Grouting in rock caverns

• Main Author: Foo, Cheryl Yock Ping
• Other Authors: Zhao Zhiye
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Civil engineering
• Online Access: https://hdl.handle.net/10356/154377
• Institution: Nanyang Technological University

In light of Singapore’s rising population along with its land scarcity, underground construction has become a more feasible alternative to regular land builds due to its advantage of freeing land space. However, despite such a benefit, many still abstain from this option due to the high cost of construction related to it. Such high cost is mainly derived from the uncertainty of rock geology beneath the ground along with potential seepage leaks due to high water table. In response, grouting is a solution commonly employed to seal off seepage, but due to the variation of ground stratum, there is a tendency to over grout to ensure safety. However, this adds an additional financial burden. This report focuses on the usage of an Artificial Neural Network to create a regression model that is capable of predicting the grout volume required as a guideline for engineers to follow when grouting to prevent excessive over grouting. Different Analysis will be carried out to identify key parameters from data that is easily obtained during the process of grouting, and multiple iterations will be done to ensure the model’s reliability and precision.