ABSTRACT
In this study, an expert system called NESASS (Neural network Expert System for Adjacent Structure Safety analysis) was developed to predict the ground movements and damages occurring in adjacent structures due to tunnel excavation. In developing NESASS, an artificial neural network technique was incorporated to take into account both measured field data and tunnel construction information. Results of training and inference of NESASS for the known site conditions and measured ground movements confirmed a high reliability with a narrow margin of error. NESASS was found to be highly reliable in predicting the ground movements due to tunnel excavation with respect to the field data that were excluded in the training process. NESASS includes a scheme that allows the prediction of damage and the possible crack patterns. Since evaluating the damage of buildings occurring during tunnel excavation steps calls for a three-dimensional assessment, the conventional two-dimensional theories were extended into three-dimensional ones in this study. The building damages predicted from the proposed method were compared with those calculated from the three-dimensional finite element analysis as well as with the measured field data. Results of the comparison showed that the reliability of the proposed scheme was acceptable. This paper also presents the charts for the damage assessment of adjacent structures due to tunnel excavation based on the Seoul subway data.
