Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Towards self-diagnostic solar farms: Leveraging EfficientNet and class activation mapping for predictive maintenance

International Journal of Renewable Energy Development : JRED · Vol. 15 No. 2 (2026) · hlm. 443–451

DOI
10.61435/ijred.2026.62298
ISSN
2252-4940
Terbit
2026-03-01
Penerbit
Center of Biomass & Renewable Energy (CBIORE)
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

The high rate of utility photovoltaic (PV) system development has increased the demand for stable, automated, and interpretable fault diagnostic systems that can be utilised in real-world environments. Solar farms with a large size are increasingly making conventional manual inspection methods impractical, and triggering the use of intelligent data-driven solutions. This paper presents a justifiable deep learning model for automated fault classification of solar panels based on the EfficientNet-B2 architecture combined with Gradient-weighted Class Activation Mapping (Grad-CAM). A six-class image dataset made of clean panels and five prevalent fault types is used. The two stages of transfer learning used to train the model include a warm-up phase and selective fine-tuning of upper network layers. Data augmentation is also performed extensively to make it more robust to changing illumination, viewing angles, and environmental noise. The experimental findings reveal consistent convergence and excellent generalization ability, and a high level of classification accuracy of all types of faults, as it achieved high classification accuracy, macro-averaged F1-scores exceeding 0.90 for most fault classes, and a macro-averaged ROC–AUC of approximately 0.981, highlighting the robustness and reliability of the proposed diagnostic model. The suggested structure will provide a scalable, interpretable, and realistic predictive maintenance of solar farms of the next generation with self-diagnostic capabilities.

Kata kunci

Jaringan kolaborasi para penulis

29 penulis · 119 tautan kepenulisan bersama · 70 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Ho Chi Minh City University of Transport
  • HUTECH University
  • Dong A University
  • Trường Đại học Công nghệ Đồng Nai
  • Mepco Schlenk Engineering College
  • Van Lang University
  • Delhi Skill and Entrepreneurship University
  • Organisasi lain
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Thanh Tuan LeHUTECH University3
Huu Cuong LeHo Chi Minh City University of Transport3
Dao Nam CaoHo Chi Minh City University of Transport2
Duy Tân NguyễnHo Chi Minh City University of Transport1
Diep Ngoc Long HuynhHUTECH University1
Thanh Hai NguyenTrường Đại học Công nghệ Đồng Nai1
Anh Vu VoAfiliasi tidak diketahui1
Van Quy NguyenHo Chi Minh City University of Transport1
J. Chandra PriyaMepco Schlenk Engineering College1
Nguyen Viet Linh LeVan Lang University1
Dhanaraj Savary NasanAfiliasi tidak diketahui1
Minh Ho TranDong A University1
Phuoc Quy Phong NguyenHo Chi Minh City University of Transport1
Prabhakar SharmaDelhi Skill and Entrepreneurship University1
Việt Dũng TrầnHo Chi Minh City University of Transport1
Malayathi SivaramakrishnaiahAfiliasi tidak diketahui1
Van Quy NguyenHo Chi Minh City University of Transport1
Prabhu ParamasivamChitkara University1
Elvis AdrilPoliteknik Negeri Padang1
Minh Xuan LeDong A University1
Anh Quan NguyenHo Chi Minh City University of Transport1
Khac Binh LeVinh University of Technology Education1
Van Vang LeHo Chi Minh City University of Transport1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) https://ijred.cbiore.id/index.php/ijred/oai, pertama di-harvest 8 Nov 2026, terakhir terlihat 16 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Towards self-diagnostic solar farms: Leveraging EfficientNet and class activation mapping for predictive maintenance</dc:title>
	<dc:creator>Nguyen, Du</dc:creator>
	<dc:creator>Nguyen, Thi Bich Ngoc</dc:creator>
	<dc:creator>Nguyen, Duc Chuan</dc:creator>
	<dc:creator>Chau, Thanh Hieu</dc:creator>
	<dc:creator>Duong, Minh Thai</dc:creator>
	<dc:creator>Dang, Thanh Nam</dc:creator>
	<dc:subject xml:lang="en-US">Photovoltaic fault diagnosis; EfficientNet-B2; Explainable artificial intelligence; Grad-CAM; Deep learning; Solar energy systems</dc:subject>
	<dc:description xml:lang="en-US">The high rate of utility photovoltaic (PV) system development has increased the demand for stable, automated, and interpretable fault diagnostic systems that can be utilised in real-world environments. Solar farms with a large size are increasingly making conventional manual inspection methods impractical, and triggering the use of intelligent data-driven solutions. This paper presents a justifiable deep learning model for automated fault classification of solar panels based on the EfficientNet-B2 architecture combined with Gradient-weighted Class Activation Mapping (Grad-CAM). A six-class image dataset made of clean panels and five prevalent fault types is used. The two stages of transfer learning used to train the model include a warm-up phase and selective fine-tuning of upper network layers. Data augmentation is also performed extensively to make it more robust to changing illumination, viewing angles, and environmental noise. The experimental findings reveal consistent convergence and excellent generalization ability, and a high level of classification accuracy of all types of faults, as it achieved high classification accuracy, macro-averaged F1-scores exceeding 0.90 for most fault classes, and a macro-averaged ROC–AUC of approximately 0.981, highlighting the robustness and reliability of the proposed diagnostic model. The suggested structure will provide a scalable, interpretable, and realistic predictive maintenance of solar farms of the next generation with self-diagnostic capabilities.</dc:description>
	<dc:publisher xml:lang="en-US">Center of Biomass &amp; Renewable Energy (CBIORE)</dc:publisher>
	<dc:date>2026-03-01</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US"></dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://ijred.cbiore.id/index.php/ijred/article/view/62298</dc:identifier>
	<dc:identifier>10.61435/ijred.2026.62298</dc:identifier>
	<dc:source xml:lang="en-US">International Journal of Renewable Energy Development; Vol 15, No 2 (2026): March 2026; 443-451</dc:source>
	<dc:source>2252-4940</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://ijred.cbiore.id/index.php/ijred/article/view/62298/pdf</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2026 The Author(s). Published by Centre of Biomass and Renewable Energy (CBIORE)</dc:rights>
	<dc:rights xml:lang="en-US">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>