EXPERIMENTAL AND ARTICIAL NEURAL NETWORK BASED STUDIES ON THERMAL CONDUCTIVITY OF LIGHTWEIGHT BUILDING MATERIALS

Abstract

The growing concern about energy consumption of heating and cooling of buildings has led to a demand for improved thermal performances of building materials. In this study, an experimental investigation is performed to predict the thermal insulation properties of wall structures of which the mechanical properties are known; by using Levenberg-Marquardt training algorithm based artificial neural network (ANNs) method for energy efficient buildings. The produced samples are cement based and have relatively high insulation properties for energy efficient buildings. In this regard, 102 new concrete samples and their compositions are produced and their mechanical and thermal properties are tested in accordance with ASTM and EN standards. Then, comparisons have been made between the experimental results and the ANN predicted results. It can be concluded that thermal performance of lightweight materials could be predicted with high accuracy using artificial neural network approach

Keywords

• Concrete, thermal properties, mechanical properties, ANN, energy efficient building