Abstract
Predicting surface settlement in deep foundation pit engineering plays a central role in the safety of foundation pit construction. Recently, static or dynamic methods are usually applied to predict ground settlement in deep foundation pit projects. In this work, we propose a model combining wavelet noise reduction and radial basis neural network (XW-RBF) to reduce noise interference in monitoring data. The results show that the XW-RBF model predicts an average relative error of 0.77 and a root average square error of 0.13. The prediction performance is better than the original data prediction results with noise structure and has higher prediction accuracy. The noise data caused by the interference of construction and the surrounding environment in the original data can be removed via the wavelet noise reduction method, with the discreteness of the original data reducing by 30%. More importantly, our results show that the XW-RBF model can reflect the law of data change to predict the future data trend with high credibility. The findings of this study indicate that the XW-RBF model could optimize the deep foundation pit settlement prediction model for high accuracy during the prediction, which inspires the potential application in deep foundation pit engineering.