PSI - Issue 17

Maria Apostolopoulou et al. / Procedia Structural Integrity 17 (2019) 914–923 Maria Apostolopoulou et al. / Structural Integrity Procedia 00 (2019) 000 – 000

916

3

2. Research Significance

The compressive strength of hydraulic lime mortars is of high importance for their use as compatible restoration mortars, as well as for their use in new constructions. As mortars are complex systems, their compressive strength at different ages is dependent on the values of the mix parameters selected for their design. Although many researches have been conducted studying the characteristics of different hydraulic lime mortars, it is difficult for one researcher alone to examine all possible ranges of the mix mortar parameters. In addition, there is a nonlinear dependence of the compressive strength on the mix parameters involved in t he mortars’ design which the traditional approaches cannot solve effectively. In this study, thus, we have used soft computing techniques namely ANNs, which are powerful in exploring the complicated and nonlinear relationship of the data, to predict the compressive strength of hydraulic lime mortars. This study might help in overcoming costly and time-consuming experiments.

3. Materials and Methods

3.1. Artificial Neural Networks

Artificial Neural Networks (ANN) are information-processing models that are configured to learn and perform several tasks such as classification, prediction, and decision-making. A trained ANN maps a given input onto a specific output, and therefore it is considered to be similar to a response surface method. The main advantage of a trained ANN over conventional numerical analysis procedures (e.g., regression analysis) is that the results are more reliable and can be produced with much less computational effort (Asteris et al. 2016, Hornik et al. 1989, Plevris and Asteris 2014a, Plevris and Asteris 2014b, Plevris and Asteris 2015, Giovanis and Papadopoulos 2015). The concept of an ANN is based on the concept of the biological neural network of the human brain (Fig. 1). The basic building block of the ANN is the artificial neuron, which is a mathematical model trying to mimic the behavior of the biological neuron. Information is passed into the artificial neuron as input and processed with a mathematical function leading to an output that determines the behavior of the neuron (similar to fire-or-not situation for the biological neuron). Before the information enters the neuron, it is weighted in order to approximate the random nature of the biological neuron. A group of such neurons consists of an ANN in a manner similar to biological neural networks. In order to set up an ANN, one needs to define: (i) the architecture of the ANN; (ii) the training algorithm, which will be used for the ANN learning phase; and (iii) the mathematical functions describing the mathematical model. The architecture or topology of the ANN describes the way the artificial neurons are organized in the group and how information flows within the network. For example, if the neurons are organized in more than one layers, then the network is called a multilayer ANN. Regarding the training phase of the ANN, it can be considered as a function minimization problem, in which the optimum value of weights needs to be determined by minimizing an error function.

Fig. 1. Schematic representation of a biological neuron