Back propagation modeling of shear stress and viscosity of aqueous Ionic-MXene nanofluids
28 Mar 2021-Journal of Thermal Analysis and Calorimetry (Springer International Publishing)-Vol. 145, Iss: 4, pp 2129-2149
TL;DR: In this paper, back-propagation modeling of viscosity and shear stress of Ionic-MXene nanofluid is carried out in order to obtain better performance.
Abstract: Back-propagation modeling of viscosity and shear stress of Ionic-MXene nanofluid is carried out in this work. The data for Ionic-MXene nanofluid of 0.05, 0.1, and 0.2 mass concentration (mass%) are collected from the experimental analysis. Shear stress and viscosity as a function of shear rate and mass% of MXene nanoparticles is used as input. Additionally, viscosity as a function of temperature and % of MXene nanoparticles is collected separately. Based on the possible combinations, five back-propagation algorithms are developed. In each algorithm, five models depending upon the number of neurons in the hidden layer are used. The training and testing of all the models in each algorithm are performed. Statistical analysis of the network output is done to evaluate the accuracy of models by finding the losses in terms of mean squared error (MAE), root-mean-squared error, mean absolute error, (MAE), and error deviation. Model 1 is found to have lower accuracy than the remaining models as the number of neurons in its hidden layer is only one. The performance evaluation metrices of the back-propagation model show that the error involved is acceptable. The training and testing of the algorithms are satisfactory as the network output is found to be in comfortably good agreement with the desired experimental output.
Citations
More filters
TL;DR: In this paper, the authors recognized the inclusion of ceramics such as Gr and B4C in manufacturing AMMCs through stir casting, and tested the composites for hardness and wear behaviour.
Abstract: Lightweight composite materials have recently been recognized as appropriate materials have been adopted in many industrial applications because of their versatility. The present research recognizes the inclusion of ceramics such as Gr and B4C in manufacturing AMMCs through stir casting. Prepared composites were tested for hardness and wear behaviour. The tests’ findings revealed that the reinforced matrix was harder (60%) than the un-reinforced alloy because of the increased ceramic phase. The rising content of B4C and Gr particles led to continuous improvements in wear resistance. The microstructure and worn surface were observed through SEM (Scanning electron microscope) and revealed the formation of mechanically mixed layers of both B4C and Gr, which served as the effective insulation surface and protected the test sample surface from the steel disc. With the rise in the content of B4C and Gr, the weight loss declined, and significant wear resistance was achieved at 15 wt.% B4C and 10 wt.% Gr. A response surface analysis for the weight loss was carried out to obtain the optimal objective function. Artificial neural network methodology was adopted to identify the significance of the experimental results and the importance of the wear parameters. The error between the experimental and ANN results was found to be within 1%.
36 citations
TL;DR: In this paper , two modern ensemble machine learning algorithms, Matern 5/2 Gaussian process regression (GPR) and quadratic support vector regression (SVR), were employed to model-predict the thermal conductivity, specific heat, and viscosity of novel Ionic liquid-MXene hybrid nanofluids.
Abstract: The current work employs two modern ensemble machine learning algorithms, Matern 5/2 Gaussian process regression (GPR) and quadratic support vector regression (SVR), to model-predict the thermal conductivity, specific heat, and viscosity of novel Ionic liquid-MXene hybrid nanofluids. The data for model development was obtained in the lab at various temperatures and mass concentrations. The obtained thermal conductivity value for the pure aqueous Ionic liquid (IL) solution at 20 °C was 0.443 W/m·K which rose to 0.82 W/m·K due to the inclusion of 0.5 wt% MXene nanomaterial. The achieved result for the specific heat capacity of the pure aqueous IL solution is 1.985 J/g·K, while this value enhances up to 2.374 J/g·K due to the inclusion of the highest loading concentration (0.5 wt%) of MXene nanomaterial. The acquired data was divided into two portions, with 70% of the data utilized for model training and 30% (hold-out) data used for model testing. Several statistical indicators were used to evaluate the GPR and SVR-based prognostic models created for specific heat, viscosity, and thermal conductivity. For SVM models, the correlation coefficient (R) ranged from 0.9741 to 0.9958, while for GPR-based models, it ranged from 0.9942 to 0.9998. The inaccuracy in the prediction model was quantified using root mean squared error, which ranged from 0.0129 to 0.0398 for SVM-based models and 0.004 to 0.105 for GPR-based models. The predictive effectiveness of the models was tested using Willmott's Index of Agreement, which was 0.9833 to 0.999 for SVM-based models and 0.9834 to 0.9999 for GPR-based models, respectively. The close to unity regression coefficient, low model error, and good prediction effectiveness illustrate the robustness of both SVM and GPR prognostic models. However, the GPR outperformed the SVM on all the statistical indices. The experiment results were also used to compute the Mouromtseff number (<4) and Figure of merit (>1). The results showed that the studied nanofluids can successfully substitute water in specified applications for solar energy. • Thermophysical properties of novel Ionic liquid-MXene hybrid nanofluids are investigated. • Thermal conductivity of 0.82 W/m·K with 0.5 wt% MXene nanomaterial was obtained. • GPR and SVR-based prognostic models were created for specific heat, thermal conductivity, and viscosity. • For SVM models, the correlation coefficient (R) ranged from 0.9741 to 0.9958. • GPR-based models, the correlation coefficient (R) ranged from 0.9942 to 0.9998. • Mouromtseff number (<4) and figure of merit (>1) were achieved.
