Non-destructive in situ Identification of the Moisture Content in Saline Brick Walls Using Artificial Neural Networks

The article proposes a method of neuron identification of the moisture content in saline brick walls of historic buildings, carried out on the basis of non-destructive testing. The method is based on the use of artificial neural networks, which were trained, tested and experimentally verified on a set of data constructed for this purpose. The set consists of test results that were obtained using non-destructive methods on a selected representative group of historic masonry buildings. Based on numerical analyzes, an appropriate type and structure of the ANN and learning algorithm were selected. Positive results were obtained, which indicated the possibility of using the proposed method in practice. © 2019 The Authors. Published by Budapest University of Technology and Economics & Diamond Congress Ltd. Peer-review under responsibility of the scientific committee of the Creative Construction Conference 2019.