แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Prasit Nangtin. Transfer learning evaluation of convolutional neural network architectures for thermal image classification of solar modules. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2025.
Transfer learning evaluation of convolutional neural network architectures for thermal image classification of solar modules
Name: Chutinun Phungket
Organization :
Pathumwan Institute of Technology. Faculty of Engineering
Email :
chutinun@pit.ac.th
Name: Prasit Nangtin
Organization :
Pathumwan Institute of Technology. Faculty of Engineering
Email :
prasit@pit.ac.th
keyword:
Convolutional neural networks
LCSH:
Image processing
-- Digital techniques
LCSH:
Solar cells
-- Testing
LCSH:
Thermography
Abstract:
Accurate anomaly classification in solar modules
is crucial for efficient solar power system monitoring and
maintenance. This study explores deep learning, specifically
Convolutional Neural Networks (CNNs), for automated defect
classification in thermal images. We employed transfer learning
with pre-trained AlexNet and GoogleNet architectures,
comparing static feature extraction and fine-tuning. Using a
dataset of thermal images categorized as no anomaly, cracked,
or soiled modules, the fully fine-tuned GoogleNet model
achieved the highest classification accuracy 95.5%,
outperforming AlexNet and traditional feature-based methods.
GoogleNet's superior performance stems from its Inception
modules, which learn more discriminative features by
employing multiple convolutional filter sizes within the same
layer, capturing complex thermal image patterns. Fine-tuning
further boosts performance by adapting pre-trained knowledge
to the specific task. These results demonstrate deep learning's
potential for enhancing solar system maintenance reliability and
efficiency.
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2025
Modified:
2025-06-18
Issued:
2025-06-18
บทความ/Article
application/pdf
BibliograpyCitation :
In Electrical Engineering Academic Association (Thailand) and King Mongkut's University of Technology North Bangkok. Department of Electrical and Computer Engineering. 13th International Electrical Engineering Congress (iEECON 2025) (P06259). Bangkok : Electrical Engineering Academic Association (Thailand), 2025
eng
©copyrights King Mongkut's University of Technology North Bangkok
RightsAccess:
ใช้เวลา
0.026445 วินาที
Chutinun Phungket
| Title | Contributor | Type |
|---|---|---|
| Deep convolutional neural networks for accurate solar module classification in thermal images
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Chutinun Phungket;Prasit Nangthin | บทความ/Article | |
| Transfer learning evaluation of convolutional neural network architectures for thermal image classification of solar modules
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Chutinun Phungket;Prasit Nangtin | บทความ/Article |
Prasit Nangtin