Photovoltaic Panels Classification Using Isolated and Transfer Learned Deep Neural Models Using Infrared Thermographic Images
Defective PV panels reduce the efficiency of the whole PV string, causing loss of investment by decreasing its efficiency and lifetime. In this study, firstly, an isolated convolution neural model (ICNM) was prepared from scratch to classify the infrared images of PV panels based on their health, i....
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/16/5668 |
| _version_ | 1797522045177692160 |
|---|---|
| author | Waqas Ahmed Aamir Hanif Karam Dad Kallu Abbas Z. Kouzani Muhammad Umair Ali Amad Zafar |
| author_facet | Waqas Ahmed Aamir Hanif Karam Dad Kallu Abbas Z. Kouzani Muhammad Umair Ali Amad Zafar |
| author_sort | Waqas Ahmed |
| collection | DOAJ |
| description | Defective PV panels reduce the efficiency of the whole PV string, causing loss of investment by decreasing its efficiency and lifetime. In this study, firstly, an isolated convolution neural model (ICNM) was prepared from scratch to classify the infrared images of PV panels based on their health, i.e., healthy, hotspot, and faulty. The ICNM occupies the least memory, and it also has the simplest architecture, lowest execution time, and an accuracy of 96% compared to transfer learned pre-trained ShuffleNet, GoogleNet, and SqueezeNet models. Afterward, ICNM, based on its advantages, is reused through transfer learning to classify the defects of PV panels into five classes, i.e., bird drop, single, patchwork, horizontally aligned string, and block with 97.62% testing accuracy. This proposed approach can identify and classify the PV panels based on their health and defects faster with high accuracy and occupies the least amount of the system’s memory, resulting in savings in the PV investment. |
| first_indexed | 2024-03-10T08:24:00Z |
| format | Article |
| id | doaj.art-fbbac52ea74e4350b8c9f721e6d57fee |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T08:24:00Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-fbbac52ea74e4350b8c9f721e6d57fee2023-11-22T09:43:46ZengMDPI AGSensors1424-82202021-08-012116566810.3390/s21165668Photovoltaic Panels Classification Using Isolated and Transfer Learned Deep Neural Models Using Infrared Thermographic ImagesWaqas Ahmed0Aamir Hanif1Karam Dad Kallu2Abbas Z. Kouzani3Muhammad Umair Ali4Amad Zafar5Department of Electrical Engineering, University of Wah, Wah Cantt 47040, PakistanDepartment of Electrical Engineering, University of Wah, Wah Cantt 47040, PakistanDepartment of Robotics and Intelligent Machine Engineering (RIME), School of Mechanical and Manufacturing Engineering (SMME), National University of Sciences and Technology (NUST) H-12, Islamabad 44000, PakistanSchool of Engineering, Deakin University, Geelong, VIC 3216, AustraliaDepartment of Unmanned Vehicle Engineering, Sejong University, Seoul 05006, KoreaDepartment of Electrical Engineering, Islamabad Campus, University of Lahore, Islamabad 54590, PakistanDefective PV panels reduce the efficiency of the whole PV string, causing loss of investment by decreasing its efficiency and lifetime. In this study, firstly, an isolated convolution neural model (ICNM) was prepared from scratch to classify the infrared images of PV panels based on their health, i.e., healthy, hotspot, and faulty. The ICNM occupies the least memory, and it also has the simplest architecture, lowest execution time, and an accuracy of 96% compared to transfer learned pre-trained ShuffleNet, GoogleNet, and SqueezeNet models. Afterward, ICNM, based on its advantages, is reused through transfer learning to classify the defects of PV panels into five classes, i.e., bird drop, single, patchwork, horizontally aligned string, and block with 97.62% testing accuracy. This proposed approach can identify and classify the PV panels based on their health and defects faster with high accuracy and occupies the least amount of the system’s memory, resulting in savings in the PV investment.https://www.mdpi.com/1424-8220/21/16/5668deep convolution neural networkPV panelsinfrared imageshotspots |
| spellingShingle | Waqas Ahmed Aamir Hanif Karam Dad Kallu Abbas Z. Kouzani Muhammad Umair Ali Amad Zafar Photovoltaic Panels Classification Using Isolated and Transfer Learned Deep Neural Models Using Infrared Thermographic Images Sensors deep convolution neural network PV panels infrared images hotspots |
| title | Photovoltaic Panels Classification Using Isolated and Transfer Learned Deep Neural Models Using Infrared Thermographic Images |
| title_full | Photovoltaic Panels Classification Using Isolated and Transfer Learned Deep Neural Models Using Infrared Thermographic Images |
| title_fullStr | Photovoltaic Panels Classification Using Isolated and Transfer Learned Deep Neural Models Using Infrared Thermographic Images |
| title_full_unstemmed | Photovoltaic Panels Classification Using Isolated and Transfer Learned Deep Neural Models Using Infrared Thermographic Images |
| title_short | Photovoltaic Panels Classification Using Isolated and Transfer Learned Deep Neural Models Using Infrared Thermographic Images |
| title_sort | photovoltaic panels classification using isolated and transfer learned deep neural models using infrared thermographic images |
| topic | deep convolution neural network PV panels infrared images hotspots |
| url | https://www.mdpi.com/1424-8220/21/16/5668 |
| work_keys_str_mv | AT waqasahmed photovoltaicpanelsclassificationusingisolatedandtransferlearneddeepneuralmodelsusinginfraredthermographicimages AT aamirhanif photovoltaicpanelsclassificationusingisolatedandtransferlearneddeepneuralmodelsusinginfraredthermographicimages AT karamdadkallu photovoltaicpanelsclassificationusingisolatedandtransferlearneddeepneuralmodelsusinginfraredthermographicimages AT abbaszkouzani photovoltaicpanelsclassificationusingisolatedandtransferlearneddeepneuralmodelsusinginfraredthermographicimages AT muhammadumairali photovoltaicpanelsclassificationusingisolatedandtransferlearneddeepneuralmodelsusinginfraredthermographicimages AT amadzafar photovoltaicpanelsclassificationusingisolatedandtransferlearneddeepneuralmodelsusinginfraredthermographicimages |