Artificial Neural Networks: Modeling and Comparison to Detect High Impedance Faults
High impedance faults constitute one of the biggest challenges in electrical power systems. In overhead distribution systems, faults are caused by tree branches that touch the electrical grid or by the rupture of energized conductors on low conductivity soils. They are also known as low-current faul...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10304113/ |
_version_ | 1797628978351046656 |
---|---|
author | Andressa Tais Diefenthaler Airam Teresa Zago Romcy Sausen Mauricio De Campos Paulo Sergio Sausen Joao Manoel Lenz |
author_facet | Andressa Tais Diefenthaler Airam Teresa Zago Romcy Sausen Mauricio De Campos Paulo Sergio Sausen Joao Manoel Lenz |
author_sort | Andressa Tais Diefenthaler |
collection | DOAJ |
description | High impedance faults constitute one of the biggest challenges in electrical power systems. In overhead distribution systems, faults are caused by tree branches that touch the electrical grid or by the rupture of energized conductors on low conductivity soils. They are also known as low-current faults, which are not detected by conventional protection systems, compromising the quality of the power supply and causing hazardous risks to the electrical system. This paper aims to address the problem of high impedance faults detection using Artificial Neural Networks: two Multi Layer Perceptron networks, being one Neural Pattern Recognition and another Neural Fitting, and a Convolutional Neural Network. The neural networks are trained and analyzed in scenarios based on a medium-voltage distribution grid model, located in the Basque Country, Spain. The network topologies are implemented, repeatedly trained considering multiple architectures, and validated in other scenarios with different location, time, and duration of the fault using the Matlab software. After, the criteria of accuracy, reliability, security, safety and sensitivity are evaluated. At last, a comparative analysis between them is carried out, and from the results obtained, a superior performance of the Convolutional Neural Network in compared to the Multi Layer Perceptron networks is observed. |
first_indexed | 2024-03-11T10:47:52Z |
format | Article |
id | doaj.art-40c37e6e3df244c891872b9be81d7e1b |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-11T10:47:52Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-40c37e6e3df244c891872b9be81d7e1b2023-11-14T00:00:55ZengIEEEIEEE Access2169-35362023-01-011112449912450810.1109/ACCESS.2023.332943910304113Artificial Neural Networks: Modeling and Comparison to Detect High Impedance FaultsAndressa Tais Diefenthaler0https://orcid.org/0000-0003-2206-8957Airam Teresa Zago Romcy Sausen1https://orcid.org/0000-0001-6499-4145Mauricio De Campos2https://orcid.org/0000-0001-8691-2913Paulo Sergio Sausen3https://orcid.org/0000-0001-9863-8800Joao Manoel Lenz4https://orcid.org/0000-0002-7349-4828Department of Exact Sciences and Engineering, Northwest Regional University of Rio Grande do Sul State (UNIJUÍ), Ijuí, Rio Grande do Sul, BrazilDepartment of Exact Sciences and Engineering, Northwest Regional University of Rio Grande do Sul State (UNIJUÍ), Ijuí, Rio Grande do Sul, BrazilDepartment of Exact Sciences and Engineering, Northwest Regional University of Rio Grande do Sul State (UNIJUÍ), Ijuí, Rio Grande do Sul, BrazilDepartment of Exact Sciences and Engineering, Northwest Regional University of Rio Grande do Sul State (UNIJUÍ), Ijuí, Rio Grande do Sul, BrazilInstitute of Technology, Infrastructure, and Territory (ILATIT), Federal University of Latin–American Integration (UNILA), Foz do Iguaçu, BrazilHigh impedance faults constitute one of the biggest challenges in electrical power systems. In overhead distribution systems, faults are caused by tree branches that touch the electrical grid or by the rupture of energized conductors on low conductivity soils. They are also known as low-current faults, which are not detected by conventional protection systems, compromising the quality of the power supply and causing hazardous risks to the electrical system. This paper aims to address the problem of high impedance faults detection using Artificial Neural Networks: two Multi Layer Perceptron networks, being one Neural Pattern Recognition and another Neural Fitting, and a Convolutional Neural Network. The neural networks are trained and analyzed in scenarios based on a medium-voltage distribution grid model, located in the Basque Country, Spain. The network topologies are implemented, repeatedly trained considering multiple architectures, and validated in other scenarios with different location, time, and duration of the fault using the Matlab software. After, the criteria of accuracy, reliability, security, safety and sensitivity are evaluated. At last, a comparative analysis between them is carried out, and from the results obtained, a superior performance of the Convolutional Neural Network in compared to the Multi Layer Perceptron networks is observed.https://ieeexplore.ieee.org/document/10304113/High impedance faultsdetectionelectrical systemartificial neural networkmodelingperformance comparison |
spellingShingle | Andressa Tais Diefenthaler Airam Teresa Zago Romcy Sausen Mauricio De Campos Paulo Sergio Sausen Joao Manoel Lenz Artificial Neural Networks: Modeling and Comparison to Detect High Impedance Faults IEEE Access High impedance faults detection electrical system artificial neural network modeling performance comparison |
title | Artificial Neural Networks: Modeling and Comparison to Detect High Impedance Faults |
title_full | Artificial Neural Networks: Modeling and Comparison to Detect High Impedance Faults |
title_fullStr | Artificial Neural Networks: Modeling and Comparison to Detect High Impedance Faults |
title_full_unstemmed | Artificial Neural Networks: Modeling and Comparison to Detect High Impedance Faults |
title_short | Artificial Neural Networks: Modeling and Comparison to Detect High Impedance Faults |
title_sort | artificial neural networks modeling and comparison to detect high impedance faults |
topic | High impedance faults detection electrical system artificial neural network modeling performance comparison |
url | https://ieeexplore.ieee.org/document/10304113/ |
work_keys_str_mv | AT andressataisdiefenthaler artificialneuralnetworksmodelingandcomparisontodetecthighimpedancefaults AT airamteresazagoromcysausen artificialneuralnetworksmodelingandcomparisontodetecthighimpedancefaults AT mauriciodecampos artificialneuralnetworksmodelingandcomparisontodetecthighimpedancefaults AT paulosergiosausen artificialneuralnetworksmodelingandcomparisontodetecthighimpedancefaults AT joaomanoellenz artificialneuralnetworksmodelingandcomparisontodetecthighimpedancefaults |