Performance Comparison Between Deep Learning Models for Fault Classification in Transmission Lines Using Time Series Data
ABSTRACT Deep learning has become a vital tool for addressing complex challenges in power systems, particularly fault detection and classification in transmission lines. This study presents a comparative analysis of three advanced time‐series models like temporal convolutional networks (TCN), bidire...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-05-01
|
| Series: | Energy Science & Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/ese3.70033 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850193493371125760 |
|---|---|
| author | Nadeem Ahmed Tunio Mohsin Ali Tunio Muhammad Amir Raza Muhammad Faheem Ashfaque Ahmed Hashmani Rumaisa Nadeem |
| author_facet | Nadeem Ahmed Tunio Mohsin Ali Tunio Muhammad Amir Raza Muhammad Faheem Ashfaque Ahmed Hashmani Rumaisa Nadeem |
| author_sort | Nadeem Ahmed Tunio |
| collection | DOAJ |
| description | ABSTRACT Deep learning has become a vital tool for addressing complex challenges in power systems, particularly fault detection and classification in transmission lines. This study presents a comparative analysis of three advanced time‐series models like temporal convolutional networks (TCN), bidirectional long short‐term memory (BiLSTM), and gated recurrent units (GRU) for fault classification. Leveraging a comprehensive data set encompassing diverse fault scenarios like single‐phase to ground fault (AG), double line to ground fault (ABG), three‐phase fault (ABC) from both simulated and real transmission line data, the study provides a rigorous evaluation of these models’ performance under realistic conditions. The results demonstrate that TCN achieves a fault classification accuracy of 99.9%, significantly outperforming BiLSTM (92.31%) and GRU (95.27%), while also excelling in precision, recall, F1 score, and training efficiency. Additionally, this study incorporates feature extraction techniques like discrete wavelet transform (CWT) to establish new benchmarks for fault classification. The findings underscore TCN's robustness in handling the dynamic nature of transmission line signals and its practical potential for real‐time applications, contributing to the development of more reliable and efficient power system fault classification systems. |
| format | Article |
| id | doaj-art-249004d7352e451680b91256223fe2d7 |
| institution | OA Journals |
| issn | 2050-0505 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Wiley |
| record_format | Article |
| series | Energy Science & Engineering |
| spelling | doaj-art-249004d7352e451680b91256223fe2d72025-08-20T02:14:15ZengWileyEnergy Science & Engineering2050-05052025-05-011352330235110.1002/ese3.70033Performance Comparison Between Deep Learning Models for Fault Classification in Transmission Lines Using Time Series DataNadeem Ahmed Tunio0Mohsin Ali Tunio1Muhammad Amir Raza2Muhammad Faheem3Ashfaque Ahmed Hashmani4Rumaisa Nadeem5Department of Electrical Engineering Mehran University of Engineering & Technology SZAB Campus Khairpur Mirs PakistanDepartment of Electrical Engineering Mehran University of Engineering & Technology SZAB Campus Khairpur Mirs PakistanDepartment of Electrical Engineering Mehran University of Engineering & Technology SZAB Campus Khairpur Mirs PakistanVTT Technical Research Centre of Finland Ltd. Espoo FinlandDepartment of Electrical Engineering Mehran University of Engineering and Technology Jamshoro PakistanSchool of Computer Sciences, University of Saskatchewan Saskatoon CanadaABSTRACT Deep learning has become a vital tool for addressing complex challenges in power systems, particularly fault detection and classification in transmission lines. This study presents a comparative analysis of three advanced time‐series models like temporal convolutional networks (TCN), bidirectional long short‐term memory (BiLSTM), and gated recurrent units (GRU) for fault classification. Leveraging a comprehensive data set encompassing diverse fault scenarios like single‐phase to ground fault (AG), double line to ground fault (ABG), three‐phase fault (ABC) from both simulated and real transmission line data, the study provides a rigorous evaluation of these models’ performance under realistic conditions. The results demonstrate that TCN achieves a fault classification accuracy of 99.9%, significantly outperforming BiLSTM (92.31%) and GRU (95.27%), while also excelling in precision, recall, F1 score, and training efficiency. Additionally, this study incorporates feature extraction techniques like discrete wavelet transform (CWT) to establish new benchmarks for fault classification. The findings underscore TCN's robustness in handling the dynamic nature of transmission line signals and its practical potential for real‐time applications, contributing to the development of more reliable and efficient power system fault classification systems.https://doi.org/10.1002/ese3.70033bidirectional long short‐term memoryfault classificationgated recurrent unitsmart gridtemporal convolutional networktransmission lines |
| spellingShingle | Nadeem Ahmed Tunio Mohsin Ali Tunio Muhammad Amir Raza Muhammad Faheem Ashfaque Ahmed Hashmani Rumaisa Nadeem Performance Comparison Between Deep Learning Models for Fault Classification in Transmission Lines Using Time Series Data Energy Science & Engineering bidirectional long short‐term memory fault classification gated recurrent unit smart grid temporal convolutional network transmission lines |
| title | Performance Comparison Between Deep Learning Models for Fault Classification in Transmission Lines Using Time Series Data |
| title_full | Performance Comparison Between Deep Learning Models for Fault Classification in Transmission Lines Using Time Series Data |
| title_fullStr | Performance Comparison Between Deep Learning Models for Fault Classification in Transmission Lines Using Time Series Data |
| title_full_unstemmed | Performance Comparison Between Deep Learning Models for Fault Classification in Transmission Lines Using Time Series Data |
| title_short | Performance Comparison Between Deep Learning Models for Fault Classification in Transmission Lines Using Time Series Data |
| title_sort | performance comparison between deep learning models for fault classification in transmission lines using time series data |
| topic | bidirectional long short‐term memory fault classification gated recurrent unit smart grid temporal convolutional network transmission lines |
| url | https://doi.org/10.1002/ese3.70033 |
| work_keys_str_mv | AT nadeemahmedtunio performancecomparisonbetweendeeplearningmodelsforfaultclassificationintransmissionlinesusingtimeseriesdata AT mohsinalitunio performancecomparisonbetweendeeplearningmodelsforfaultclassificationintransmissionlinesusingtimeseriesdata AT muhammadamirraza performancecomparisonbetweendeeplearningmodelsforfaultclassificationintransmissionlinesusingtimeseriesdata AT muhammadfaheem performancecomparisonbetweendeeplearningmodelsforfaultclassificationintransmissionlinesusingtimeseriesdata AT ashfaqueahmedhashmani performancecomparisonbetweendeeplearningmodelsforfaultclassificationintransmissionlinesusingtimeseriesdata AT rumaisanadeem performancecomparisonbetweendeeplearningmodelsforfaultclassificationintransmissionlinesusingtimeseriesdata |