Application of data mining techniques to estimate elastic young modulus over time of jet grouting laboratory formulations

Abstract

Jet Grouting (JG) technology is currently applied in many geotechnical works for improving mechanics properties of soil, mainly soft-soils. In many geotechnical structures advance design incorporates the serviceability design criteria. For this purpose, deformability properties of the improved soils are needed. In this paper, three data mining models, i.e. Artificial Neural Network (ANN), Support Vector Machine (SVM) and Functional Network (FN), were used to predict the Elastic Young Modulus (E0) of JG laboratory formulations of cases studies using JG technology for soils improvement. Furthermore, the results obtained were compared with the Eurocode 2 predictive formula, as well as with the CEB-FIP Model Code 1990 approach. The proposed predictive approaches of E0 can give a valuable contribution in terms of improving the construction control process of JG columns and reducing the costs of laboratory formulations.