32 citations
TL;DR: In this paper, a combined cycle power plant (CCPP) was modeled using different algorithms, including Ridge, Linear Regression (LR), Support Vector Regressor (SVR), and Upport vector Regressor(SVR).
Abstract: This work aims to model the combined cycle power plant (CCPP) using different algorithms. The algorithms used are Ridge, Linear regressor (LR), and upport vector regressor (SVR). The CCPP energy output data collected as a factor of thermal input variables, mainly exhaust vacuum, ambient temperature, relative humidity, and ambient pressure. Initially, the Ridge algorithm-based modeling is performed in detail, and then SVR-based LR, named as SVR (LR), SVR-based radial basis function—SVR (RBF), and SVR-based polynomial regression—SVR (Poly.) algorithms, are applied. Mean absolute error (MAE), R-squared (R2), median absolute error (MeAE), mean absolute percentage error (MAPE), and mean Poisson deviance (MPD) are assessed after their training and testing of each algorithm. From the modeling of energy output data, it is seen that SVR (RBF) is the most suitable in providing very close predictions compared to other algorithms. SVR (RBF) training R2 obtained is 0.98 while all others were 0.9–0.92. The testing predictions made by SVR (RBF), Ridge, and RidgeCV are nearly the same, i.e., R2 is 0.92. It is concluded that these algorithms are suitable for predicting sensitive output energy data of a CCPP depending on thermal input variables.
25 citations
TL;DR: In this article, the effect of reinforcements and thermal exposure on the tensile properties of aluminum AA 5083-silicon carbide (SiC) -fly ash composites were studied.
Abstract: The effect of reinforcements and thermal exposure on the tensile properties of aluminium AA 5083–silicon carbide (SiC)–fly ash composites were studied in the present work. The specimens were fabricated with varying wt.% of fly ash and silicon carbide and subjected to T6 thermal cycle conditions to enhance the properties through “precipitation hardening”. The analyses of the microstructure and the elemental distribution were carried out using scanning electron microscopic (SEM) images and energy dispersive spectroscopy (EDS). The composite specimens thus subjected to thermal treatment exhibit uniform distribution of the reinforcements, and the energy dispersive spectrum exhibit the presence of Al, Si, Mg, O elements, along with the traces of few other elements. The effects of reinforcements and heat treatment on the tensile properties were investigated through a set of scientifically designed experimental trials. From the investigations, it is observed that the tensile and yield strength increases up to 160 °C, beyond which there is a slight reduction in the tensile and yield strength with an increase in temperature (i.e., 200 °C). Additionally, the % elongation of the composites decreases substantially with the inclusion of the reinforcements and thermal exposure, leading to an increase in stiffness and elastic modulus of the specimens. The improvement in the strength and elastic modulus of the composites is attributed to a number of factors, i.e., the diffusion mechanism, composition of the reinforcements, heat treatment temperatures, and grain refinement. Further, the optimisation studies and ANN modelling validated the experimental outcomes and provided the training models for the test data with the correlation coefficients for interpolating the results for different sets of parameters, thereby facilitating the fabrication of hybrid composite components for various automotive and aerospace applications.
23 citations
TL;DR: In this paper, the impact of different input variables on the thermal performance features of an automobile radiator was investigated, statistically analyzed, and optimized using the powerful technique-Taguchi's grey relational analysis (GRA) and Response surface methodology (RSM).
