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.