An Artificial Neural Network Model to Predict the Thermal Properties of Concrete Using Different Neurons and Activation Functions

Abstract

Growing concerns on energy consumption of buildings by heating and cooling applications have led to a demand for improved insulating performances of building materials. The establishment of thermal property for a building structure is the key performance indicator for energy efficiency, whereas high accuracy and precision tests are required for its determination which increases time and experimental costs. The main scope of this study is to develop a model based on artificial neural network (ANN) in order to predict the thermal properties of concrete through its mechanical characteristics. Initially, different concrete samples were prepared, and their both mechanical and thermal properties were tested in accordance with ASTM and EN standards. Then, the Levenberg–Marquardt algorithm was used for training the neural network in the single hidden layer using 5, 10, 15, 20, and 25 neurons, respectively. For each thermal property, various activation functions such as tangent sigmoid functions and triangular basis functions were used to examine the best solution performance. Moreover, a cross-validation technique was used to ensure good generalization and to avoid overtraining. ANN results showed that the best overall R2 performances for the prediction of thermal conductivity, specific heat, and thermal diffusivity were obtained as 0.996, 0.983, and 0.995 for tansig activation functions with 25, 25, and 20 neurons, respectively. The performance results showed that there was a great consistency between the predicted and tested results, demonstrating the feasibility and practicability of the proposed ANN models for predicting the thermal property of a concrete.

Artificial Intelligence to Analyze the Performance of the Ceramic‐Coated Diesel Engine Using Digital Filter Optimization

“…In order to train and evaluate neural networks, the target and input data patterns are required. e existing dataset was separated into two sets while creating an ANN model [19], one for training the network and the other for testing the network's generalization capabilities. e user does not need to know any technical specifics of neural networks because they operate in a "black box" fashion.…”

Combining multi-phase field simulation with neural network analysis to unravel thermomigration accelerated growth behavior of Cu6Sn5 IMC at cold side Cu–Sn interface

“…In order to avoid these problem posed by non-uniformity of data, a statistical process called normalization is employed to treat the dataset having input and output features. For any element (X )of an input or output feature of the neural network, normalization [50] is defined by the following formula:…”

An experimental investigation of the effect of thermophysical properties on time lag and decrement factor for building elements

“…The chemical composition and physical properties of the materials, as well as the preparation of concrete mixtures, are explained in detail in ref. [32]. The thermophysical tests were performed by the Transient Plane Source (TPS) technique, according to EN 12667 [33].…”