Predictability evaluation of support vector regression methods for thermophysical properties, heat transfer performance, and pumping power estimation of MWCNT/ZnO–engine oil hybrid nanofluid

Asadi, Amin; Bakhtiyari, Ali Naderi; Alarifi, Ibrahim M.

doi:10.1007/s00366-020-01038-3

Cited by 28 publications

(6 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They explored that the nanomaterial viscosity decays with rise in temperature while it grows up with the addition of nanoparticles. Asadi et al 14 showed that the support vector regression (SVR) method is very effective for thermo-physical properties. According to this method, if there is rise in temperature then the thermal conductivity will be increased.…”

Section: Introductionmentioning

confidence: 99%

RETRACTED ARTICLE: Marangoni convection in dissipative flow of nanofluid through porous space

Ullah

Alam

Shah

et al. 2023

Sci Rep

View full text Add to dashboard Cite

In various machinery engines, the engine oil is utilized as a lubricant. Heat transportation rate and to saving the energy dissipated due to higher temperature are the basic goals of all thermal systems. Thus, current work is mainly focused to develop a model for the Marangoni flow of nanofluids (NFs) with viscous dissipation. The considered NFs are made of nanoparticles (NPs) i.e. $${\text{CoCr}}_{20} {\text{W}}_{15} {\text{N}}$$ CoCr 20 W 15 N and base fluid (BF) as Engine Oil (EO). Darcy Forchheimer (DF) law which leads to porous medium is implemented in the model to investigate the variations of NF velocity and temperature. The governing flow expressions are simplified through similarity variables. The obtained expressions are solved numerically via an effective technique known as the NDSolve algorithm. The consequences of pertinent variables on temperature, velocity and Nusselt number are designed through tables and graphs. The obtained results reveal that velocity rises for higher Marangoni number, Darcy Forchheimer (DF) parameter whereas it shows decaying behavior against nanoparticles volume fraction.

show abstract

Section: Introductionmentioning

confidence: 99%

RETRACTED ARTICLE: Marangoni convection in dissipative flow of nanofluid through porous space

Ullah

Alam

Shah

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…SVR has useful applications in regression control, using SVM based ideas, support vectors, finding optimal hyperplane, and minimizing total deviation and structural risk. [39,40] The SVR learning algorithm finds a relationship between input and target attributes. This relationship is defined by transferring the X vector to the phi high dimensional space and using the kernel as an f (x) function (Equation (6) in Figure 1).…”

Section: Support Vector Regression Modelingmentioning

confidence: 99%

Implementing Machine Learning in Laboratory Synthesis by Hybrid of SVR Model and Optimization Algorithms

Pourashraf

Shokri²,

Yousefi

et al. 2021

Advcd Theory and Sims

View full text Add to dashboard Cite

Numerous studies have been performed to modify ferrites to achieve the desired magnetic properties for the intended applications. Many variables with interactions between themselves are involved in modifying these properties. This study aims to provide an accurate and effective method for predicting the magnetic properties of M‐type ferrites under the influence of involved variables. For this purpose, ferrites are synthesized by doping 17 different ions and the results of the analysis of samples form the experimental data. The support vector regression (SVR) model is selected for prediction and in order to optimize hyper parameters, genetic, particle swarm optimization, and sequential minimal optimization techniques are used. Based on the comparison between the outcomes of these algorithms, the model with the best performance is used to predict coercivity and residual magnetism in M‐type magnetic ferrites. Furthermore, with the cross validation technique, the accuracy and robustness of the model designed for new samples are evaluated. The results show that the selected SVR model, with an average absolute relative error of 2% and 0.7%, is able to predict coercivity and residual magnetism, respectively. Consequently, the prediction method presented has the capability to accelerate and develop the modification of magnetic properties for different applications.

show abstract

“…Most previous work has sought to improve the performance of heat exchangers by increasing effectiveness by adding fins and micro-fins, changing the shape and/or construction materials of the HE. However, a significant recent development is to use a nanofluid, as the working fluid to improve the performance of an HE [ 62 , 63 , 64 , 65 , 66 , 67 , 68 , 69 ]. The coolant properties are important factors affecting the overall performance of a HE, such as when it is used as an intercooler [ 70 ].…”

Section: Introducing Nanofluids In Heat Exchangersmentioning

confidence: 99%

Application of Nanofluids in Gas Turbine and Intercoolers—A Comprehensive Review

et al. 2022

View full text Add to dashboard Cite

Today, the optimal use of non-renewable energy sources, reducing pollution, and increasing the efficiency of power-generating cycles are of particular importance. There are several ways to increase the efficiency of gas turbines; one that has recently attracted attention is to use an intercooler. However, the efficiency of the heat exchanger used in intercoolers depends on the type of heat exchanger, the characteristics of the operating fluid and the thermal boundary layers, and the pump speed. Improving the thermophysical properties of the working fluid is a passive method of increasing heat transfer, which has attracted the attention of those researching engineering applications. The current review addresses the latest methods of improving gas turbine efficiency using nanofluids and includes experimental and numerical studies. First, the general principles governing turbines are described, then the commonly used types of heat exchangers are introduced. Finally, studies on the use of nanofluids in heat exchangers are reviewed. The technology of producing nanoparticles that can be used in heat exchangers is also discussed. This review article can provide the reader with comprehensive information on making nanofluids and using them in heat exchangers used as intercoolers.

show abstract

Predictability evaluation of support vector regression methods for thermophysical properties, heat transfer performance, and pumping power estimation of MWCNT/ZnO–engine oil hybrid nanofluid

Cited by 28 publications

References 58 publications

RETRACTED ARTICLE: Marangoni convection in dissipative flow of nanofluid through porous space

RETRACTED ARTICLE: Marangoni convection in dissipative flow of nanofluid through porous space

Implementing Machine Learning in Laboratory Synthesis by Hybrid of SVR Model and Optimization Algorithms

Application of Nanofluids in Gas Turbine and Intercoolers—A Comprehensive Review

Contact Info

Product

Resources

About