A unique physics-aided deep learning model for predicting viscosity of nanofluids

Bhaumik, Bivas; Chaturvedi, Shivam; Changdar, Satyasaran; De, Soumen

doi:10.1080/15502287.2022.2120441

Cited by 9 publications

(7 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Table 1 , the thermal/dynamic viscosity of the nanofluids is predicted based on several parameters including the size [ 36 , 40 , 41 ], volume fraction (VF) [ 40 ], and shape [ 42 ] of the nanoparticles as well as the temperature and base fluid type. In addition, some studies use the nanofluid density as input parameter to predict the viscosity as in Refs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Accurate prediction of dynamic viscosity of polyalpha-olefin boron nitride nanofluids using machine learning

AbuShanab

Al‐Ammari

Gowid

et al. 2023

Heliyon

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

“…In addition, some studies use the nanofluid density as input parameter to predict the viscosity as in Refs. [ 35 , 41 , 43 ]. In general, it can be noted that the nanofluid viscosity is predicted using at least two inputs (temperature and VF).…”

Section: Introductionmentioning

confidence: 99%

Accurate prediction of dynamic viscosity of polyalpha-olefin boron nitride nanofluids using machine learning

AbuShanab

Al‐Ammari

Gowid

et al. 2023

Heliyon

View full text Add to dashboard Cite

“…27,28 It is worth-mentioning about a very recent Physics Guided Deep Neural Network approach for predicting viscosity of a nanofluid. 29,30 A series of recent analytical and numerical studies enhance understanding in this context. In these studies, the effort has mainly been put towards modeling the behavior of relevant non-Newtonian fluids.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, a fractional‐order rheological model was tested to model the MNP transport in blood flow 27,28 . It is worth‐mentioning about a very recent Physics Guided Deep Neural Network approach for predicting viscosity of a nanofluid 29,30 . A series of recent analytical and numerical studies 31–58 enhance understanding in this context.…”

Section: Introductionmentioning

confidence: 99%

Non‐Newtonian blood flow with magnetic nanoparticles in a W‐shaped stenosed arterial segment: A numerical study

Giri¹,

Dalal

Muralidhar

2023

Heat Trans

View full text Add to dashboard Cite

Flow of blood, infused with magnetic nanoparticles, in a W‐shaped stenosed human arterial segment is studied numerically using a realistic non‐Newtonian blood rheology model. It is observed that the Newtonian model predicts less time to reach a steady state than the non‐Newtonian blood rheology model. An increased drug retention time at the target site with an increase in nanoparticle concentration is predicted. Detailed simulations further reveal that the skin friction coefficient does not increase significantly with the increase in nanoparticle concentration. Hence, it is anticipated from our study that the infusion of drug‐carrying nanoparticles in blood flow does not excessively enhance wall shear stress that may lead to arterial wall damage. An overall increase in heat transfer rates and wall shear stress at the stenosed section is seen with an increase in Reynolds number. The present study provides valuable information for designing computer‐assisted drug delivery systems.

show abstract

“…Predicting viscosity in nano uids plays a crucial role in understanding their ow behaviour and optimising their applications in various industries [1][2][3][4][5][6][7][8]. Nano uids, suspensions of nanoparticles in base uids, exhibit unique rheological properties that differ from those of conventional uids [4].…”

Section: Introductionmentioning

confidence: 99%

Modelling Nanofluid Viscosity: Comparing Models and Optimizing Feature Selection - A Novel Approach

Onyiriuka

2023

Preprint

View full text Add to dashboard Cite

Background The accurate prediction of viscosity in nanofluids is essential for comprehending their flow behaviour and enhancing their effectiveness in different industries. This research delves into modelling the viscosity of nanofluids and assessing various models through cross-validation techniques. The models are compared based on the root mean square error of the cross-validation sets, serving as the selection criteria. The main body of the abstract: Four feature selection algorithms were evaluated to identify the most influential features for viscosity prediction. The feature selection based on physical meaning was the algorithm that yielded the best results, as outlined in this study. This methodology takes into account the physical relevance of most aspects of the nanofluid's viscosity. To assess the predictive performance of the models, we conducted a cross-validation process, which provided a robust evaluation. We used the root mean squared error of the cross-validation sets to compare the models. This rigorous evaluation identified the most accurate and reliable model for predicting nanofluid viscosity. Results The results showed that the novel feature selection algorithm outclassed the established approaches in predicting the viscosity of single material nanofluid. The proposed feature selection algorithm had a root mean squared error of 0.022 and an r squared value of 0.9941 for the validation set, while for the test set, the root mean squared error was 0.0146, the mean squared error was 0.0157, the r squared value was 0.9924. Conclusions This research provides valuable insights into nanofluid viscosity and offers guidance on choosing the most suitable features for viscosity modelling. The study also highlights the importance of using physical meaning to select features and cross-validation to assess model performance. The models developed in this study can be helpful in predicting nanofluid viscosity and optimising their use in different industrial processes.

show abstract

A unique physics-aided deep learning model for predicting viscosity of nanofluids

Cited by 9 publications

References 44 publications

Accurate prediction of dynamic viscosity of polyalpha-olefin boron nitride nanofluids using machine learning

Accurate prediction of dynamic viscosity of polyalpha-olefin boron nitride nanofluids using machine learning

Non‐Newtonian blood flow with magnetic nanoparticles in a W‐shaped stenosed arterial segment: A numerical study

Modelling Nanofluid Viscosity: Comparing Models and Optimizing Feature Selection - A Novel Approach

Contact Info

Product

Resources

About