TY - JOUR

T1 - Enhancing thermal management systems

T2 - a machine learning and metaheuristic approach for predicting thermophysical properties of nanofluids

AU - Saha, Aritra

AU - Basu, Ankan

AU - Banerjee, Sumanta

N1 - Publisher Copyright: © 2024 The Author(s).

PY - 2024/11/5

Y1 - 2024/11/5

N2 - In thermal engineering, predicting nanofluid thermophysical properties is essential for efficient cooling systems and improved heat transfer. Traditional methods often fall short in handling complex datasets. This study leverages machine learning (ML) and metaheuristic algorithms to predict key nanofluid properties, such as specific heat capacity (SHC), thermal conductivity (TC), and viscosity. By utilizing Artificial Neural Networks (ANN), Support Vector Regression (SVR), Gradient Boosting (GB), and Linear Regression (LR), alongside metaheuristic models like Differential Evolution (DE) and Particle Swarm Optimization (PSO),we achieve superior prediction accuracy compared to traditional models. The integration of these computational techniques with empirical data demonstrates their effectiveness in capturing the complex dynamics of thermofluids. Our results validate the precision ofMLand metaheuristic models in predicting nanofluid properties and underscore their potential as robust tools for researchers and practitioners in thermal engineering. This work paves the way for future exploration ofMLalgorithms in thermal management, marking a significant advancement in optimizing nanofluid applications in industry and research.

AB - In thermal engineering, predicting nanofluid thermophysical properties is essential for efficient cooling systems and improved heat transfer. Traditional methods often fall short in handling complex datasets. This study leverages machine learning (ML) and metaheuristic algorithms to predict key nanofluid properties, such as specific heat capacity (SHC), thermal conductivity (TC), and viscosity. By utilizing Artificial Neural Networks (ANN), Support Vector Regression (SVR), Gradient Boosting (GB), and Linear Regression (LR), alongside metaheuristic models like Differential Evolution (DE) and Particle Swarm Optimization (PSO),we achieve superior prediction accuracy compared to traditional models. The integration of these computational techniques with empirical data demonstrates their effectiveness in capturing the complex dynamics of thermofluids. Our results validate the precision ofMLand metaheuristic models in predicting nanofluid properties and underscore their potential as robust tools for researchers and practitioners in thermal engineering. This work paves the way for future exploration ofMLalgorithms in thermal management, marking a significant advancement in optimizing nanofluid applications in industry and research.

KW - heat transfer

KW - machine learning

KW - nanofluids

UR - http://www.scopus.com/inward/record.url?scp=85209353597&partnerID=8YFLogxK

U2 - 10.1088/2631-8695/ad8536

DO - 10.1088/2631-8695/ad8536

M3 - Article

AN - SCOPUS:85209353597

VL - 6

JO - Engineering Research Express (ERX)

JF - Engineering Research Express (ERX)

IS - 4

M1 - 045537

ER -