Title: Jet grouting: using artificial neural networks to predict soilcrete column diameter - part II
Authors: B. Nikbakhtan; D. Apel; K. Ahangari
Addresses: School of Mining and Petroleum Engineering, Department of Civil & Environmental Engineering, University of Alberta, Edmonton T6G 2R3, Canada ' School of Mining and Petroleum Engineering, Department of Civil & Environmental Engineering, University of Alberta, Edmonton T6G 2R3, Canada ' Department of Mining Engineering, Islamic Azad University, Science & Research Branch, Tehran 1477893855, Iran
Abstract: Previously authors attempted to predict soilcrete diameter using Sum of Squared-Deviations mathematical model (Part I). It has been shown that the mathematical model cannot relate all impacting parameters with the diameter where the relation between soil conductivity and grout density did not match with literature and field observations. Therefore, in this paper an approach based on artificial neural network (ANN) with a wider range of data are used to calculate the diameter. ANN is a useful predictive method because it utilises both extensive computerised database and existing knowledge of what influences the diameter. This paper attempts to evaluate potential as well as limitations of ANN for predicting the diameter and to develop optimal neural network models to reduce the need for trial jet grouting as much as possible. One of the most significant results of this study is the optimisation of the costs and time needed for mining and civil projects.
Keywords: jet grouting; ANNs; artificial neural networks; soilcrete column diameter; soil conductivity; grout density; optimisation.
International Journal of Mining and Mineral Engineering, 2015 Vol.6 No.1, pp.57 - 71
Received: 15 Nov 2013
Accepted: 25 May 2014
Published online: 09 Mar 2015 *