CFP last date
22 April 2024
Reseach Article

Prediction of Ultrasonic Parameters of Mortar by using Artificial Neural Networks Techniques

by Abdelilah Dariouchy, Hicham Lotfi
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 179 - Number 3
Year of Publication: 2017
Authors: Abdelilah Dariouchy, Hicham Lotfi
10.5120/ijca2017913547

Abdelilah Dariouchy, Hicham Lotfi . Prediction of Ultrasonic Parameters of Mortar by using Artificial Neural Networks Techniques. International Journal of Computer Applications. 179, 3 ( Dec 2017), 1-5. DOI=10.5120/ijca2017913547

@article{ 10.5120/ijca2017913547,
author = { Abdelilah Dariouchy, Hicham Lotfi },
title = { Prediction of Ultrasonic Parameters of Mortar by using Artificial Neural Networks Techniques },
journal = { International Journal of Computer Applications },
issue_date = { Dec 2017 },
volume = { 179 },
number = { 3 },
month = { Dec },
year = { 2017 },
issn = { 0975-8887 },
pages = { 1-5 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume179/number3/28713-2017913547/ },
doi = { 10.5120/ijca2017913547 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:59:11.633264+05:30
%A Abdelilah Dariouchy
%A Hicham Lotfi
%T Prediction of Ultrasonic Parameters of Mortar by using Artificial Neural Networks Techniques
%J International Journal of Computer Applications
%@ 0975-8887
%V 179
%N 3
%P 1-5
%D 2017
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Two artificial neural networks (ANN) models are developed to predict the evolution of group velocity and peak to peak amplitude of an ultrasonic wave propagate in mortar, also we these models use it to know the acoustic impedance during hydration of mortar specimen. The useful data bases to train and to test the performances of the models are collected from the experiences done on the mortar dough. In this study, the temperature, the mass reports of cement on sand, water on cement and the time of the manipulation, are retained like relevant entries of our models. Several network configurations are evaluated. For the two architectures of models, the optimal model selected is an ANN with only one hidden layer. These models are able to predict respectively group velocity, acoustic impedance and peak to peak amplitude evolution with the means relative errors (MRE) of 0.29% and 0.35% and 4%.

References
  1. Aggelis DG, Polyzos D, Philippidis TP. Wave dispersion and attenuation in fresh mortar: theorical predictions vs. experimental results. Journal of the Mechanics and Physics of Solids 2005; (53) 857-883.
  2. Philippidis TP, Aggelis DG. Experimental study of wave dispersion and attenuation in concrete. J. Ultrasonics (2004), Elseiver.
  3. Dreyfus G, Martinez JM, Samuelides M, Gordon MB, Badran F, Thiria S, Hérault L. Réseaux de neurones méthodologie et applications. Livre 2ème édition, 2004; (ISBN : 2-212-11464-8).
  4. H.Lotfi, B.Faiz, A.Moudden, D.Izbaim, A.Menou, G.Maze Et D.Decultot "Ultrasonic Characterization and Hardening of Mortar Using the Reflection Technique” ,journal High Temperature and Process, 2009.
  5. Geman S, Bienenstock E, Doursat R. Neural Networks and the bias/variance dilemma. Neural computation 1992; (4) pp. 1-58.
  6. Sablani SS, Baik OD, Marcotte M. Neural networks for predicting thermal conductivity of bakery products. Journal of food Engineering May 2002; (52) pp. 299-304.
  7. Singh SK, Srinivasan K, Chakraborty D. Acoustic characterization and prediction of surface roughness. Journal of Materials Processing Technology March 2004; (152) pp. 127-130.
  8. REGOURD M. L’hydratation du ciment portland, le béton hydrolique. Paris presse de l’ENPC, sous direction de Jacques BARON et Raymond SAUTEREY, 1995; Chapitre 11, PP 191-211.
  9. HEWLETT C. Chemistry of cement and concrete, fourth edition. Edition by Peter LEA, 1998; pp 241-289.
Index Terms

Computer Science
Information Sciences

Keywords

Group velocity Acoustic impedance Peak to peak amplitude Neural network Back-propagation algorithm