Dynamic behavior of impinging drops on water repellent surfaces: Machine learning-assisted approach to predict maximum spreading

Yancheshme, Amir Azimi; Enayati, Saman; kashcooli, Y.; Jafari, Reza; Ezzaidi, H.; Momen, Gelareh

doi:10.1016/j.expthermflusci.2022.110743

Cited by 6 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, data-driven machine learning (ML) has been demonstrated to be a powerful technique for investigating fluid mechanics. − ML methods have been successful to predict various fluid phenomena, such as boiling, condensation, and multiphase flow. In recent studies by Yancheshme et al, the random forest method was utilized to predict β max by training their ML model with a database of 198 data points. They found that beyond a critical contact angle, β max was independent.…”

Section: Introductionmentioning

confidence: 99%

Universal Model for Predicting Maximum Spreading of Drop Impact on a Smooth Surface Developed Using Boosting Machine Learning Models

Tang,

Yu,

Hou

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Drop impact on a solid surface is a fundamental phenomenon in nature and engineering. Prediction of the maximum spreading ratio during drop impact is critical for modeling and optimizing the relevant processes. However, accurately modeling the maximum spreading using empirical and numerical methods remains challenging. Machine learning (ML) has recently provided a promising way to understand and model complex fluid phenomena. Thus, in this study, a universal model is developed by using machine learning methods to predict the maximum spreading. TPE (Tree-Structured Parzen Estimator) algorithm, a variant of Bayesian optimization, is applied to optimize the hyperparameters to improve the predictive performance of ML models. An extensive database containing 1015 experimental data points has been constructed from 24 research sources and the present experimental results. Four boosting ML models were compared with conventional models, and the results show that the mean absolute percentage error (MAPE) of ML models is 2.62− 3.40%, which is less than a third that of the best conventional model. Among these ML models, the TPE-based CatBoost model is superior to others, with an MAPE of 1.67% and an R 2 of 0.952. Then, SHAP (SHapley Additive exPlanations) was used to address the black-box nature of the ML-based models. Parameter analysis indicates that the developed ML model robustly captures the physical variation trend of the maximum spreading for various working fluids. The results presented here demonstrate that the TPEbased CatBoost model can model the drop maximum spreading ratio with high accuracy and broad applicability.

show abstract

Section: Introductionmentioning

confidence: 99%

Universal Model for Predicting Maximum Spreading of Drop Impact on a Smooth Surface Developed Using Boosting Machine Learning Models

Tang,

Yu,

Hou

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…In recent years, with the increasing availability and accessibility of data, data-driven approaches-and machine learning in particular-have attracted increasing attention among fluid researchers as a faster and cheaper alternative or complement to experimental and numerical studies [32][33][34][35][36][37][38][39]. Regarding drop impacts, several machine-learning-based studies have been carried out [40][41][42][43]. Notably, a number of studies on predicting the maximum spreading factor of a non-splashing drop under various conditions were published in 2022.…”

Section: Introductionmentioning

confidence: 99%

“…Notably, a number of studies on predicting the maximum spreading factor of a non-splashing drop under various conditions were published in 2022. For example, Yancheshme et al used the random forest to predict the maximum spreading of a drop on hydrophobic and superhydrophobic surfaces [40]. Also, Tembely et al compared the performances of the linear regression model, decision tree, random forest, and gradient boost regression model on predicting the maximum spreading of a drop on surfaces of various wettabilities [41].…”

Section: Introductionmentioning

confidence: 99%

Prediction of the morphological evolution of a splashing drop using an encoder–decoder

Yee¹,

Igarashi²,

Miyatake³

et al. 2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

The impact of a drop on a solid surface is an important phenomenon that has various implications and applications. However, the multiphase nature of this phenomenon causes complications in the prediction of its morphological evolution, especially when the drop splashes. While most machine-learning-based drop-impact studies have centred around physical parameters, this study used a computer-vision strategy by training an encoder-decoder to predict the drop morphologies using image data. Herein, we show that this trained encoder-decoder is able to successfully generate videos that show the morphologies of splashing and non-splashing drops. Remarkably, in each frame of these generated videos, the spreading diameter of the drop was found to be in good agreement with that of the actual videos. Moreover, there was also a high accuracy in splashing/non-splashing prediction. These findings demonstrate the ability of the trained encoder-decoder to generate videos that can accurately represent the drop morphologies. This approach provides a faster and cheaper alternative to experimental and numerical studies.

show abstract

“…Over the past decades, the advancements of software development and increased accessibility of high computing power have facilitated computational fluid dynamics (CFD) investigations in the field. ,− , More recently, applications utilizing data-driven machine learning (ML) within the domain of fluid mechanics have emerged. − …”

Section: Introductionmentioning

confidence: 99%

“…Machine learning has also been integrated to understand the influence of the substrate characteristics on an impacting droplet. Researchers integrated ML to predict the droplet behavior and spreading dynamic when landing on surfaces of varying wettability or hydrophobicity ,, and on a spherical particle with a varying droplet-to-particle size ratio . Expanding the application of ML even further, models have been developed to consider the surface temperature ( T s ) below the freezing point. ,, For example, on supercooled surfaces, icing patterns have been classified through image analysis, with a convolutional neural network employed to determine the degree of supercooling …”

Section: Introductionmentioning

confidence: 99%

Predicting Impact Outcomes and Maximum Spreading of Drop Impact on Heated Nanostructures Using Machine Learning

Au-Yeung,

Tsai

2023

Langmuir

View full text Add to dashboard Cite

Dynamic behavior of impinging drops on water repellent surfaces: Machine learning-assisted approach to predict maximum spreading

Cited by 6 publications

References 50 publications

Universal Model for Predicting Maximum Spreading of Drop Impact on a Smooth Surface Developed Using Boosting Machine Learning Models

Universal Model for Predicting Maximum Spreading of Drop Impact on a Smooth Surface Developed Using Boosting Machine Learning Models

Prediction of the morphological evolution of a splashing drop using an encoder–decoder

Predicting Impact Outcomes and Maximum Spreading of Drop Impact on Heated Nanostructures Using Machine Learning

Contact Info

Product

Resources

About