article · Sustainability
Photovoltaic systems require careful monitoring and diagnosis of faults to ensure reliable operation during the shift towards sustainable energy. A three-step deep learning framework provides automated fault detection and classification for solar arrays. The process begins with developing and fine-tuning a photovoltaic model through a heuristic optimisation technique. Next, a database is assembled using model data together with monitored solar irradiance and module temperatures under normal and faulty operating conditions. Finally, features are processed using a combined Convolutional Neural Network and Bidirectional Gated Recurrent Unit architecture, which leverages parallel and sequential processing simultaneously. Testing confirms the capability of this network to identify and classify conditions including open circuits, short circuits, and partial shading. The findings demonstrate that separating detection and diagnosis into distinct stages yields more effective results than using neural networks to identify faults in a single step.
Solar power generation depends heavily on continuous system uptime and early problem identification. By identifying and categorising disruptions such as partial shading or electrical short circuits quickly and accurately, advanced monitoring helps maintain solar energy production. Ensuring consistent performance and early intervention supports the broader reliability and long-term viability of renewable energy installations.
This methodology offers a diagnostic framework suitable for solar farm operators and energy management software developers seeking automated monitoring tools. The application targets the identification of open circuits, short circuits, and shading events. Because the work is validated using a combined model and operational dataset within a study, it sits at an applied, tested stage requiring integration into commercial monitoring hardware or SCADA systems before deployment.
AI-generated from the published abstract. Always read the original work before citing.
The meticulous monitoring and diagnosis of faults in photovoltaic (PV) systems enhances their reliability and facilitates a smooth transition to sustainable energy. This paper introduces a novel application of deep learning for fault detection and diagnosis in PV systems, employing a three-step approach. Firstly, a robust PV model is developed and fine-tuned using a heuristic optimization approach. Secondly, a comprehensive database is constructed, incorporating PV model data alongside monitored module temperature and solar irradiance for both healthy and faulty operation conditions. Lastly, fault classification utilizes features extracted from a combination consisting of a Convolutional Neural Network (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU). The amalgamation of parallel and sequential processing enables the neural network to leverage the strengths of both convolutional and recurrent layers concurrently, facilitating effective fault detection and diagnosis. The results affirm the proposed technique’s efficacy in detecting and classifying various PV fault types, such as open circuits, short circuits, and partial shading. Furthermore, this work underscores the significance of dividing fault detection and diagnosis into two distinct steps rather than employing deep learning neural networks to determine fault types directly.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/su16031012
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
