A Camera System For Detecting Dust And Other Deposits On Solar Panels
Keywords:Multivariate distribution, Mahalanobis distance, Hotelling’s T-square, Misclassification
AbstractSolar panels over time, due to winds, sandstorms, bird droppings, suffer from dust, and other deposits. As a result of these deposits the sunlight is refracted, and only part of the sunlight reaches the chips inside the glass cage that are generating the electricity . In a remote area with thousands of solar panels, it is both expensive and cumbersome to send maintenance people to inspect each panel and clean it if needed. We have smart cameras with R, G, B, and infrared for night vision, that take the picture of each panel continuously. The picture becomes input to our classification algorithm that decides real time if the panel needs cleaning or not. Our classification algorithm consists of: our classification vector, the metric used, the training of the classifier, the testing of the classifier, and the classifier put into play for everyday use. At the present time we use a commercial camera transmitting JPEG frames wireless to our server where the classification and storage takes place. But in the near future our classification algorithm will reside on a flash memory which will be part of a circuit board that we are designing. The algorithm operates on the incoming data and will be executed by an ARM processor which will also be on the board. The circuit board also will include a CCD and Infrared camera. The hardware and software on this electronic board will be designed and programmed by the authors. Once our intelligent system detects that the panel needs cleaning it will automatically trigger a mechanism which will clean the panel.
C. E. Bohren and A. B. Fraser, “Colors of the Sky,” The Physics Teacher, no. 5, 1985, pp. 269-272.
H. C. V. D. Hulst, “Light Scattering by Small Particles,” John Wiley and Sons Inc., New York, 1957.
P. E. Haralabidis, and C. Pilinis, “Skylight Color Shifts due to Variations of Urban-Industrial Aerosol Properties: Observer Color Difference Sensitivity Compared to a Digital Camera,” Aerosol Science and Technology, vol. 8, no 42, pp. 658-673, 2008.
E. Zamora Ramos, “Using Image Processing Techniques To Estimate The air Quality,” Journal of Mcnair Scholars Institute, 6th Edition, pp. 189-194.
S.-C Tsay, G. L. Stephens and T. J. Greenwald,, “An Investigation of aerosol Microstructure on Visual air Quality,” atmospheric environment, vol. 25A, no 5/6, pp. 1039-1053, 1991.
R. v. Hogg and A. T. Craig, “Introduction to mathematical Statistics,”, Fourth Edition, Macmillan Publishing Co., pp. 1-438, 1978.
S. Theodoridis, K. Koutroumbas, “Pattern recognition,” fourth edition, Academic Press, pp. 1-961.