Prediction of pile capacity using artificial neural network with two hidden

Tóm tắt

The bearing capacity of the pile is an important factor in the design of the pile foundation. Determining the bearing capacity of piles through in situ load testing is costly and time consuming. The purpose of this study is to show the applicability of artificial neural network (ANN) to predict the axial load capacity of piles. The data set used to build and verify the ANN simulation tool includes 100 data of test results of pile load testing in Dong Van industrial zone - Ha Nam. After conducting trial and error, the structure of the selected ANN includes 10 input parameters, two hidden layers with the number of neurons in the two layers of 12 and 10 neurons, respectively. Programmed and run in the Python platform, the authors use the ANN model to predict the axial load capacity of the pile. The results show that ANN has good potential to be used as a pile bearing capacity prediction tool to help design engineers predict pile load capacity for minimizing the time experimental and expensive