DOI: 10.5593/SGEM2014/B62/S26.031


D. Lepadatu, M. Barbuta, L. Judele, R. Mitroi, A. Ilas
Wednesday 1 October 2014 by Libadmin2014

References: 14th International Multidisciplinary Scientific GeoConference SGEM 2014, www.sgem.org, SGEM2014 Conference Proceedings, ISBN 978-619-7105-21-6 / ISSN 1314-2704, June 19-25, 2014, Book 6, Vol. 2, 235-242 pp

In the paper the Artificial Neural Network - ANN was used for prediction the
mechanical characteristics such as flexural strength and split tensile strength of polymer concrete with silica fume. Neural network modeling generated the mixes with the lowest cost and maximum strength. The association of these two materials has unpredictable effects on the properties of concrete. The experimental mixes of polymer concrete realized of epoxy resin, silica fume and aggregate were established using the mixture design of experiments that is a suitable method for checking an adequate mathematical modeling of real phenomenon which is strongly nonlinear. Flexural strength and split tensile strength where experimentally determined for all mixtures. An artificial neural network - ANN is a computational model inspired by the biological natural neuron. The complexity of real neurons is highly abstracted by mathematical equation when modeling artificial neuron. This transforms the input data in output data function the operator ability of choosing and connecting more neurons or more layers for obtaining the expected performance. Their capacity of learning and adapting to operator demands makes a useful tool in math modeling and optimization of nonlinear processes. ANN presents a high potential of adaption to mathematical modeling of processes or phenomena type black box, generally with a pronounced nonlinear character and which are difficult to describe and model with simple mathematical models. ANN has ability to solve new problems by applying information learned from past experience, as human brain.

Keywords: artificial neural network, epoxy resin, mechanical characteristics, polymer concrete, silica fume.