Comparative Analysis of Machine Learning Models for Nanofluids Viscosity Assessment

Abstract

The process of selecting a nanofluid for a particular application requires determining the thermophysical properties of nanofluid, such as viscosity. However, the experimental measurement of nanofluid viscosity is expensive. Several closed-form formulas for calculating the viscosity have been proposed by scientists based on theoretical and empirical methods, but these methods produce inaccurate results. Recently, a machine learning model based on the combination of seven baselines, which is called the committee machine intelligent system (CMIS), was proposed to predict the viscosity of nanofluids. CMIS was applied on 3144 experimental data of relative viscosity of 42 different nanofluid systems based on five features (temperature, the viscosity of the base fluid, nanoparticle volume fraction, size, and density) and returned an average absolute relative error (AARE) of 4.036% on the test. In this work, eight models (on the same dataset as the one used in CMIS), including two multilayer perceptron (MLP), each with Nesterov accelerated adaptive moment (Nadam) optimizer; two MLP, each with three hidden layers and Adamax optimizer; a support vector regression (SVR) with radial basis function (RBF) kernel; a decision tree (DT); tree-based ensemble models, including random forest (RF) and extra tree (ET), were proposed. The performance of these models at different ranges of input variables was assessed and compared with the ones presented in the literature. Based on our result, all the eight suggested models outperformed the baselines used in the literature, and five of our presented models outperformed the CMIS, where two of them returned an AARE less than 3% on the test data. Besides, the physical validity of models was studied by examining the physically expected trends of nanofluid viscosity due to changing volume fraction.

Damage Diagnosis for Offshore Wind Turbine Foundations Based on the Fractal Dimension

“…As a final remark, the performance of the Gaussian SVM over the quadratic SVM may depend on the nature of the data or even on how this data is preprocessed and what features are extracted. In this sense, the exceeding performance of the Gaussian SVM has been reported in the literature as a machine learning model for the prediction of the viscosity of nanofluids [43] or, in the field of fault diagnosis, to get the operation status of a wind turbine [44].…”

Thermal Conductivity of Nanofluids: A Review on Prediction Models, Controversies and Challenges

“…In recent years, many machine learning and statistical models has been developed to predict the thermal conductivity and other thermal properties of materials and nanofluids with high accuracy and robustness. In fact, properties such as thermal conductivity [85], density [86], and viscosity [87,88] of nanofluids, glass transition temperature of polymers [89,90] and also the decomposition onset temperature of lubricant additives [91] have been estimated precisely with machine learning-based models. Those models are fast, stable, and low-cost tools to predict the thermal properties on a wide range of industrial applications, particularly in electronic devices, heat sinks, heat exchangers, renewable energy [92], and automotive industries.…”

An advanced computational intelligent framework to predict shear sonic velocity with application to mechanical rock classification

“…During the past two decades, artificial intelligence (AI) has drawn increasing attention in petroleum engineering and geosciences owing to its capability and robustness in modeling complicated phenomena, including reservoir fluid and rock properties 19 – 22 , hydrocarbon-bearing potential of source rocks 23 , rock failure behavior 24 – 28 , soil behavior 29 , 30 and seismic characterization 31 , 32 . Predictive models thus got a boost with these new techniques.…”