當今流體密度、黏度與表面張力量測方法大多只能一次量測單一物性且對於
待測液體有嚴格的溫度範圍限制，還有複雜、精密設備使量測成本難以降低。排液容
器法為基礎以容器盛裝一靜止流體並由容器底部的孔口排出，量測出口隨時間或隨高
度頭的質量流率數據作為流動特徵，其優勢為不論在冷、熱流場都能有高度的適應
性，在實驗操作簡單能同時量測三種流體物性，且設備結構簡單和低維護成本。
本研究捨棄了過往排液容器法中的修正排放係數或是初始猜測值，避免了排放係
數涵蓋物性範圍受限於實驗或是決定初始猜測的問題，改以深度學習作為回歸的演算
法。本文使用 COMSOL Multiphysics 商用軟體建立一個接近現實排液容器法實驗模型
的計算流體力學模型，產生大量不同流體的流動特徵數據作為回歸資料的基礎，再運
用 TensorFlow 深度學習對繁多流動特徵進行整理並建立回歸模型，省去了實驗量測資
料轉換為目標物性反覆迭代的計算過程，快速地從質量流率資料經由深度學習模型直
接算出目標物性預測值。
以甘油水溶液與丙二醇水溶液對最終預測模型進行驗證，密度由實驗資料得到的
預測值平均絕對誤差為 7.21kg/m3，平均相對誤差為 0.66%，黏度由實驗資料得到的預
測值平均絕對誤差為 0.215cP，平均相對誤差為 6.03%，在表面張力係數由實驗資料得
到的預測結果，其平均絕對誤差為 24.27mN/m，平均相對誤差為 42.98%。對比使用模
擬正算的質量流率作為輸入資料得到的預測值之平均絕對誤差為 1.52mN/m，平均相對
誤差為 3.16%，由此可知此方法在量測密度與黏度的可靠度，然而在表面張力係數的
預測上僅在理論上可使用質量流率回歸，尚無法在現實的實驗中執行。未來想要改良
此量測方法，必須要盡可能縮小模擬與實驗資料的誤差才能將此量測方法推向更穩定
更精確度的表現，並實現量測表面張力係數在實務上的應用。

Most of the measuring methods for fluid density, viscosity and surface tension
coefficient nowadays can only measure one single physical property at one time and have
strict restriction of fluid temperature range. In addition, the cost of measurement is difficultly
reduced resulting in the complex and sophisticated equipment. Based on Draining Vessel
Method, a stationary fluid is contained in a vessel and discharged from the orifice of the
bottom of vessel. Make the mass flow rate over time or head measured from outlet as flowing
feature. The advantage of this method is high adaptability in cold or hot flow field.
Furthermore, it allows measuring three kinds of fluid physical property at one operation of
experiment with simple equipment and low maintaining cost.
In this study, we abandon the discharging coefficient and initial guess value in previous
research of Draining Vessel Method to avoid the problem owing to lack of physical property
range covered by experiment or the decision of initial guess value. We apply the deep learning
as the algorithm of regression. With the CFD simulation software (COMSOL Multiphysics),
we establish a model of draining vessel that is close to reality and generate a large number of
flow feature data of different fluids as the basis for the regression data. Through deep
learning, various flow features are sorted out and the regression model are established. It
saves the iterative calculation process during converting the experiment measurement data to
target physical property. The mass flow rates are rapidly figured out predicted target value
through the deep learning model directly.
We verify the final prediction model with the aqueous glycerol and aqueous propylene
glycol. The mean absolute error of prediction of density obtained from experiment data is
7.21kg/m3
, and the mean relative error is 0.66%. The mean absolute error of prediction of
viscosity obtained from experiment data is 0.215cP, and the mean relative error is 6.03%. In
the prediction result of surface tension coefficient obtained from experiment data, its mean
iii
absolute error 24.27mN/m and its mean relative error is 42.98%, while the mean absolute
error is 1.52mN/m, and the mean relative error is 3.16% with the prediction obtained from
using the simulated mass flow rate the as input data. This method is reliable in measuring
density and viscosity, but it hasn’t been able to measure surface tension coefficient in real
experiment. If we want to improve this measurement method in the future, it is necessary to
reduce error between the simulation and experiment as much as possible so as to make this
method more stable and accurate performance and realize the practical application of the
measurement of surface tension.

[ 1 ] Sutterby, J. L. (1976). Density by Archimedes' principle using a top
loading balance. Journal of Chemical Education, 53(4), p.249
[ 2 ] Crawley, A. F. and Kiff, D. R. (1971), "Density of liquid bismuth,"
Metallurgical Transactions B, vol. 2, p. 609–610.
[ 3 ] Bacchi, O. O. S., REICHARDT, K., Oliveira, J. C. M., & Nielsen, D.
R. (1998). Gamma-ray beam attenuation as an auxiliary technique
for the evaluation of the soil water retention curve. Scientia
Agricola, 55, 498-502.
[ 4 ] Akpek, A. (2016). Effect of non-uniform temperature field in viscosity
measurement. Journal of Visualization, 19(2), 291-299.
[ 5 ] Beavers, G. S., & Joseph, D. D. (1975). The rotating rod
viscometer. Journal of Fluid Mechanics, 69(3), 475-511.
