Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Lateral Load — Deflection Modeling of Group Pile using Artificial Neural Networks
In this paper, Artificial Neural Networks (ANNs) are applied to the prediction of lateral load — deflection relationships of group piles. The results of neural networks are compared with the measured data from the model tests. A series of model tests were performed with group piles in the Nak-Dong River Sand. For the verification of applicability of BPNN (Back Propagation Neural Network) and SNN (Sequential Neural Network), a total of 64 model test results for group piles were used. Also, in this study, the structure of neural network with one input layer-two hidden layer-one output layer was used. The number of neuron for each hidden layer determined to be 30 from the results of model test and the learning rate determined to be 0.9 to optimize network learning. The results show that the prediction of BPNN can provide a good matching with model pile test results by training with more than 50% of the total data. The investigation confirmed that a SNN with feedback is more effective than a conventional ANN without feedback to simulate the lateral load-deflection relationship for group piles. It is concluded from this study that artificial neural networks based on pile-soil interaction models can be developed by properly predicting and learning algorithms based on a comprehensive data set, and that useful inferences can be made from such models.
Lateral Load — Deflection Modeling of Group Pile using Artificial Neural Networks
In this paper, Artificial Neural Networks (ANNs) are applied to the prediction of lateral load — deflection relationships of group piles. The results of neural networks are compared with the measured data from the model tests. A series of model tests were performed with group piles in the Nak-Dong River Sand. For the verification of applicability of BPNN (Back Propagation Neural Network) and SNN (Sequential Neural Network), a total of 64 model test results for group piles were used. Also, in this study, the structure of neural network with one input layer-two hidden layer-one output layer was used. The number of neuron for each hidden layer determined to be 30 from the results of model test and the learning rate determined to be 0.9 to optimize network learning. The results show that the prediction of BPNN can provide a good matching with model pile test results by training with more than 50% of the total data. The investigation confirmed that a SNN with feedback is more effective than a conventional ANN without feedback to simulate the lateral load-deflection relationship for group piles. It is concluded from this study that artificial neural networks based on pile-soil interaction models can be developed by properly predicting and learning algorithms based on a comprehensive data set, and that useful inferences can be made from such models.
Lateral Load — Deflection Modeling of Group Pile using Artificial Neural Networks
Kim, Byung-Tak (Autor:in) / Kim, Young-Su (Autor:in)
International Deep Foundations Congress 2002 ; 2002 ; Orlando, Florida, United States
Deep Foundations 2002 ; 305-319
01.02.2002
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Lateral Load-Deflection Modeling of Group Pile Using Artificial Neural Networks
| British Library Conference Proceedings | 2002
Pile Group Response Under Lateral Load
| British Library Conference Proceedings | 2001
Effect of Pile Cap Thickness on Load Deflection Behaviour of Pile Groups Under Lateral Loading
| British Library Conference Proceedings | 1995
Nonlinear Lateral Pile Deflection Prediction in Sands
| British Library Online Contents | 1996
Nonlinear Lateral Pile Deflection Prediction in Sands
| Online Contents | 1997