Photovoltaics Plant Fault Detection Using Deep Learning Techniques
Solar energy is the fastest-growing clean and sustainable energy source, outperforming other forms of energy generation. Usually, solar panels are low maintenance and do not require permanent service. However, plenty of problems can result in a production loss of up to ~20% since a failed panel will...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/15/3728 |
| _version_ | 1827618385803870208 |
|---|---|
| author | Sherozbek Jumaboev Dadajon Jurakuziev Malrey Lee |
| author_facet | Sherozbek Jumaboev Dadajon Jurakuziev Malrey Lee |
| author_sort | Sherozbek Jumaboev |
| collection | DOAJ |
| description | Solar energy is the fastest-growing clean and sustainable energy source, outperforming other forms of energy generation. Usually, solar panels are low maintenance and do not require permanent service. However, plenty of problems can result in a production loss of up to ~20% since a failed panel will impact the generation of a whole array. High-quality and timely maintenance of the power plant will reduce the cost of its repair and, most importantly, increase the life of the power plant and the total generation of electricity. Manual monitoring of panels is costly and time-consuming on large solar plantations; moreover, solar plantations located distantly are more complicated for humans to access. This paper presents deep learning-based photovoltaics fault detection techniques using thermal images obtained from an unmanned aerial vehicle (UAV) equipped with infrared sensors. We implemented the three most accurate segmentation models to detect defective panels on large solar plantations. The models employed in this work are DeepLabV3+, Feature Pyramid Network (FPN) and U-Net with different encoder architectures. The obtained results revealed intersection over union (IoU) of 79%, 85%, 86%, and dice coefficients of 87%, 92%, 94% for DeepLabV3+, FPN, and U-Net, respectively. The implemented models showed efficient performance and proved effective to resolve these challenges. |
| first_indexed | 2024-03-09T10:05:51Z |
| format | Article |
| id | doaj.art-d329c7c5bea14249a6319dc7124e5bd6 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T10:05:51Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-d329c7c5bea14249a6319dc7124e5bd62023-12-01T23:08:33ZengMDPI AGRemote Sensing2072-42922022-08-011415372810.3390/rs14153728Photovoltaics Plant Fault Detection Using Deep Learning TechniquesSherozbek Jumaboev0Dadajon Jurakuziev1Malrey Lee2Graduate School of Integrated Energy-AI, Jeonbuk National University, Jeonju 54896, KoreaGraduate School of Integrated Energy-AI, Jeonbuk National University, Jeonju 54896, KoreaInstitute for Education Innovation, Jeonbuk National University, Jeonju 54896, KoreaSolar energy is the fastest-growing clean and sustainable energy source, outperforming other forms of energy generation. Usually, solar panels are low maintenance and do not require permanent service. However, plenty of problems can result in a production loss of up to ~20% since a failed panel will impact the generation of a whole array. High-quality and timely maintenance of the power plant will reduce the cost of its repair and, most importantly, increase the life of the power plant and the total generation of electricity. Manual monitoring of panels is costly and time-consuming on large solar plantations; moreover, solar plantations located distantly are more complicated for humans to access. This paper presents deep learning-based photovoltaics fault detection techniques using thermal images obtained from an unmanned aerial vehicle (UAV) equipped with infrared sensors. We implemented the three most accurate segmentation models to detect defective panels on large solar plantations. The models employed in this work are DeepLabV3+, Feature Pyramid Network (FPN) and U-Net with different encoder architectures. The obtained results revealed intersection over union (IoU) of 79%, 85%, 86%, and dice coefficients of 87%, 92%, 94% for DeepLabV3+, FPN, and U-Net, respectively. The implemented models showed efficient performance and proved effective to resolve these challenges.https://www.mdpi.com/2072-4292/14/15/3728PV plantfault detectionpanel defectssemantic segmentationFPNU-Net |
| spellingShingle | Sherozbek Jumaboev Dadajon Jurakuziev Malrey Lee Photovoltaics Plant Fault Detection Using Deep Learning Techniques Remote Sensing PV plant fault detection panel defects semantic segmentation FPN U-Net |
| title | Photovoltaics Plant Fault Detection Using Deep Learning Techniques |
| title_full | Photovoltaics Plant Fault Detection Using Deep Learning Techniques |
| title_fullStr | Photovoltaics Plant Fault Detection Using Deep Learning Techniques |
| title_full_unstemmed | Photovoltaics Plant Fault Detection Using Deep Learning Techniques |
| title_short | Photovoltaics Plant Fault Detection Using Deep Learning Techniques |
| title_sort | photovoltaics plant fault detection using deep learning techniques |
| topic | PV plant fault detection panel defects semantic segmentation FPN U-Net |
| url | https://www.mdpi.com/2072-4292/14/15/3728 |
| work_keys_str_mv | AT sherozbekjumaboev photovoltaicsplantfaultdetectionusingdeeplearningtechniques AT dadajonjurakuziev photovoltaicsplantfaultdetectionusingdeeplearningtechniques AT malreylee photovoltaicsplantfaultdetectionusingdeeplearningtechniques |