Soil compaction parameters prediction using GMDH-type neural network and genetic algorithm

Abstract

The maximum dry density (γ_d,max) and optimum moisture content (ω_opt) determined from the results of the Proctorr test are very important for geotechnical engineering and earth structures. As the Proctor test is relatively time consuming and laborious, in present research Group Method of Data Handling (GMDH) type neural network (NN) is used to estimate the compaction parameters (γ_d,max and ω_opt) of soils indirectly from more simply determined index properties such as liquid limit (LL), plastic limit (PL) and fine-grained content (FC) as well as sand content (SC). A database containing 212 data-sets were used for the training and testing of the models. A comparison was carried out between the experimentally measured compaction parameters with the predictions in order to evaluate the performance of the GMDH method. The results demonstrate that generalised GMDH-type NN has a great ability for prediction of the γ_d,max and ω_opt. At the end, sensitivity analysis of the obtained model has been carried out to study the influence of input parameters on model outputs, and shows that the LL and PL are the most influential parameters on the compaction parameters.

Keywords:

• Compaction parameters
• maximum dry density
• optimum moisture content
• proctor test
• group method of data handling