Predicting Lateral Wall Deflection in Top-down Excavation by Neural Network

摘要

Deep excavation is widely undertaken in the construction of high-rise building foundations in urban areas. Measurement of diaphragm wall deflection is so important in deep excavation that monitoring data are always adopted to evaluate construction performance so as to avoid failures of the supporting system. This paper attempts to predict the diaphragm wall deflection in deep excavations by using a back-propagation artificial neural network (NN) learning model. Case histories of deep excavations (with 4 to 8 excavation stages) from the construction projects in Taipei Basin are collected for training and verification. From the results of this research, it is shown that the artificial NN can reasonably predict both magnitude and location of the maximum deflection of the braced wall in deep excavations.