Genetic programming approach for estimating the deformation modulus of rock mass using sensitivity analysis by neural network

We use genetic programming (GP) to determine the deformation modulus of rockmasses. A database of 150 datasets, including modulus of elasticity of intact rock (Ei), uniaxial compressive strength (UCS), rock mass quality designation (RQD), the number of joint permeter (J/m), porosity, and dry density for possible input parameters, and the modulus deformation of the rockmassdeterminedbyaplate loading test for out put, was established. The values of geological strength index (GSI) system were also determined for all sites and considered as another input parameter. Sensitivity analyses are considered to find out the important parameters for predicting of the deformation modulus of rockmass. Two approachesofsensitivityanalyses, basedon`` statisticalanalysisof RSE values'' and "sensitivity analysis aboutthemean'', areperformed. Evolution of the sensitivity analyses results establish the fact that variable of UCS, GSI, and RQD play more prominent roles for predicting modulus of the rock mass, andso those are considered as the predictors to design the GPmodel. Finally, twoequationswereachievedby GP. The statistical measures of root mean square error (RMSE) and variance account for (VAF) havebeen used to compare GP models with the well- knownexistingempiricalequationsproposedforpredicting the deformation modulus. These performance criteria proved that the GP models give higher predictions overexisting empirical models. (c) 2010 Elsevier Ltd. All rights reserved.