fazal Badshah |
author_facet | Muhammad Zain Yousaf Muhammad Faizan Tahir Ali Raza Muhammad Ahmad Khan Fazal Badshah |
author_sort | Muhammad Zain Yousaf |
collection | DOAJ |
description | We develop a probabilistic model for determining the location of dc-link faults in MT-HVdc networks using discrete wavelet transforms (DWTs), Bayesian optimization, and multilayer artificial neural networks (ANNs) based on local information. Likewise, feedforward neural networks (FFNNs) are trained using the Levenberg–Marquardt backpropagation (LMBP) method, which multi-stage BO optimizes for efficiency. During training, the feature vectors at the sending terminal of the dc link are selected based on the norm values of the observed waveforms at various frequency bands. The multilayer ANN is trained using a comprehensive set of offline data that takes the denoising scheme into account. This choice not only helps to reduce the computational load but also provides better accuracy. An overall percentage error of 0.5144% is observed for the proposed algorithm when tested against fault resistances ranging from 10 to 485 Ω. The simulation results show that the proposed method can accurately estimate the fault site to a precision of 485 Ω and is more robust. |
first_indexed | 2024-03-09T15:51:21Z |
format | Article |
id | doaj.art-33b9ae0fafe54615a94b574ff8033a7e |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T15:51:21Z |
publishDate | 2022-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-33b9ae0fafe54615a94b574ff8033a7e2023-11-24T17:57:44ZengMDPI AGSensors1424-82202022-12-012224993610.3390/s22249936Intelligent Sensors for dc Fault Location Scheme Based on Optimized Intelligent Architecture for HVdc SystemsMuhammad Zain Yousaf0Muhammad Faizan Tahir1Ali Raza2Muhammad Ahmad Khan3Fazal Badshah4School of Electrical and Information Engineering, Hubei University of Automotive Technology, Shiyan 442002, ChinaSchool of Electric Power, South China University of Technology, Guangzhou 510630, ChinaSchool of Electrical Engineering, University of Engineering and Technology, Lahore 39161, PakistanSchool of Electrical and Information Engineering, Tianjin University, Tianjin 300072, ChinaSchool of Electrical and Information Engineering, Hubei University of Automotive Technology, Shiyan 442002, ChinaWe develop a probabilistic model for determining the location of dc-link faults in MT-HVdc networks using discrete wavelet transforms (DWTs), Bayesian optimization, and multilayer artificial neural networks (ANNs) based on local information. Likewise, feedforward neural networks (FFNNs) are trained using the Levenberg–Marquardt backpropagation (LMBP) method, which multi-stage BO optimizes for efficiency. During training, the feature vectors at the sending terminal of the dc link are selected based on the norm values of the observed waveforms at various frequency bands. The multilayer ANN is trained using a comprehensive set of offline data that takes the denoising scheme into account. This choice not only helps to reduce the computational load but also provides better accuracy. An overall percentage error of 0.5144% is observed for the proposed algorithm when tested against fault resistances ranging from 10 to 485 Ω. The simulation results show that the proposed method can accurately estimate the fault site to a precision of 485 Ω and is more robust.https://www.mdpi.com/1424-8220/22/24/9936Levenberg–Marquardt backpropagationprotection sensorBayesian optimizationmodular multilevel converter |
spellingShingle | Muhammad Zain Yousaf Muhammad Faizan Tahir Ali Raza Muhammad Ahmad Khan Fazal Badshah Intelligent Sensors for dc Fault Location Scheme Based on Optimized Intelligent Architecture for HVdc Systems Sensors Levenberg–Marquardt backpropagation protection sensor Bayesian optimization modular multilevel converter |
title | Intelligent Sensors for dc Fault Location Scheme Based on Optimized Intelligent Architecture for HVdc Systems |
title_full | Intelligent Sensors for dc Fault Location Scheme Based on Optimized Intelligent Architecture for HVdc Systems |
title_fullStr | Intelligent Sensors for dc Fault Location Scheme Based on Optimized Intelligent Architecture for HVdc Systems |
title_full_unstemmed | Intelligent Sensors for dc Fault Location Scheme Based on Optimized Intelligent Architecture for HVdc Systems |
title_short | Intelligent Sensors for dc Fault Location Scheme Based on Optimized Intelligent Architecture for HVdc Systems |
title_sort | intelligent sensors for dc fault location scheme based on optimized intelligent architecture for hvdc systems |
topic | Levenberg–Marquardt backpropagation protection sensor Bayesian optimization modular multilevel converter |
url | https://www.mdpi.com/1424-8220/22/24/9936 |
work_keys_str_mv | AT muhammadzainyousaf intelligentsensorsfordcfaultlocationschemebasedonoptimizedintelligentarchitectureforhvdcsystems AT muhammadfaizantahir intelligentsensorsfordcfaultlocationschemebasedonoptimizedintelligentarchitectureforhvdcsystems AT aliraza intelligentsensorsfordcfaultlocationschemebasedonoptimizedintelligentarchitectureforhvdcsystems AT muhammadahmadkhan intelligentsensorsfordcfaultlocationschemebasedonoptimizedintelligentarchitectureforhvdcsystems AT fazalbadshah intelligentsensorsfordcfaultlocationschemebasedonoptimizedintelligentarchitectureforhvdcsystems |