RESEARCH ARTICLE
Non-destructive Method of the Assessment of Stone Masonry by Artificial Neural Networks
Rachel Martini1, *, Jorge Carvalho2, António Arêde3, Humberto Varum3
Article Information
Identifiers and Pagination:
Year: 2020Volume: 14
First Page: 84
Last Page: 97
Publisher ID: TOBCTJ-14-84
DOI: 10.2174/1874836802014010084
Article History:
Received Date: 15/11/2019Revision Received Date: 05/12/2019
Acceptance Date: 29/01/2020
Electronic publication date: 23/05/2020
Collection year: 2020
open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: (https://creativecommons.org/licenses/by/4.0/legalcode). This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Abstract
Background:
In this study , a methodology based on non-destructive tests was used to characterize historical masonry and later to obtain information regarding the mechanical parameters of these elements. Due to the historical and cultural value that these buildings represent, the maintenance and rehabilitation work are important to maintain the appreciation of history. The preservation of buildings classified as historical-cultural heritage is of social interest, since they are important to the history of society. Considering the research object as a historical building, it is not recommended to use destructive investigative techniques.
Objective:
This work contributes to the technical-scientific knowledge regarding the characterization of granite masonry based on geophysical, mechanical and neural networks techniques.
Methods:
The database was built using the GPR (Ground Penetrating Radar) method, sonic and dynamic tests, for the characterization of eight stone masonry walls constructed in a controlled environment. The mechanical characterization was performed with conventional tests of resistance to uniaxial compression, and the elastic modulus was the parameter used as output data of ANNs.
Results:
For the construction and selection of network architecture, some possible combinations of input data were defined, with variations in the number of hidden layer neurons (5, 10, 15, 20, 25 and 30 nodes), with 122 trained networks.
Conclusion:
A mechanical characterization tool was developed applying the Artificial Neural Networks (ANN), which may be used in historic granite walls. From all the trained ANNs, based on the errors attributed to the estimated elastic modulus, networks with acceptable errors were selected.
