Prediction of Change Rate of Settlement for Piled Raft Due to Adjacent Tunneling Using Machine Learning

For tunneling in urban areas, understanding the interaction and behavior of tunnels foundation adjacent structures is very important, various studies have been conducted. Superstructures areas are designed constructed with piled rafts, which more effective than conventional foundation. However, settlement a raft induced by mostly focuses on settlement. In this study, therefore, pile settlements were obtained through 3D numerical analysis, change rate along length was calculated linear assumption. Machine learning utilized to develop prediction models for due tunneling. addition, laboratory model test used verification settlement, derived machine learning. As result, between 0.64 ?0.71. among features, horizontal offset tunnel had greatest influence, diameter number relatively little influence.