Grouting in rock cavern : a case study
Due to the growing population in Singapore, the constant development of its urban landscape has driven it to consider underground space development to mitigate the lack of land space. The construction of the Jurong Rock Cavern (JRC) was designed to store hydrocarbons and was the first kind of deep s...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project |
| 語言: | English |
| 出版: |
2018
|
| 主題: | |
| 在線閱讀: | http://hdl.handle.net/10356/75757 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | Due to the growing population in Singapore, the constant development of its urban landscape has driven it to consider underground space development to mitigate the lack of land space. The construction of the Jurong Rock Cavern (JRC) was designed to store hydrocarbons and was the first kind of deep storage facility constructed in Singapore. During the excavation process, water seepage is an inherent obstacle that hinders the tunnelling process and reaps detrimental effects if its risks are not properly managed. Therefore, jet grouting has been one form of measure adopted to alleviate ground water inflows into the caverns and its parameters are being studied in this report to further enhance efficiency of its usage. Due to the large extent of data variables, this project aims to derive grouting parameters as a function of hydrogeological parameters within the rock caverns. The Artificial Neural Network (ANN) has been successful in generating underlying correlations among large data sets with considerable precision and thus, has been employed for this project to derive possible relationships regarding grout volume and pressure. Some characteristic properties of the rock caverns involving RMR, Q tunnelling index and permeability are studied and included in the neural network fitting process. Rock cavern data provided by JTC Corporation will be applied into a neural network code via a software called MATLAB and the data will be trained accordingly. Regression analysis of the data will be conducted to generate a model used to predict respective tunnel conditions. In doing so, this holds the intent to aid engineers in achieving better situational awareness in the rock caverns during grouting practice for future underground excavations. |
|---|