Prediction of the pile capacity in purely coherent soils using the approach of the artificial neural networks
Amel Benali, Ammar Nechnech · 2011
It is widely-known that the human brain has the adv antage of its efficiency in the parallel distribution of information (data) between neurons dispersed inside the human body. This famous network memorizes information by a process of training, to this effect the theory of artificial neural network is developed and is applied in sever al fields of sciences, the geotechnical domain is among them and in particular the resolution of p roblems of which parameters that govern them have an uncertain character, as the case of the pre diction of the pile capacity. For it we collected 80 cases of the literature, sweeping a variety of s ites through the world. The model conceived by an iterative process that is the retropropagation i s verified while applying him in the case of the non heavy soils (� =0) of which we possesses the exact solution. The r esults indicate the feasibility of the use of the artificial neural net works (ANNs) in this type of problem