Modeling and Prediction of CBR Values of soils Using Geotechnical Parameters and Evolved GMDH-type Neural Network

In this paper, some California Bearing Ratio (CBR) values of soil extracted from a series of tests are employed to develop polynomial models using GMDH-type (Group Method of Data Handling) neural networks. In this way, a Genetic Algorithm (GA) and Singular Value Decomposition (SVD) are deployed simultaneously for optimal design of both connectivity configuration and the values of coefficients, respectively, involved in GMDH-type neural networks which are used for modeling and prediction of CBR values of soil. The aim of such modeling is to show how these characteristic change with the variation of important parameters involved in the CBR values of soil, namely, density, gradation parameters such as D10, D60, D50, D30 and D85 and Atterberg limits. A new encoding scheme is presented to genetically design the generalized GMDH-type neural networks in which the connectivity configuration in such networks is not limited to adjacent layers. Such generalization of network's topology provides optimal networks in terms of hidden layers and/or number of neurons so that a polynomial expression for dependent variable of the process can be achieved consequently. The results of modeling obtained by evolved GMDH-type neural network are then compared with some available experimental results. The comparison has shown a very promising agreement with those obtained from the models.

کلیدواژه ها:

CBR ، GMDH ، GA ، Geotechnical Parameters