Automated Classification of Snow-Covered Solar Panel Surfaces Based on Deep Learning Approaches

作     者：Abdullah Ahmed Al-Dulaimi Muhammet Tahir Guneser Alaa Ali Hameed Mohammad Shukri Salman 

作者机构：Department of Electrical and Electronics EngineeringKarabuk UniversityKarabuk78100Turkey Department of Computer EngineeringIstinye UniversityIstanbul34303Turkey College of Engineering and TechnologyAmerican University of the Middle EastEgaila54200Kuwait 

出 版 物：《Computer Modeling in Engineering & Sciences》 (工程与科学中的计算机建模（英文）)

年 卷 期：2023年第136卷第9期

页      面：2291-2319页

核心收录：

学科分类：08[工学] 080502[工学-材料学] 0805[工学-材料科学与工程（可授工学、理学学位）] 

主　　题：Deep learning CNN models image classification solar panels solar panel defect detection 

摘      要：Recently,the demand for renewable energy has increased due to its environmental and economic *** panels are the mainstay for dealing with solar energy and converting it into another form of usable *** panels work under suitable climatic conditions that allow the light photons to access the solar cells,as any blocking of sunlight on these cells causes a halt in the panels work and restricts the carry of these ***,the panels are unable to work under these conditions.A layer of snow forms on the solar panels due to snowfall in areas with low ***,it causes an insulating layer on solar panels and the inability to produce electrical *** detection of snow-covered solar panels is crucial,as it allows us the opportunity to remove snow using some heating techniques more efficiently and restore the photovoltaics system to proper *** paper presents five deep learning models,■-16,■-19,ESNET-18,ESNET-50,and ESNET-101,which are used for the recognition and classification of solar panel *** this paper,two different cases were applied;the first case is performed on the original dataset without trying any kind of preprocessing,and the second case is extreme climate conditions and simulated by generating motion ***,the dataset was replicated using the upsampling technique in order to handle the unbalancing *** conducted dataset is divided into three different categories,namely;all_snow,no_snow,and partial *** fivemodels are trained,validated,and tested on this dataset under the same conditions 60%training,20%validation,and testing 20%for both *** accuracy of the models has been compared and verified to distinguish and classify the processed *** accuracy results in the first case showthat the comparedmodels■-16,■-19,ESNET-18,and ESNET-50 give 0.9592,while ESNET-101 gives *** the second case,the models outperformed their counterparts in the first case by evaluating performan