Result: Optical efficiency and performance optimization of a two-stage secondary reflection hyperbolic solar concentrator using machine learning.

This paper focuses on the geometric analysis of parabolic trough solar collectors (PTCs) with components of different sizes. The concentration ratio of the receiver tube, intercept factor, and optical efficiency are the three main features for PTCs geometric optimization. This study proposes a python-based algorithm for calculating the optical efficiency of PTCs based on a secondary hyperbolic mirror. This algorithm is suitable for writing programs, inputting AutoCAD data into software for simulation of different incident angles and focal lengths of the secondary hyperbolic mirror concentrator, and processing simulation data. The error between the simulated and theoretical optical efficiency results is less than 3.13%. To provide an accurate optical efficiency computing method for geometric designing, energy analyses, and optimizing solar concentration collectors, this paper presents an available method of predicting optical efficiency for solar concentrating design based on machine learning is presented. The optical efficiency was fitted using machine learning approaches numerically with a coefficient of determination (R2 = 0.97874). The optical efficiency fitting formulas for PTCs are generated by analyzing the secondary reflection hyperbolic data of samples computed through a variable reduction technique, while the R2 values are obtained from linear regression. Then the final optical efficiency fitting formula is applied to adequately characterize optical efficiency under different geometrical configurations, incidence angles, and tracking models for the optical and geometrical optimization of PTCs. Data from tests involving the secondary hyperbolic mirror concentrators are used to validate the ray-tracing model and compute optical efficiency based on a secondary reflection hyperbolic mirror. • A numerical model is established to compute Optical efficiency. • Multivariate combination optimization method is used for performance optimization. • A coefficient of determination (R2) of 0.97874 for machine learning is achieved. • Linear regression model was accurately sufficient in predicting Optical efficiency. • Optical efficiency was easily achieved with the new design. [ABSTRACT FROM AUTHOR]

Copyright of Renewable Energy: An International Journal is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)