| Title |
A Study on the Selection Model of Retaining Wall Bearing Methods Using Neural Networks |
| Authors |
Kim Jae-Youp ; Soe Jang-Woo ; Kang Kyung-In |
| Keywords |
Sub-structure Works ; retaining wall bearing Methods ; Neural Network |
| Abstract |
As a construction project in urban area tends to be high-rise and huge, the importance of the project's underground work, in terms of the cost and the schedule, is increasing gradually. The selection of a suitable shoring method is most important in this underground work. However, in Korea, because the design and the construction parts of the shoring works are separated, many changes of design have occurred and the changes have effects on the cost and the schedule of the project. In this study, we have suggested a decision model for shoring method that can be used to determine the suitable method in planning and design phase of a project. Based on history data, a neural network model was proven to be efficient. The tests of the model for decision of suitable shoring method by using data which were not used in the learning process of neural network showed that accuracy of the selections is up to 77%. |