Induction of tunnel reinforcement selection rules by using decision tree technique

Due to the uncertainty involved in ground condition and environment, tunnel reinforcement has been applied with tunnel supports to prevent local collapse at the tunnel face. The selection of tunnel reinforcement, however, primarily relies on the empirical judgement. In this study, we use data mining technique to induce tunnel reinforcement selection rules depending upon many variables. The results show that the parameters affecting the selection of tunnel reinforcement at urban and mountainous zones differs; for tunnelling at urban area, "existence of adjacent structures" and "depth of overburden" are important and for mountainous area "excavation location in a tunnel" and "RMR" values are important variables. (A) This paper was presented at Safety in the underground space - Proceedings of the ITA-AITES 2006 World Tunnel Congress and the 32nd ITA General Assembly, Seoul, Korea, 22-27 April 2006. For the covering abstract see ITRD E129148. "Reprinted with permission from Elsevier".