Search

In this study, a model is proposed by applying the least squares support vector machine (LSSVM). In addition, genetic algorithm is used for selection and optimization of hyperparameters that are embedded in the LSSVM model. In addition to temperature and concentration of nanoparticles, the parameters which are used in most of the modeling procedures for thermal conductivity, the effect of particle size is considered. By considering the size of nanoparticles as one of the input variables, a more comprehensive model is obtained which is applicable for wider ranges of influential factor on the thermal conductivity of the nanofluid. The coefficient of determination (R2) for the introduced model is equal to 0.9902, and the mean squared error is 8.64 × 10−4 for the thermal conductivity ratio of Al2O3/EG. [ABSTRACT FROM AUTHOR]

Thermal conductivity and dynamic viscosity play key role in heat transfer capacity of nanofluids. In the present study, thermal conductivity and dynamic viscosity of Fe2O3/water are modeled by applying various artificial neural network algorithms. The applied algorithms are MLP, GA-RBF, LSSVM, and CHPSO ANFIS algorithms. The data for modeling procedure are extracted from several experimental studies. Obtained results by the different algorithms are compared and it was concluded that the highest R-squared values belonged to GA-RBF algorithm which were equal to 0.9962 and 0.9982 for thermal conductivity ratio and dynamic viscosity, respectively. [ABSTRACT FROM AUTHOR]

Highlights • Developing a robust deterministic tools for determination of Thermal conductivity of nanofluids. • Suggests the predictive model based on least square support vector machine (LSSVM) calculate Thermal conductivity of nanofluids. • Analysis of variance was performed on the data samples. • Genetic algorithm (GA) is employed to optimize hyperparameters (γ and σ2) of LSSVM model. Abstract Thermal conductivity of nanofluids plays key rol in heat transfer capacity of fluids. adding nanoparticles to a base fluid can lead to enhancement in thermal conductivty ratio. CuO/Ethyle Glycol (EG) is one of the most applicable nanofluids for heat transfer purposes. In the present study, thermal conductivty ratio of CuO/EG nanofluid is modeled by applying Group Method of Data Hnadling and Least Square Support Vector Machine – Gentic Algorithm approaches. Results indicated that the utilized model are very accurate in predicting thermal conductivty ratio of the nanofluid. The R-squared values for the proposed model are equal to 0.994 and 0.991 by applying Group Method of Data Handling and Least Square Support Vector Machine – Gentic Algorithm approaches, Respectivly. The relative importance of investigated parameters, temperature, size and concentration obtained 57%, 26% and 17%, respectively. Graphical abstract Image, graphical abstract [ABSTRACT FROM AUTHOR]

Various parameters affect thermal conductivity of nanofluid; however, some of them are more influential such as temperature, size and type of nano particles and volumetric concentration. In this study, artificial neural network as well as least square support vector machine (LSSVM) are applied in order to predict thermal conductivity ratio of alumina/water nanofluid as a function of particle size, temperature and volumetric concentration. LSSVM, Self-Organizing Map and Levenberg-Marquardt Back Propagation algorithms are applied to predict thermal conductivity ratio. Obtained results indicated that these algorithms are appropriate tool for thermal conductivity ratio prediction. The correlation coefficient values are very favorable and equal to 0.88125 and 0.87575 and 0.89999 by applying SOM, LM-BP algorithms and LSSVM, respectively. [ABSTRACT FROM AUTHOR]

