A Novel Method for Detecting Dust Accumulation in Photovoltaic Systems: Evaluating Visible Sunlight Obstruction in Different Dust Levels and AI-based Bird Droppings Detection
This paper presents an innovative method for automatically detecting dust accumulation on a PV system and notifying the user to clean it instantly. The accumulation of dust, bird, or insect droppings on the surface of photovoltaic (PV) panels creates a barrier between the solar energy and the panel's surface to receive sufficient energy to generate electricity. The study investigates the effects of dust on PV panel output and visible sunlight (VSL) block amounts to utilize the necessity of cleaning and detection. The amount of blocked visible sunlight while passing through glass due to dust determines the accumulated dust level. Visible sunlight can easily pass through the clean, transparent glass but reflects when something like dust obstructs it. Based on those concepts, a system is designed with a light sensor that is simple, effective, easy to install, hassle-free, and can spread the technology. The study also explores the effectiveness of the detection system developed by using image processing and machine learning algorithms to identify dust levels and bird or insect droppings accurately. The experimental setup in Gazipur, Bangladesh, found that excessive dust can block up to 55% of visible sunlight, wasting 55% of solar energy in the visible spectrum, and cleaning can recover 3% of power weekly. The data from the dust detection system is correlated with the 400W capacity solar panels' naturally lost efficiency data to validate the system. This research measured visible sunlight obstruction and loss due to dust. However, the addition of an infrared radiation sensor can draw the entire scenario of energy loss by doing more research.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
HOTSPOT-YOLO: A Lightweight Deep Learning Attention-Driven Model for Detecting Thermal Anomalies in Drone-Based Solar Photovoltaic Inspections
Thermal anomaly detection in solar photovoltaic (PV) systems is essential for ensuring operational efficiency and reducing maintenance costs. In this study, we developed and named HOTSPOT-YOLO, a lightweight artificial i…
Anomaly DetectionObject DetectionCellDefectNet: A Machine-designed Attention Condenser Network for Electroluminescence-based Photovoltaic Cell Defect Inspection
Photovoltaic cells are electronic devices that convert light energy to electricity, forming the backbone of solar energy harvesting systems. An essential step in the manufacturing process for photovoltaic cells is visual…
Defect DetectionA Self-Evolving Defect Detection Framework for Industrial Photovoltaic Systems
Reliable photovoltaic (PV) power generation requires timely detection of module defects that may reduce energy yield, accelerate degradation, and increase lifecycle operation and maintenance costs during field operation.…
Smart fault detection in satellite electrical power system
This paper presents an new approach for detecting in the electrical power system of satellites operating in Low Earth Orbit (LEO) without an Attitude Determination and Control Subsystem (ADCS). Components of these system…
DiagnosticFault DetectionImage Quality Enhancement and Detection of Small and Dense Objects in Industrial Recycling Processes
This paper tackles two key challenges: detecting small, dense, and overlapping objects (a major hurdle in computer vision) and improving the quality of noisy images, especially those encountered in industrial environment…
Computational Efficiency