Fault Diagnosis for PV Modules Based on AlexNet and Symmetrized Dot Pattern

Meng-Hui Wang, Chun-Chun Hung, Shiue- Der Lu (), Zong-Han Lin and Cheng-Chien Kuo
Additional contact information
Meng-Hui Wang: Department of Electrical Engineering, National Chin-Yi University of Technology, Taichung 411, Taiwan
Chun-Chun Hung: Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei 106, Taiwan
Shiue- Der Lu: Department of Electrical Engineering, National Chin-Yi University of Technology, Taichung 411, Taiwan
Zong-Han Lin: Department of Electrical Engineering, National Chin-Yi University of Technology, Taichung 411, Taiwan
Cheng-Chien Kuo: Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei 106, Taiwan

Energies, 2023, vol. 16, issue 22, 1-15

Abstract: Faults in solar photovoltaic (PV) modules often result from component damage, leading to voltage fluctuations and decreased stability in the power system. In this study, the original voltage signals of different PV modules show little variation. Therefore, a solution that combines symmetrized dot pattern (SDP) and AlexNet for fault detection in PV modules was proposed. This solution investigates three common faults: poor welding, cracking, and bypass diode failure, which can be applied to fault-free modules. First, a high-frequency signal was input into the PV module, and the raw signal was captured using an NI PXI-5105 high-speed data acquisition card. Next, we used SDP to process the signal and create images with specific snowflake-like features. These images were used as a basis for fault diagnosis. Finally, deep-learning algorithms were used to perform status detection on the PV module. This research also used 3200 training samples and 800 test samples (200 for each type) to evaluate a new method for diagnosing faults in PV modules. The results show that the accuracy of the new method reached 99.8%, surpassing traditional convolutional neural networks (CNN) and extension neural networks (ENN), whose accuracies were 99.5% and 91.75%, respectively. Furthermore, this study compares the proposed method with more traditional numerical fault diagnosis methods. SDP effectively extracts fault signals and presents them as images. With AlexNet used for fault identification, the method excels in accuracy, training time, and testing time, thereby enhancing the stability and reliability of future energy systems.

Keywords: photovoltaic; symmetrized dot pattern; AlexNet; convolutional neural network; extension neural network (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/16/22/7563/pdf (application/pdf)
https://www.mdpi.com/1996-1073/16/22/7563/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:16:y:2023:i:22:p:7563-:d:1279503

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().