Advertisement
Published in:
2021 | OriginalPaper | Chapter
The Application of Artificial Neural Network to Predict Cleanliness Drop in CSP Power Plants Using Meteorological Measurements
Authors : Hicham El Gallassi, Ahmed Alami Merrouni, Mimoun Chourak, Abdellatif Ghennioui
Published in: Proceedings of the 2nd International Conference on Electronic Engineering and Renewable Energy Systems
Publisher: Springer Singapore
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
The dust accumulation on solar mirrors is a complex and site-specific phenomenon. It strongly depends on the environment parameters such as wind, precipitation, ambient temperature and relative humidity. Therefore, finding the relationship between these parameters we can predict the impact of this accumulation on the mirrors optical efficiency. Currently the Artificial Neural Network (ANN) is one of the best solutions that can be used for a performant prediction of such problematic. In this paper, a new approach using ANN and different meteorological parameters is used to predict the soiling level for a solar mirror with a maximum accuracy. As first results we reached an accuracy value of 95% using only 7 months of daily measurements of the environment data in Green Energy Park (GEP) research facility.