High-efficiency low-power microdefect detection in photovoltaic cells via a field programmable gate array-accelerated dual-flow network

Haoxuan Wang, Huaian Chen, Ben Wang, Yi Jin, Guiqiang Li and Yan Kan

Applied Energy, 2022, vol. 318, issue C, No S0306261922005645

Abstract: Harvesting solar energy through photovoltaic (PV) power systems plays an important role in achieving the goal of carbon neutrality. However, the early microdefects in PV cells considerably affect the efficiencies of PV power systems. In addition, the growing number of PV power systems require more efficient and economic detection methods to ensure the long-term efficiency of PV power systems. To address this problem, recent state-of-the-art methods have attempted to use a convolutional neural network (CNN) model. However, these methods involve large amounts of parameters and require too many calculations, considerably affecting the efficiency, economy, and flexibility in real applications. In this work, we propose a lightweight dual-flow defect detection network (DDDN) and accelerate it with a field programmable gate array (FPGA) based on the developed dual-flow parallel computing architecture (DPCA). The DDDN can accurately detect early microdefects in PV cells with low calculations and storage costs, while the DPCA optimizes the data access and computation process to improve detection efficiency and reduce power consumption. Benefiting from the designed DDDN and DPCA, the proposed system achieves a high detection accuracy (88.26%), low power consumption (22 W), and competitive detection efficiency, making it more suitable than previous methods for ensuring the long-term efficiency of PV power systems.

Keywords: Photovoltaic modules; Defect detection; Deep learning; Convolutional neural network; Field programmable gate array; Electroluminescence imaging (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261922005645
Full text for ScienceDirect subscribers only

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:eee:appene:v:318:y:2022:i:c:s0306261922005645

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2022.119203

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().