Data-driven time-dependent state estimation for interfacial fluid mechanics in evaporating droplets

Abstract

Droplet evaporation plays crucial roles in biodiagnostics, microfabrication, and inkjet printing. Experimentally studying the evolution of a sessile droplet consisting of two or more components needs sophisticated equipment to control the vast parameter space affecting the physical process. On the other hand, the non-axisymmetric nature of the problem, attributed to compositional perturbations, introduces challenges to numerical methods. In this work, droplet evaporation problem is studied from a new perspective. We analyze a sessile methanol droplet evolution through data-driven classification and regression techniques. The models are trained using experimental data of methanol droplet evolution under various environmental humidity levels and substrate temperatures. At higher humidity levels, the interfacial tension and subsequently contact angle increase due to higher water uptake into droplet. Therefore, different regimes of evolution are observed due to adsorption–absorption and possible condensation of water which turns the droplet from a single component into a binary system. In this work, machine learning and data-driven techniques are utilized to estimate the regime of droplet evaporation, the time evolution of droplet base diameter and contact angle, and level of surrounding humidity. Droplet regime is estimated by classification algorithms through point-by-point analysis of droplet profile. Decision tree demonstrates a better performance compared to Naïve Bayes (NB) classifier. Additionally, the level of surrounding humidity, as well as the time evolution of droplet base diameter and contact angle, are estimated by regression algorithms. The estimation results show promising performance for four cases of methanol droplet evolution under conditions unseen by the model, demonstrating the model’s capability to capture the complex physics underlying binary droplet evolution.

Time-Lapse Quantitative Analysis of Drying Patterns and Machine Learning for Classifying Abnormalities in Sessile Blood Droplets

“…The plant extracts in which different textures are classified using transfer learning (DenseNet-a densely connected pre-trained CNN) [40]. Traditional ML approaches (DT and NB) are used in methanol drying droplets to estimate drying stages using data related to droplet base diameter, contact angle, and relative humidity [54]. Importantly, all these studies (except[54]) involve (i) the acquisition of images via optical microscopy and (ii) the implementation of neural networks and PCA on these acquired images.…”

“…The plant extracts in which dierent textures are classied using transfer learning (DenseNet a densely connected pre-trained CNN) [40]. Traditional ML approaches (DT and NB) are used in methanol drying droplets to estimate drying stages using data related to droplet base diameter, contact angle, and relative humidity [54]. Importantly, all these studies (except [54]) involve (i) the acquisition of images via optical microscopy and…”

Drying of bio-colloidal sessile droplets: Advances, applications, and perspectives

“…Recently, the drying kinetics using the reduction-oxidation (redox) stimulus is also investigated to achieve robust and tunable control of the particle deposition, self-organization, and assembling mechanism of the colloidal particles inside the droplet [225]. In addition, data-driven methods, such as MLA, have been used extensively in fluid dynamics to make real-time predictions of the interfacial phenomena during the drying process [226].…”

Fundamentals of Monitoring Condensation and Frost/Ice Formation in Cold Environments Using Thin-Film Surface-Acoustic-Wave Technology

“…Cold environments, especially those under high relative humidity (RH) levels, can lead to moisture condensation and the formation of frost, snow, or ice on the structural surfaces, imposing severe safety issues for aircraft wings, , power transmission lines, − and wind turbine blades. − Mitigation strategies include measures on their prevention, elimination, and monitoring. However, sensing, monitoring, and/or removal of these hazardous formations in a cold environment are challenging due to the interplay of many environmental factors including temperature, RH, pressure, etc., which influence the phase transitions of water (among states of gas, liquid, and solid, including water vapor, fog, moisture, snow, frost, or ice). − Frost or ice formation rates are also significantly increased with an increase of the RH values in air and affected by atmospheric pressure, wind speed, cold rains, and ice formation at different temperatures. , …”