Predicting the thermal conductivity of Janus nanofluids based on molecular dynamics simulation and machine learning
Authors:
- Yibo FengYFYibo Feng
- Kai QiKQKai Qi
- Jun WangJWJun Wang
- Guodong XiaGXGuodong Xia
Open Access
- 1 January 2026
- journal article
- Published by Acta Physica Sinica, Chinese Physical Society and Institute of Physics, Chinese Academy of Sciences in Acta Physica Sinica
- Vol. 75 (11)
Abstract
在悬浮液中添加纳米尺寸的金属、金属氧化物或非金属颗粒,可制备具有较高导热性能的纳米流体。Janus纳米流体是将表面性质经不对称修饰的Janus纳米颗粒添加到基础流体中所形成的纳米流体。相较于普通纳米流体,Janus纳米流体具有更高的热导率。本文将平衡分子动力学模拟方法与机器学习方法相结合,计算并分析了银、铜或铁的Janus纳米流体热导率。基于分子动力学模拟计算所得Janus纳米流体热导率数据,分别采用反向传播神经网络、支持向量回归、数据分组处理方法以及随机森林四种机器学习模型,用于预测Janus纳米流体的热导率。机器学习模型的输入参数包括纳米颗粒粒径、体积分数、Janus纳米颗粒差异性参数、纳米流体密度、纳米颗粒质量以及颗粒材料的热导率。通过对比各机器学习模型的预测结果与误差,验证了机器学习预测Janus纳米流体热导率的可行性。综合分析表明,数据分组处理方法在预测Janus纳米流体的热导率中表现最优,均方根误差为0.0058 W/(m·K),决定系数为0.9844,具有较高的预测精度。分析表明,各参数对Janus纳米流体热导率的正向影响规律与已有研究结论相符合,并得到了各影响参数的重要性排序。Keywords
This publication has 46 references indexed in Scilit:
- Integrating molecular dynamics and machine learning for optimizing thermal control in Li-ion batteries with air-cooling, liquid-cooling, and phase change materialsApplied Thermal Engineering, 2025
- Evaluating Machine Learning as an Alternative to CFD for Heat Transfer ModelingMicrogravity Science and Technology, 2025
- Dynamic viscosity modeling of nanofluids with MgO nanoparticles by utilizing intelligent methodsEnergy Reports, 2023
- Stability, Thermal Conductivity and Photothermal Conversion Performance of Water-Based ZnO NanofluidsJournal of Thermal Science, 2021
- Prediction of nanofluids viscosity using random forest (RF) approachChemometrics and Intelligent Laboratory Systems, 2020
- Modeling thermal conductivity enhancement of metal and metallic oxide nanofluids using support vector regressionAdvanced Powder Technology, 2018
- Thermal conductivity and viscosity of nanofluids: A review of recent molecular dynamics studiesChemical Engineering Science, 2017
- Molecular dynamics simulation of effect of liquid layering around the nanoparticle on the enhanced thermal conductivity of nanofluidsJournal of Nanoparticle Research, 2009
- Investigation on characteristics of thermal conductivity enhancement of nanofluidsCurrent Applied Physics, 2006
- The group method of data handling in long-range forecastingTechnological Forecasting and Social Change, 1978