22 citations
References
More filters
TL;DR: It has been found nan ofluids have a much higher and strongly temperature-dependent thermal conductivity at very low particle concentrations than conventional fluids, which can be considered as one of the key parameters for enhanced performances for many of the applications of nanofluids.
Abstract: Nanofluids are potential heat transfer fluids with enhanced thermophysical properties and heat transfer performance can be applied in many devices for better performances (i.e. energy, heat transfer and other performances). In this paper, a comprehensive literature on the applications and challenges of nanofluids have been compiled and reviewed. Latest up to date literatures on the applications and challenges in terms of PhD and Master thesis, journal articles, conference proceedings, reports and web materials have been reviewed and reported. Recent researches have indicated that substitution of conventional coolants by nanofluids appears promising. Specific application of nanofluids in engine cooling, solar water heating, cooling of electronics, cooling of transformer oil, improving diesel generator efficiency, cooling of heat exchanging devices, improving heat transfer efficiency of chillers, domestic refrigerator-freezers, cooling in machining, in nuclear reactor and defense and space have been reviewed and presented. Authors also critically analyzed some of the applications and identified research gaps for further research. Moreover, challenges and future directions of applications of nanofluids have been reviewed and presented in this paper. Based on results available in the literatures, it has been found nanofluids have a much higher and strongly temperature-dependent thermal conductivity at very low particle concentrations than conventional fluids. This can be considered as one of the key parameters for enhanced performances for many of the applications of nanofluids. Because of its superior thermal performances, latest up to date literatures on this property have been summarized and presented in this paper as well. However, few barriers and challenges that have been identified in this review must be addressed carefully before it can be fully implemented in the industrial applications.
1,558 citations
TL;DR: The measurements showed that nanogrooving increases the surface area of carbon microtubes, as a result, die swelling of the extrudate is reduced and the mechanical strength of composite is reinforced due to stronger interactions between Nanogrooved carbon tubes and polymer matrix.
Abstract: Extrusion processing of carbon tubes can be problematic due to their poor interfacial interactions with polymeric matrices. Surface chemical modification of carbon tubes can be utilized to create bonding sites to form networks with polymer chains. However, chemical reactions resulting in intermolecular primary bonding limit processability of extrudate, since they cause unstable rheological behaviour, and thus decrease the stock holding time, which is determinative in extrusion. This study presents a method for the synthesis of carbon microtubes with physically modified surface area to improve the filler and matrix interfacial interactions. The key concept is the formation of a nanogrooved topography, through acoustic cavitation on the surface of processing fibres. The effect of nanogrooving on roughness parameters is described, along with the role of surface modified carbon tubes on rheological behaviour, homogeneity, and coherency of extrudate. The measurements showed that nanogrooving increases the surface area of carbon microtubes, as a result, die swelling of the extrudate is reduced. Furthermore, after solidification, the mechanical strength of composite is reinforced due to stronger interactions between nanogrooved carbon tubes and polymer matrix.
396 citations
TL;DR: In this paper, a comprehensive review of research and development on rheological characteristics of nanofluids for their advanced heat transfer applications is performed and reported in this paper, which identifies the research anomaly and importance on this topic besides analysing rheology of nanophluids.
Abstract: A comprehensive review of research and development on rheological characteristics of nanofluids for their advanced heat transfer applications is performed and reported in this paper. It identifies the research anomaly and importance on this topic besides analysing rheology of nanofluids. Various classical and recently developed viscosity models for nanofluids are presented and discussed. Nanofluids are classified as metallic and nonmetallic types and research findings on this key property of available nanofluids are analyzed. Effects of several important factors such as concentration of nanoparticles and temperature on viscosity of each type of nanofluids have been explicitly reviewed. Results from various research groups and predictions from viscosity models are also compared and discussed in detail. Role and importance of the viscosity in connection with other thermal properties and parameters for their thermal management applications are highlighted. Furthermore, the research challenges and needs in this important area of nanofluids are also revealed.
314 citations
TL;DR: This Article contains an error in panel C of Figure 4, where “WT” was incorrectly written as “E50K−tg” and the correct Figure 4 appears below as Figure 1.
Abstract: Scientific Reports 6: Article number: 33830; published online: 22 September 2016; updated: 19 January 2017. This Article contains an error in panel C of Figure 4, where “WT” was incorrectly written as “E50K−tg”. The correct Figure 4 appears below as Figure 1.
309 citations
TL;DR: In this article, the experimental and numerical results for the thermal conductivity, viscosity, specific heat and the heat transfer coefficient reported by several authors are presented, with and without the application of nano-fluids.
261 citations