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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Machines (Basel) Jg. 12; H. 12; S. 894
Hauptverfasser: Arifeen, Murshedul, Petrovski, Andrei, Hasan, Md Junayed, Noman, Khandaker, Navid, Wasib Ul, Haruna, Auwal
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 01.12.2024
Schlagworte:
Arrays
Artificial neural networks
Deep learning
Energy
Error analysis
Error detection
Fault detection
Fault diagnosis
Faults
Fourier transforms
graph convolutional network
Machine learning
Neural networks
Performance evaluation
photovoltaic array
Renewable energy sources
Sensor arrays
Sensors
solar array
Solar arrays
Solar collectors
Solar energy
Solar energy conversion
Solar energy industry
Spatiotemporal data
Spread spectrum
System reliability
Time series
variational autoencoder
New Jersey
ISSN:2075-1702, 2075-1702
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2075-1702
2075-1702
DOI:10.3390/machines12120894