Feed-Forward Neural Network Prediction of the Mechanical Properties of Sandcrete Materials

Panagiotis G Asteris; Panayiotis C Roussis; Maria G Douvika

doi:10.3390/s17061344

Feed-Forward Neural Network Prediction of the Mechanical Properties of Sandcrete Materials

Sensors (Basel). 2017 Jun 9;17(6):1344. doi: 10.3390/s17061344.

Authors

Panagiotis G Asteris¹, Panayiotis C Roussis², Maria G Douvika³

Affiliations

¹ Computational Mechanics Laboratory, School of Pedagogical and Technological Education, Heraklion, GR, 14121 Athens, Greece. asteris@aspete.gr.
² Department of Civil and Environmental Engineering, University of Cyprus, 1678 Nicosia, Cyprus. roussis@ucy.ac.cy.
³ Computational Mechanics Laboratory, School of Pedagogical and Technological Education, Heraklion, GR, 14121 Athens, Greece. mariadouvika7@gmail.com.

Abstract

This work presents a soft-sensor approach for estimating critical mechanical properties of sandcrete materials. Feed-forward (FF) artificial neural network (ANN) models are employed for building soft-sensors able to predict the 28-day compressive strength and the modulus of elasticity of sandcrete materials. To this end, a new normalization technique for the pre-processing of data is proposed. The comparison of the derived results with the available experimental data demonstrates the capability of FF ANNs to predict with pinpoint accuracy the mechanical properties of sandcrete materials. Furthermore, the proposed normalization technique has been proven effective and robust compared to other normalization techniques available in the literature.

Keywords: artificial intelligence techniques; artificial neural networks; compressive strength; modulus of elasticity; non-destructive testing (NDT) methods; sandcrete materials; soft sensors; soft-computing techniques; velocity of ultrasonic pulses.