Decision-Tree를 이용한 터널 보조공법 의사결정

초록

Auxiliary reinforcement methods such as for-poling and multi-steel pipe grouting etc. are frequently used to avoid a possible collapse of tunnel face, where the ground condition is not favourable as well as geological formation is not sufficient. However, among those methods a suitable reinforcement method is exclusively decided by tunnel engineers’ experience so far. Therefore, this study introduces a data-mining technique for the proper auxiliary reinforcement method during uncertainty of tunnelling work. The data-mining technique has widely been used in the field of social science, medical treatment, banking and agriculture etc. A decision-tree together with PDA technique based on tunnel construction data was developed to provide a reasonable reinforcement method in this study. Future study will be focused on the application of this technique in a variety of underground space developments.