Droplet oscillation method is a noncontact experimental approach, which can be used to measure the surface tension of acoustically levitated droplet. In this paper, we obtained huge amounts of experimental data of deionized water and water-based graphene oxide nanofluids within the temperature range of −8.2–11.2∘C. Based on the experimental data, we analyzed the influence of droplet’s deformation and frequency shift phenomenon on the surface tension of levitated droplet. Eight parameters that strongly correlate with surface tension were found and used as input neurons of artificial neural network model to predict the surface tension of supercooling graphene oxide nanofluids. The experimental data of nonsupercooling graphene oxide nanofluids were used as training set to optimize artificial neural network model, and that of deionized water were served as validation set, which was used to verify the predictive ability of artificial neural network model. The root mean square error of the optimized artificial neural network model to validation set is only 0.2558mN/m, and the prediction values of the surface tension of supercooling deionized water were in good agreement with the theoretical values calculated by Vargaftik equation, which indicates that artificial neural network model can deal well with the complex nonlinear relationship. Afterwards, we successfully predicted the surface tension of supercooling nanofluids by means of the optimized artificial neural network model and obviously reduced the dispersion and deviation caused by droplet deformation and other problems during oscillation process.

中文翻译：

---

人工神经网络用于预测过冷纳米流体声悬浮液滴的表面张力

液滴振荡法是一种非接触式实验方法，可用于测量声悬浮液滴的表面张力。在本文中，我们获得了大量的去离子水和水基氧化石墨烯纳米流体在温度范围内的实验数据。-8.2–11.2∘C.根据实验数据，我们分析了液滴变形和频移现象对悬浮液滴表面张力的影响。找到了与表面张力密切相关的8个参数，并将其作为人工神经网络模型的输入神经元来预测过冷氧化石墨烯纳米流体的表面张力。以非过冷氧化石墨烯纳米流体的实验数据为训练集优化人工神经网络模型，去离子水实验数据为验证集，验证人工神经网络模型的预测能力。优化后的人工神经网络模型对验证集的均方根误差仅为 0.2558mN/m，过冷去离子水的表面张力预测值与Vargaftik方程计算的理论值吻合较好，说明人工神经网络模型能够很好地处理复杂的非线性关系。之后，我们通过优化的人工神经网络模型成功预测了过冷纳米流体的表面张力，明显减少了振荡过程中液滴变形等问题引起的分散和偏差。