Application of data mining techniques in the estimation of mechanical properties of jet grouting laboratory formulations over time

Abstract

Sometimes, the soil foundation is inadequate for constructions purpose (soft-soils). In these cases there is need to improve its mechanical and physical properties. For this purpose, there are several geotechnical techniques where Jet Grouting (JG) is highlighted. In many geotechnical structures, advance design in- corporates the ultimate limit state (ULS) and the serviceability limit state (SLS) design criteria, for which uniaxial compressive strength and deformability proper- ties of the improved soils are needed. In this paper, three Data Mining models, i.e. Artificial Neural Networks (ANN), Support Vector Machines (SVM) and Functional Networks (FN), were used to estimate the tangent elastic Young modulus at 50% of the maximum stress applied (Etg50%) of JG laboratory formulations over time. A sensitivity analysis procedure was also applied in order to understand the influence of each parameter in Etg50% estimation. It is shown that the data driven model is able to learn the complex relationship between Etg50% and its contributing factors. The obtained results, namely the relative importance of each parameter, were com- pared with the predictive models of elastic Young modulus at very small strain (E0) as well as the uniaxial compressive strength (Qu). The obtained results can help to understand the behavior of soil-cement mixtures over time and reduce the costs with laboratory formulations.