The current study presents an artificial neural network model used to predict the boiling heat transfer coefficient of different coating thicknesses of a graphene-coated copper surface in the pool boiling experimental setup for deionized water. The surface characterization has been carried out to study the structure, morphology and surface behavior. The investigations are carried out to evaluate the boiling heat transfer coefficient, heat flux and wall superheat for various thicknesses of nano-coated surfaces experimentally, and the obtained results are compared with those of the reported studies and existing empirical correlations. After that, these results are compared with the outputs such as current, heat flux, wall superheat and boiling heat transfer coefficient obtained using a MATLAB-based artificial neural network model with coating thickness, surface roughness and voltage as input variables. The admirable accuracies are obtained with the predicted optimal model outputs with experimental observation in each test case.

中文翻译：

---

石墨烯涂层铜表面池沸腾传热增强的实验研究与优化

当前的研究提出了一个人工神经网络模型，该模型用于预测在去离子池沸腾实验装置中石墨烯涂层的铜表面的不同涂层厚度的沸腾传热系数。已经进行了表面表征以研究结构，形态和表面行为。进行了研究，以实验方式评估各种厚度的纳米涂层表面的沸腾传热系数，热通量和壁过热，并将所得结果与已报道的研究结果和现有的经验相关性进行比较。然后，将这些结果与电流，热通量，使用基于MATLAB的人工神经网络模型获得的壁过热和沸腾传热系数，其中涂层厚度，表面粗糙度和电压为输入变量。通过在每个测试案例中进行实验观察，通过预测的最佳模型输出获得了令人称赞的准确性。