In the present paper, we have employed the application of artificial neural networks (ANN) to predict effective heat storage coefficient (HSC) of building materials. First we prepared a database to train and test the models developed here. Two types of architectures from different networks are developed, one with three inputs and the other with four inputs mixed architecture combining an ANN with a theoretical model developed by us previously. These ANN models are built, trained and tested by the feed forward back propagation algorithm, to obtain the effective properties of building materials from the properties of their constituents. Feed forward back propagation neural network structure has been developed, which includes an input layer, a hidden layer and an output layer. The number of neurons in the input layer is equal to the number of input parameters and the number of neurons in the output layer is equal to the output parameters. A good agreement has been found between the predicted values using ANN and the experimental results reported in the literature.
Two-phase samples were prepared by mixing Fe, Cu, and Al particles (<50 mm) in lithium multipurpose grease with different weight fractions of Fe, Cu, and Al powders. Effective thermal conductivity of these samples has been measured by a laboratory-made thermal conductivity probe as a function of weight fraction of filled metal particles. Grease-Fe, Grease-Cu, and Grease-Al systems showed maximum thermal conductivity enhancement of 35.28%, 72.28%, and 97.40% at weight fraction of 0.3, 0.4, and 0.4 of Fe, Cu, and Al particles, respectively. An artificial neural network approach is used to model the effective thermal conductivity of these samples with three input parameters, viz. thermal conductivity of grease, thermal conductivity of metal particles, and weight fraction of metal particles, respectively. A theoretical prediction was also done using a model developed by Verma et al. Results obtained were compared based on coefficient of determination and mean absolute error between experimental and predicted values of effective thermal conductivity by artificial neural network and theoretical formulation. It is found that artificial neural network approach showed better agreement with the experimental results.
A theoretical model, to predict effective heat storage coefficient (HSC) from the values of HSCs of the constituent phases and their volume fractions for real two-phase systems is presented and is extended to three-phase moist materials, assuming an effective continuous medium (ECM) approach. Particles are assumed to be ellipsoidal in shape and arranged in three-dimensional cubic array. The arrangement has been divided into unit cells, each of which contains an ellipsoid. The HSC of the unit cell has been determined by applying resistor model. To take account of the non-linear flow of heat flux lines in real systems, incorporating an empirical correction factor in the place of physical porosity modifies an expression for HSC. An effort is made to correlate it in terms of the ratio of HSCs of the constituents and the physical porosity. To test the validity of the derived expression, the HSC of some building materials saturated with different liquids have been determined. The HSC of metal powders and metallic oxides at varying temperatures have also been determined. A good agreement has been found between the experimental and the predicted values reported in the literature.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.