Application of data-driven methods to predict dynamic viscosity in nanofluids

IF 4.5 2区工程技术 Q2 ENGINEERING, CHEMICAL

Powder Technology Pub Date : 2025-04-25 DOI:10.1016/j.powtec.2025.121072

Piaoyun Gu , Xizhen Zhu , Yiqin Fan

{"title":"Application of data-driven methods to predict dynamic viscosity in nanofluids","authors":"Piaoyun Gu , Xizhen Zhu , Yiqin Fan","doi":"10.1016/j.powtec.2025.121072","DOIUrl":null,"url":null,"abstract":"<div><div>Nanofluids have a wide variety of applications in various scientific and engineering fields. Dynamic viscosity (DV) is one of the important features of nanofluids that needs an accurate estimation. Therefore, the present study employed several white-box data-driven methods for estimating the DV of MWCNTs and aluminum oxide dispersed in an 80 % water and 20 % ethylene glycol solution. The white-box data-driven models, including classification and regression tree (CART), M5 model tree (M5MT), multivariate adaptive regression splines (MARS), gene expression programming (GEP), multi-expression programming (MEP), and group method of data handling (GMDH), were used. The main characteristic of the proposed methods is derived mathematical equations for predicting DV. The effective parameters, including solid volume fraction (SVF), temperature (T), and shear rate (SR), were used as input variables to predict DV. The equations obtained from the white-box models can be simply employed to estimate DV. In addition, sensitivity and Shapley Additive Explanation (SHAP) analyses were conducted to determine the impact of each input variable on DV. The CART, M5MT, GMDH, and MARS models provided simple and straightforward formulas for estimating DV. On the other hand, the MEP and GEP methods presented slightly more complex structures for the estimation of DV. For the overall evaluation of the accuracy of suggested methods, the Ranking Mean (RM) method was used. The RM values indicated that the MEP model (RM = 1.3) has the most accurate models, followed by MARS (RM = 1.9), GEP (RM = 3.1), M5MT(NLR) (RM = 4), GMDH (RM = 5.3), M5MT(LR) (RM = 5.6), and CART (RM = 7.0) models.</div></div>","PeriodicalId":407,"journal":{"name":"Powder Technology","volume":"460 ","pages":"Article 121072"},"PeriodicalIF":4.5000,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Powder Technology","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S003259102500467X","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}

引用次数: 0

Abstract

Nanofluids have a wide variety of applications in various scientific and engineering fields. Dynamic viscosity (DV) is one of the important features of nanofluids that needs an accurate estimation. Therefore, the present study employed several white-box data-driven methods for estimating the DV of MWCNTs and aluminum oxide dispersed in an 80 % water and 20 % ethylene glycol solution. The white-box data-driven models, including classification and regression tree (CART), M5 model tree (M5MT), multivariate adaptive regression splines (MARS), gene expression programming (GEP), multi-expression programming (MEP), and group method of data handling (GMDH), were used. The main characteristic of the proposed methods is derived mathematical equations for predicting DV. The effective parameters, including solid volume fraction (SVF), temperature (T), and shear rate (SR), were used as input variables to predict DV. The equations obtained from the white-box models can be simply employed to estimate DV. In addition, sensitivity and Shapley Additive Explanation (SHAP) analyses were conducted to determine the impact of each input variable on DV. The CART, M5MT, GMDH, and MARS models provided simple and straightforward formulas for estimating DV. On the other hand, the MEP and GEP methods presented slightly more complex structures for the estimation of DV. For the overall evaluation of the accuracy of suggested methods, the Ranking Mean (RM) method was used. The RM values indicated that the MEP model (RM = 1.3) has the most accurate models, followed by MARS (RM = 1.9), GEP (RM = 3.1), M5MT(NLR) (RM = 4), GMDH (RM = 5.3), M5MT(LR) (RM = 5.6), and CART (RM = 7.0) models.

Abstract Image

查看原文本刊更多论文

数据驱动方法在纳米流体动态粘度预测中的应用

纳米流体在各种科学和工程领域有着广泛的应用。动态粘度是纳米流体的重要特性之一，需要对其进行准确的估计。因此，本研究采用了几种白盒数据驱动的方法来估计分散在80%水和20%乙二醇溶液中的MWCNTs和氧化铝的DV。采用白盒数据驱动模型，包括分类与回归树（CART）、M5模型树（M5MT）、多变量自适应回归样条（MARS）、基因表达编程（GEP）、多表达式编程（MEP）和数据处理分组方法（GMDH）。该方法的主要特点是推导出预测DV的数学方程。将固体体积分数（SVF）、温度(T)和剪切速率（SR）作为预测DV的输入变量。由白盒模型得到的方程可以简单地用来估计DV。此外，还进行了敏感性和Shapley加性解释（SHAP）分析，以确定每个输入变量对DV的影响。CART、M5MT、GMDH和MARS模型提供了简单直接的DV估算公式。另一方面，MEP和GEP方法对DV的估计结构略复杂。为了对建议方法的准确性进行综合评价，我们采用了秩均值（RM）法。RM值表明，MEP模型（RM = 1.3）的模型精度最高，其次是MARS （RM = 1.9）、GEP （RM = 3.1）、M5MT(NLR) （RM = 4）、GMDH （RM = 5.3）、M5MT(LR) （RM = 5.6）和CART （RM = 7.0）模型。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Powder Technology 工程技术-工程：化工

CiteScore

9.90

自引率

15.40%

发文量

1047

审稿时长

46 days

期刊介绍： Powder Technology is an International Journal on the Science and Technology of Wet and Dry Particulate Systems. Powder Technology publishes papers on all aspects of the formation of particles and their characterisation and on the study of systems containing particulate solids. No limitation is imposed on the size of the particles, which may range from nanometre scale, as in pigments or aerosols, to that of mined or quarried materials. The following list of topics is not intended to be comprehensive, but rather to indicate typical subjects which fall within the scope of the journal's interests: Formation and synthesis of particles by precipitation and other methods. Modification of particles by agglomeration, coating, comminution and attrition. Characterisation of the size, shape, surface area, pore structure and strength of particles and agglomerates (including the origins and effects of inter particle forces). Packing, failure, flow and permeability of assemblies of particles. Particle-particle interactions and suspension rheology. Handling and processing operations such as slurry flow, fluidization, pneumatic conveying. Interactions between particles and their environment, including delivery of particulate products to the body. Applications of particle technology in production of pharmaceuticals, chemicals, foods, pigments, structural, and functional materials and in environmental and energy related matters. For materials-oriented contributions we are looking for articles revealing the effect of particle/powder characteristics (size, morphology and composition, in that order) on material performance or functionality and, ideally, comparison to any industrial standard.