[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120401-en":3,"doc-seo-120401-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120401,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning Driven Shade Detection Using Infrared Image - Thesis","Photovoltaics converts light into electricity, enabling solar farms to generate power for homes and businesses. While solar energy is clean and renewable, solar output depends on sun availability and can be affected by partial shading and PV panel malfunctions. Advanced automated operation and maintenance systems improve efficiency by detecting these issues early using specialized image processing and machine learning. This thesis trains an ML classifier on infrared images of PV panels under different conditions to identify shaded cells. The approach achieves 65.46% mAP and deploys the classifier on an FPGA with 9.5s throughput for partial shading detection.","MACHINE LEARNING DRIVEN SHADE DETECTION USING INFRARED IMAGE  \nA Thesis By  \nMIR TANVEER ISLAM ORCID iD: 0009-0008-4123-4563  \nCalifornia State University, Fullerton Summer, 2024  \nIn partial fulfillment of the degree:  \nMaster of Science in Electrical Engineering  \nDepartment:  \nDepartment of Electrical and Computer Engineering  \nApproval Committee:  \nRakeshkumar Mahto, Department of Electrical and Computer Engineering, Committee Chair Kiran George, Department of Electrical and Computer Engineering  \nJaya Dofe, Department of Electrical and Computer Engineering  \nDOI:  \n10.5281/zenodo.13119629  \nKeywords:  \nphotovoltaics, machine learning, artificial intelligence, YOLOv3-tiny, PYNQ-Z2  \nAbstract:  \nPhotovoltaics is the process of converting light into electricity using semiconductor materials. Large-scale solar panels, known as solar farms, are installed to generate electricity and fed into the grid to power homes and businesses. Solar farming has several benefits, including being a clean and renewable energy source that can help reduce reliance on fossil fuels and decrease carbon emissions. However, solar farming also has challenges, such as the upfront cost of setting up a solar farm and the reliability of solar power, which only generates electricity when the sun is shining. To address these challenges, advanced automated operation and maintenance systems are used to monitor and improve the efficiency of solar farms. These systems use machine learning algorithms and specialized image processing techniques to identify issues such as partial shading and malfunctioning of PV panels. In this work, a machine learning (ML) classifier is trained using the infrared images of PV panels in different conditions to identify the presence of shaded cells in the panel that achieved 65.46% mAP and implemented the ML classifier in an FPGA with a throughput of 9.5s to determine the presence of partial shading.  \nTABLE OF CONTENTS  \nLIST OF TABLES ................................................................................................................................ iii  \nLIST OF FIGURES .............................................................................................................................. iv  \nACKNOWLEDGMENTS .................................................................................................................... v  \n1. INTRODUCTION .......................................................................................................................... 1  \n2. BACKGROUND THEORY ........................................................................................................... 4  \nSolar Panels and The Effects of Shade ........................................................................................... 4  \nMachine Learning ........................................................................................................................... 5  \nComputer Vision ....................................................................................................................... 6  \nObject Detection ....................................................................................................................... 7  \nField Programmable Gate Array ..................................................................................................... 9  \nPYNQ-Z2 ................................................................................................................................. 10  \nHigh-Level Synthesis ............................................................................................................... 12  \n3. SYSTEM DESIGN AND IMPLEMENTATION........................................................................... 14  \n4. EVALUATION AND CONCLUSION .......................................................................................... 21  \nEvaluation of the Model.................................................................................................","cbCaitezskRq0MCP","https://ap.wps.com/l/cbCaitezskRq0MCP","pdf",1484032,1,35,"English","en",105,"# List of Tables\n# List of Figures\n# Acknowledgments\n# 1. Introduction\n# 2. Background Theory\n## Solar Panels and The Effects of Shade\n## Machine Learning\n## Computer Vision\n## Object Detection\n## Field Programmable Gate Array\n## PYNQ-Z2\n## High-Level Synthesis\n# 3. System Design and Implementation\n# 4. Evaluation and Conclusion\n## Evaluation of the Model\n## Power & Resource Comparison\n## Performance Comparison\n## Conclusion\n# Appendix: Network Structure of YOLOv3-tiny\n# References","[{\"question\":\"What problem does the thesis address in solar farms?\",\"answer\":\"It targets reliability and performance issues caused by partial shading and PV panel malfunctions that reduce solar power output and complicate operation and maintenance.\"},{\"question\":\"How is the proposed shade detection method built?\",\"answer\":\"A machine learning classifier is trained using infrared images of PV panels collected across different conditions to detect whether shaded cells are present.\"},{\"question\":\"What performance results and deployment platform are reported?\",\"answer\":\"The model reaches 65.46% mAP and the classifier is implemented on an FPGA with a reported throughput of 9.5s for partial shading detection.\"}]","Machine Learning Driven Shade Detection Using Infrared Image - Thesis | PDF",1785729842,88,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-driven-shade-detection-using-infrared-image-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-driven-shade-detection-using-infrared-image-thesis/120401/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address in solar farms?","Question",{"text":75,"@type":76},"It targets reliability and performance issues caused by partial shading and PV panel malfunctions that reduce solar power output and complicate operation and maintenance.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the proposed shade detection method built?",{"text":80,"@type":76},"A machine learning classifier is trained using infrared images of PV panels collected across different conditions to detect whether shaded cells are present.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance results and deployment platform are reported?",{"text":84,"@type":76},"The model reaches 65.46% mAP and the classifier is implemented on an FPGA with a reported throughput of 9.5s for partial shading detection.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]