https://orcid.org/0000-0003-2839-7241
![Sample our Built Environment journals, sign in here to start your access, Latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5926/TOC-Subject-Sample-2021-Built-Environment.jpg"})
ABSTRACT
Solar panel performance is affected by ambient temperature, sunlight, module surface temperature, dust, and shadows. Dust inhibits sunlight from reaching photovoltaic modules, reducing power generation. Dust is aerosol pollution from natural or human-made sources. Dust on photovoltaic (PV) panels reduces power generation and raises the surface temperature, shortening panel life. This work uses a Fluke TiS60 Thermal Imager for detection of hotspot created by the accumulation of dust and further classification of the faulty and healthy images is done. The image classifiers used in this paper are SqueezeNet and AlexNet transfer learning methods, the accuracy of both methods is compared, and AlexNet performs best with an accuracy of 99.3%. Further, the effect of dust on PV modules is studied, and hotspots are created intentionally with the help of dust for study purposes. Initially, 50% of a solar module is covered with dust and then 100% of the solar module is covered with dust particles to find the power loss, when a thin layer of dust was spread over 50% of a module power loss is of 4.7% and when a thick layer of dust is spread over 50% the power loss is 5.9%, when thin layer of dust was applied over 100% of a module power loss is of 6.49% and when thick layer of dust is spread over 100% the power loss is 10.17%. This analysis for a healthy and faulty panel is done that helps PV module inspection by facilitating a more precise and cost-effective identification of PV defects.
Nomenclature
| AI | = | Artificial Intelligence |
| CLs | = | Convolutional layers |
| CNN | = | Convolutional Neural Network |
| DCNN | = | Deep Convolutional Neural Network |
| DRNN | = | Deep recurrent neural network |
| FDC | = | Fault detection and classification |
| FLCs | = | Fully connected layers |
| IR | = | Infrared image |
| LWIR | = | Long wave Infrared images |
| MATLAB | = | Matrix Laboratory |
| MWIR | = | Mid wave Infrared images |
| MAE | = | Mean average Error |
| NN | = | Neural network |
| NB-CNN | = | Nave Bayes Convolutional Neural Network |
| PL | = | Pooling Layers |
| PV | = | Photovoltaic |
| RMSE | = | Root mean square error |
| SGDM | = | Stochastic gradient descent with momentum |
| SVM | = | Support vector machine |
| TI | = | Thermography images |
Disclosure statement
No potential conflict of interest was reported by the authors.
Dataset Availability Statement
Data were recorded from a 5 kW solar panel by a solar analyzer on the rooftop of Utilization Electrical Engineering Lab, Delhi Technological University, New Delhi, India.
Declaration
The authors declare that the present research has no financial or personal ties to any individual or group that could unreasonably affect this work. This manuscript is the author’s own work and does not contain material taken from another source. All data measures are real, unaltered results, and this work has never been published or submitted to another journal for publication consideration. Also, none of the authors has any financial or scientific conflicts of interest with regard to the research described in this manuscript.
Additional information
Funding
Notes on contributors
Rahma Aman
Rahma Aman has received the M.Tech. degree in Control and Instrumentation systems from Electrical engineering department, Jamia Millia Islamia University, New Delhi, India in 2021. She completed the B.Tech. degree in Electrical engineering from United college of engineering and Research, Uttar Pradesh, India in 2018. Presently, she is pursuing the Ph.D. degree from Delhi Technological University, Delhi, India. Her research interests focus on renewable energy integration, optimization techniques, PV systems under partial shading conditions and deep learning approaches for power maximization.
M. Rizwan
M. Rizwan did his post-doctoral research at Virginia Polytechnic Institute and State University, USA. He has more than 21 years of teaching and research experience. Dr. Rizwan has successfully completed three research projects in the area of renewable energy systems and published and presented more than 180 research papers in reputed international/national journals including IEEE transactions and conference proceedings. Presently he is working on two international and one national research projects in the area of solar PV and EVs. Dr. Rizwan has authored one book for CRC Press, USA and edited one book for AIP Publishing, USA. Recently he has authored one book in energy science engineering for AICTE. He is the recipient of Raman Fellowships for Post-Doctoral Research for Indian Scholars in USA, DST Start Up Grants (Young Scientists) and many more. His area of interest includes soft computing applications in power engineering, renewable energy systems, building energy management, smart grid etc. He is a Sr. Member of IEEE, Life Member of ISTE, Life Member of SSI, Member of International Association of Engineers (IAENG), and many other reputed societies.
Astitva Kumar
Astitva Kumar has completed his B.Tech in 2013 from Uttar Pradesh Technical University in Electrical Engineering. He received his M.Tech degree in Control and Instrumentation from Delhi Technological University, Delhi, India in 2015. He further enrolled in Ph.D. and received his Doctorate degree on the topic “Optimal Design of SPV System and Application” from Delhi Technological University, Delhi, India in 2021. Presently, he is working as an Assistant Professor in Electrical Engineering Department, Netaji Subhash University of Technology, Delhi, India. He has published more than 18 research papers in reputed international journals and conference proceedings. He is currently, an active reviewer for numerous publishers such as IEEE, Springer, Elsevier and Scopus indexed international conferences. He has received Research Excellence Award in 2021 and 2023 for his commendable research and has also received international travel grants for presenting paper in international conferences. He has research experience of working on various government and international organization funded projects. His research interest focusses on utilization of electrical energy, hybrid energy systems, advanced metaheuristic techniques, smart building energy management systems, agrivoltaics, PV power forecasting, energy management systems and intelligent controllers for hybrid energy systems.