Genetic programming approach for prediction of compressive strength of concretes containing rice husk ash

Soft computing techniques have recently been widely used to model some of human activities in many areas of civil engineering applications. In this paper, two models in gene expression programming (GEP) approach for predicting compressive strength of concretes containing rice husk ash have been developed at the age of 1, 3, 7, 14, 28, 56 and 90 days. For purpose of building the models, experimental results for 188 specimens produced with 41 different mixture proportions are obtained from the literature. According to these experimental results, the models are arranged by using seven different input variables in GEP approach. In according to these input variables, the compressive strength values from mechanical properties of concretes containing rice husk ash are predicted in GEP approach models. The results of training, testing and validation sets of the models are compared with experimental results. All of the results showed that GEP is a strong technique for the prediction of compressive strength values of concretes containing rice husk ash.