A machine learning based prediction of capillary forces between inclined cylindrical particles
AIChE Journal · 19.11.2026
DOI: 10.1002/aic.70778 ↗Kurz gefasst
Fachartikel in der Zeitschrift AIChE Journal, online erschienen am 19.11.2026. Verfasst von Xudong Liao und 5 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: National Science and Technology Major Project, National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate prediction of capillary force in liquid bridges between cylindrical particles is crucial for understanding the macroscopic mechanical behavior of partially wetted granular materials. In this study, we established a comprehensive dataset of capillary forces for inclined cylindrical particles based on an experimentally validated Surface Evolver (SE) simulation—a configuration that has received limited attention in prior work. Multiple machine learning models are trained to achieve high‐fidelity predictions of the inter‐cylinder capillary force. We integrated Shapley additive explanations (SHAP) analysis to reveal the key influencing mechanisms and employed symbolic regression to derive an explicit mathematical expression. Notably, the resulting mathematical expression not only exhibits excellent predictive stability but also accurately reproduces the capillary force, offering a simple and reliable tool for rapid engineering estimation. This work advances the field by bridging data‐driven modeling with physical insight, providing a high‐accuracy predictive framework for inter‐cylinder liquid bridge forces.
Förderung
- National Science and Technology Major Project
- National Natural Science Foundation of China
Zitieren
APA
Liao, X., Yang, L., Zhang, K., Cheng, J., Li, Y., & Yang, C. (2026). A machine learning based prediction of capillary forces between inclined cylindrical particles. AIChE Journal. https://doi.org/10.1002/aic.70778
Vancouver
Liao X, Yang L, Zhang K, Cheng J, Li Y, Yang C. A machine learning based prediction of capillary forces between inclined cylindrical particles. AIChE Journal. 2026. doi:10.1002/aic.70778
BibTeX
@article{Liao2026,
author = {Liao, Xudong and Yang, Lei and Zhang, Kunya and Cheng, Jingcai and Li, Yanxiang and Yang, Chao},
title = {A machine learning based prediction of capillary forces between inclined cylindrical particles},
journal = {AIChE Journal},
year = {2026},
doi = {10.1002/aic.70778}
}
EUVIMED