[ 6 ] P. d. Noüy, 1925, "An interfacial tensiometer for universal use," The
Journal of General Physiology, vol. 7, no. 5, pp. 625-631.
[ 7 ] Wanic, M., Cabaleiro, D., Hamze, S., Fal, J., Estellé, P., & Żyła, G.
(2020). Surface tension of ethylene glycol-based nanofluids
containing various types of nitrides. Journal of Thermal Analysis
and Calorimetry, 139(2), 799-806.
[ 8 ] Wu, N., Dai, J., & Micale, F. J. (1999). Dynamic surface tension
measurement with a dynamic Wilhelmy plate technique. Journal of
colloid and interface science, 215(2), 258-269.
113
[ 9 ] Stauffer, C. E. (1965). The measurement of surface tension by the
pendant drop technique. The journal of physical chemistry, 69(6),
1933-1938.
[ 10 ] Williams, A. N., Galbreth, G. G., & Sanders, J. (2018). Accurate
determination of density, surface tension, and vessel depth using a
triple bubbler system. Journal of industrial and engineering
chemistry, 63, 149-156.
[ 11 ] Roach, S. J., & Henein, H. (2003). A dynamic approach to
determining the surface tension of a fluid. Canadian metallurgical
quarterly, 42(2), 175-186.
[ 12 ] Roach, S. J., & Henein, H. (2005). A new method to dynamically
measure the surface tension, viscosity, and density of
melts. Metallurgical and Materials Transactions B, 36(5), 667-676.
[ 13 ] Rosenblatt, F. (1958). The perceptron: a probabilistic model for
information storage and organization in the brain. Psychological
review, 65(6), p.386~407.
[ 14 ] Werbos, P. (1974). Beyond regression:" new tools for prediction and
analysis in the behavioral sciences. Ph. D. dissertation, Harvard
University.
[ 15 ] Yann,L. C., Matan, O., Boser, B., Denker, J. S., Henderson, D.,
Howard, R. E., ... & Baird, H. S. (1990, June). Handwritten zip code
recognition with multilayer networks. In [1990] Proceedings. 10th
International Conference on Pattern Recognition (Vol. 2, pp. 35-40).
IEEE.
[ 16 ] Lee, S. M., Yoon, S. M., & Cho, H. (2017, February). Human activity
114
recognition from accelerometer data using Convolutional Neural
Network. In 2017 ieee international conference on big data and
smart computing (bigcomp) (pp. 131-134). IEEE.
[ 17 ] Lim, H., Park, J., & Han, Y. (2017, November). Rare sound event
detection using 1D convolutional recurrent neural networks.
In Proceedings of the detection and classification of acoustic scenes
and events 2017 workshop (pp. 80-84).
[ 18 ] Chatzis, I., Kuntamukkula, M. S., & Morrow, N. R. (1988). Effect of capillary
number on the microstructure of residual oil in strongly water-wet sandstones. SPE
Reservoir Engineering, 3(03), 902-912..
[ 19 ] Nielsen, M. A. (2015). Neural networks and deep learning (Vol. 25).
San Francisco, CA, USA: Determination press.
[ 20 ] Hamilton, W., Ying, Z., & Leskovec, J. (2017). Inductive
representation learning on large graphs. Advances in neural
information processing systems, p.30.
[ 21] Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017, August).
Understanding of a convolutional neural network. In 2017
international conference on engineering and technology (ICET) (pp.
1-6). Ieee.
[ 22 ] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term
memory. Neural computation, 9(8), 1735-1780.
[ 23 ] Neal, B., Mittal, S., Baratin, A., Tantia, V., Scicluna, M., LacosteJulien, S., & Mitliagkas, I. (2018). A modern take on the biasvariance tradeoff in neural networks.
[ 24 ] Saltelli, A. (2002). Sensitivity analysis for importance
115
assessment. Risk analysis, 22(3), 579-590.
[ 25 ] GP Association. (1963). Physical properties of glycerine and its
solutions. Glycerine Producers’ Association.
[ 26 ] Chang, C. W., Hsiung, T. L., Lui, C. P., & Tu, C. H. (2015).
Densities, surface tensions, and isobaric vapor–liquid equilibria for
the mixtures of 2-propanol, water, and 1, 2-propanediol. Fluid Phase
Equilibria, 389, 28-40.
[ 27 ] George, J., & Sastry, N. V. (2003). Densities, dynamic viscosities,
speeds of sound, and relative permittivities for water+ alkanediols
(propane-1, 2-and-1, 3-diol and butane-1, 2-,-1, 3-,-1, 4-, and-2, 3-
diol) at different temperatures. Journal of Chemical & Engineering
Data, 48(6), 1529-1539.
[ 28 ] Francois Chollet,2018, Deep Learning with Python, Manning
Publications
[ 29 ]
Egry, I. (1993). On the relation between surface tension and viscosity
for liquid metals. Scripta metallurgica et materialia, 28(10), 1273-
1276.
[ 30 ] 翁郡鴻, 以計算流體力學結合排液容器法量測錫液之密度, 黏度
與表面張力係數. 2019. Master Thesis. National Central University.
[ 31 ] 李漢祥, 以機器學習結合排液容器法量測液體密度與黏度. 2022.
Master Thesis. National Central University