Graph-Variational Convolutional Autoencoder-Based Fault Detection and Diagnosis for Photovoltaic Arrays
Solar energy is a critical renewable energy source, with solar arrays or photovoltaic systems widely used to convert solar energy into electrical energy. However, solar array systems can develop faults and may exhibit poor performance. Diagnosing and resolving faults within these systems promptly is...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/12/12/894 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846103876343693312 |
|---|---|
| author | Murshedul Arifeen Andrei Petrovski Md Junayed Hasan Khandaker Noman Wasib Ul Navid Auwal Haruna |
| author_facet | Murshedul Arifeen Andrei Petrovski Md Junayed Hasan Khandaker Noman Wasib Ul Navid Auwal Haruna |
| author_sort | Murshedul Arifeen |
| collection | DOAJ |
| description | Solar energy is a critical renewable energy source, with solar arrays or photovoltaic systems widely used to convert solar energy into electrical energy. However, solar array systems can develop faults and may exhibit poor performance. Diagnosing and resolving faults within these systems promptly is crucial to ensure reliability and efficiency in energy generation. Autoencoders and their variants have gained popularity in recent studies for detecting and diagnosing faults in solar arrays. However, traditional autoencoder models often struggle to capture the spatial and temporal relationships present in photovoltaic sensor data. This paper introduces a deep learning model that combines a graph convolutional network with a variational autoencoder to diagnose faults in solar arrays. The graph convolutional network effectively learns from spatial and temporal sensor data, significantly improving fault detection performance. We evaluated the proposed deep learning model on a recently published solar array dataset for an integrated power probability table mode. The experimental results show that the model achieves a fault detection rate exceeding 95% and outperforms the conventional autoencoder models. We also identified faulty components by analyzing the model’s reconstruction error for each feature, and we validated the analysis through the Kolmogorov–Smirnov test and noise injection techniques. |
| format | Article |
| id | doaj-art-a68e9bb8f0bd42d6b8c9842c6321237e |
| institution | Kabale University |
| issn | 2075-1702 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj-art-a68e9bb8f0bd42d6b8c9842c6321237e2024-12-27T14:37:06ZengMDPI AGMachines2075-17022024-12-01121289410.3390/machines12120894Graph-Variational Convolutional Autoencoder-Based Fault Detection and Diagnosis for Photovoltaic ArraysMurshedul Arifeen0Andrei Petrovski1Md Junayed Hasan2Khandaker Noman3Wasib Ul Navid4Auwal Haruna5School of Computing, Engineering and Technology, Robert Gordon University, Aberdeen AB10 7AQ, UKFaculty of Secure Information Technologies, ITMO University, St. Petersburg 197101, RussiaDataxense, Aberdeen AB11 5RG, UKSchool of Civil Aviation, Northwestern Polytechnical University, Xi’an 710129, ChinaSchool of Civil Aviation, Northwestern Polytechnical University, Xi’an 710129, ChinaSchool of Aeronautics, Northwestern Polytechnical University, Xi’an 710129, ChinaSolar energy is a critical renewable energy source, with solar arrays or photovoltaic systems widely used to convert solar energy into electrical energy. However, solar array systems can develop faults and may exhibit poor performance. Diagnosing and resolving faults within these systems promptly is crucial to ensure reliability and efficiency in energy generation. Autoencoders and their variants have gained popularity in recent studies for detecting and diagnosing faults in solar arrays. However, traditional autoencoder models often struggle to capture the spatial and temporal relationships present in photovoltaic sensor data. This paper introduces a deep learning model that combines a graph convolutional network with a variational autoencoder to diagnose faults in solar arrays. The graph convolutional network effectively learns from spatial and temporal sensor data, significantly improving fault detection performance. We evaluated the proposed deep learning model on a recently published solar array dataset for an integrated power probability table mode. The experimental results show that the model achieves a fault detection rate exceeding 95% and outperforms the conventional autoencoder models. We also identified faulty components by analyzing the model’s reconstruction error for each feature, and we validated the analysis through the Kolmogorov–Smirnov test and noise injection techniques.https://www.mdpi.com/2075-1702/12/12/894solar arrayphotovoltaic arrayfault detectionfault diagnosisgraph convolutional networkvariational autoencoder |
| spellingShingle | Murshedul Arifeen Andrei Petrovski Md Junayed Hasan Khandaker Noman Wasib Ul Navid Auwal Haruna Graph-Variational Convolutional Autoencoder-Based Fault Detection and Diagnosis for Photovoltaic Arrays Machines solar array photovoltaic array fault detection fault diagnosis graph convolutional network variational autoencoder |
| title | Graph-Variational Convolutional Autoencoder-Based Fault Detection and Diagnosis for Photovoltaic Arrays |
| title_full | Graph-Variational Convolutional Autoencoder-Based Fault Detection and Diagnosis for Photovoltaic Arrays |
| title_fullStr | Graph-Variational Convolutional Autoencoder-Based Fault Detection and Diagnosis for Photovoltaic Arrays |
| title_full_unstemmed | Graph-Variational Convolutional Autoencoder-Based Fault Detection and Diagnosis for Photovoltaic Arrays |
| title_short | Graph-Variational Convolutional Autoencoder-Based Fault Detection and Diagnosis for Photovoltaic Arrays |
| title_sort | graph variational convolutional autoencoder based fault detection and diagnosis for photovoltaic arrays |
| topic | solar array photovoltaic array fault detection fault diagnosis graph convolutional network variational autoencoder |
| url | https://www.mdpi.com/2075-1702/12/12/894 |
| work_keys_str_mv | AT murshedularifeen graphvariationalconvolutionalautoencoderbasedfaultdetectionanddiagnosisforphotovoltaicarrays AT andreipetrovski graphvariationalconvolutionalautoencoderbasedfaultdetectionanddiagnosisforphotovoltaicarrays AT mdjunayedhasan graphvariationalconvolutionalautoencoderbasedfaultdetectionanddiagnosisforphotovoltaicarrays AT khandakernoman graphvariationalconvolutionalautoencoderbasedfaultdetectionanddiagnosisforphotovoltaicarrays AT wasibulnavid graphvariationalconvolutionalautoencoderbasedfaultdetectionanddiagnosisforphotovoltaicarrays AT auwalharuna graphvariationalconvolutionalautoencoderbasedfaultdetectionanddiagnosisforphotovoltaicarrays |