期刊
ENERGY REPORTS
卷 8, 期 -, 页码 6530-6542出版社
ELSEVIER
DOI: 10.1016/j.egyr.2022.05.012
关键词
Solar radiation; Flat plate collectors; Alumina-water nanofluids; Thermal efficiency; Smart computing techniques
资金
- Qatar National Library, Japan
Nanofluids have been used in experimental studies to improve the performance of flat plate solar collectors (FPSC). However, the results regarding the effect of nanofluids on FPSC are often ambiguous and contradictory. This research develops a straightforward approach to predict the thermal efficiency of nanofluid-based FPSC and compares different machine learning models to determine the most accurate tool for this task, finding that LS-SVR performs the best.
Nanofluids have recently been utilized in experimental studies to enhance the performance of flat plate solar collectors (FPSC). The reported results for the nanofluids' effect on this solar collector are ambiguous and sometimes contradictory. Furthermore, there is no reliable model to analyze the impact of nanofluids' properties on the FPSC thermal performance. Therefore, this research develops a straightforward approach to predict the thermal efficiency of nanofluid-based FPSC. Pearson's analysis confirmed that the three-quarters root of the FPSC's thermal efficiency is the best transformation for simulating the considered problem. The machine learning models are then applied to relate the transformed thermal efficiency to the absorbed energy, energy loss, reduced temperature, the tilt angle of a flat plate, and nanoparticles' size. Prediction performance of artificial neural networks (ANN), least-squares support vector regression (LS-SVR), adaptive neuro-fuzzy inference system (ANFIS), and available correlations have been compared to distinguish the highest accurate tool for the considered task. The results demonstrate that the LS-SVR has higher accuracy than other correlations for numerically analyzing the thermal efficiency of the FPSC. This highest accurate paradigm predicts 545 experimental datasets with the absolute average relative deviation (AARD) of 2.77%, mean squared errors (MSE) of 0.00039, and coefficient of determination (R-2) of 0.99311. (C) 2022 The Author(s). Published by Elsevier Ltd.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据