• A comparative study on fillers commonly used in thermally conductive polymer composites. • The low-temperature in situ expandable graphite/HDPE composite reduces the GHE length by 12.76 %. • Half of maximum potential for reducing GHE length can be achieved using a tube with thermal conductivity of about 1 Wm−1 K−1. Ground-source heat pumps, as the most environmentally friendly and energy-efficient air conditioning technology, suffer from a great required length of ground heat exchanger, partly arising from the low thermal conductivity of high-density polyethylene tubes commonly used in ground heat exchangers. In an attempt to find a replacement with an acceptable thermal conductivity for high-density polyethylene tubes, in this study, first, a comprehensive comparative study on fillers commonly used in thermally conductive polymer composites and resulting high-density polyethylene composites was conducted. Then, based on the advantages and disadvantages presented, an appropriate composite was selected and applied in the modeling of a case study to demonstrate the effect of thermal conductivity of the tube on the borehole length of the ground heat exchanger. The findings indicated that low-temperature in situ expandable graphite was a suitable filler to add to high-density polyethylene polymer, resulting in a composite with acceptable thermal and rheological properties. Investigating the effect of thermal conductivity of the tube on the borehole length revealed some intriguing findings. First, using a composite with a thermal conductivity of approximately 1.4 Wm−1 K−1, for instance, the affordable high-density polyethylene composite filled with 10 wt% of low-temperature in situ expandable graphite, the length of the ground heat exchanger reduced by a notable amount of 10 %, which is more than 68 % of the maximum potential for reducing borehole length could be achieved by improving thermal properties of the tube. Furthermore, using polymer composites with thermal conductivity in the range of 2 Wm−1 K−1 could obviate the need for using metal tubes, which are used even nowadays in certain cases. However, due to the lack of results of some specific test, such as Hydrostatic Design Basis, the mechanical properties of the newly introduced composite require further investigation. [ABSTRACT FROM AUTHOR]

One of the auspicious nanomaterials which has exceptionally enticed researchers is carbon nanotubes (CNTs) as the result of their excellent thermal properties. In this investigation, an experiment was carried out on three kinds of CNTs-nanofluids with various CNTs added to de-ionized water to compared and analyze their thermal conductivity properties. The main purpose of this study was to introduce a combination of experimental and modelling approaches to forecast the amount of thermal conductivity using four different neural networks. Between MLP-ANN, ANFIS, LSSVM, and RBF-ANN Methods, it was found that the LSSVM produced better results with the lowest deviation factor and reflected the most accurate responses between the proposed models. the regression diagram of experimental and estimated values shows an R2 coefficient of 0.9806 and 0.9579 for training and testing sections of the ANFIS method in part a, and in the b, c and d parts of the diagram, coefficients of determination were 0.9893& 0.9967 and 0.9974 & 0.9992 and 0.9996& 0.9989 for training and testing part of MLP-ANN, RBF-ANN and LSSVM models. Also, the effect of different parameters was investigated using a sensitivity analysis method which demonstrates that the temperature is the most affecting parameter on the thermal conductivity with a relevancy factor of 0.66866. [ABSTRACT FROM AUTHOR]

In the present paper, several experimental and theoretical studies conducted on the thermal conductivity of nanofluids are represented and investigated. Based on the reviewed studies, various factors affect thermal conductivity of nanofluids such as temperature, the shape of nanoparticles, concentration and etc. Results indicated the increase in temperature and concentration of nanoparticles usually leads to the higher thermal conductivity of nanofluids. In addition, it is concluded that there are some novel approaches in order to obtain nanofluids with more appropriate thermal properties including using binary fluids as the base fluid or utilizing hybrid nanofluids. [ABSTRACT FROM AUTHOR]

Thermal conductivity of nanofluids depends on several parameters including temperature, concentration, and size of nanoparticles. Most of the proposed models utilized concentration and temperature as influential factors in their modeling. In this study, group method of data handling (GMDH) artificial neural networks is applied in order to model the dependency of thermal conductivity on the mentioned factors. Firstly, temperature and concentration considered as inputs and a model is represented. Afterwards, the size of nanoparticles is added to the input variables and the results are compared. Based on obtained results, GMDH is an appropriate method to predict thermal conductivity of the nanofluids. In addition, it is necessary to consider size of nanoparticles in order to have a more precise model. [ABSTRACT FROM AUTHOR]