Surface settlement modelling using neural network 2

With an ever-increasing population and scare land, tunnelling underground has emerged as a feasible alternative for providing public works while optimising space use. Ground displacements generated by tunnelling construction is very critical since existing infrastructure and high-rise structures in...

Full description

Bibliographic Details
Main Author: Khoo, Wei Yang
Other Authors: Zhao Zhiye
Format: Final Year Project (FYP)
Language:English
Published: Nanyang Technological University 2021
Subjects:
Online Access:https://hdl.handle.net/10356/149956
Description
Summary:With an ever-increasing population and scare land, tunnelling underground has emerged as a feasible alternative for providing public works while optimising space use. Ground displacements generated by tunnelling construction is very critical since existing infrastructure and high-rise structures in the urban environment can be very sensitive to any ground movements. The traditional approaches for predicting displacement are focused on empirical studies, which have limitations and does not often provide an accurate estimate due to the complexity and unknown influences. This report will study the use of Artificial Neural Network (ANN) to create a model, capable of predicting settlement. Different analyses will be carried out to obtain the important input parameters and iterations will be done to ensure the accuracy and reliability of the model. With a good model developed, it can be used for future studies and also be tested in situations where the prediction of settlement is required.