TITLE:
Deformation Control and Early Warning Analysis of Deep Riverside Foundation Pit Construction Process Based on Machine Learning
AUTHORS:
Zunquan Zhu, Dongming Chang, Fang Xu, Mingtian Ma, Kai Zhang
KEYWORDS:
Deep Foundation Pit Engineering, Stability Monitoring, Horizontal Displacement, Machine Learning, Neural Network, Deformation Prediction
JOURNAL NAME:
World Journal of Engineering and Technology,
Vol.13 No.3,
August
8,
2025
ABSTRACT: The large deep foundation pit projects usually face complex geological conditions, with high possibility of engineering disasters and difficult construction technology. Foundation pit stability monitoring and control is essential to ensure construction quality. The traditional method of foundation pit monitoring is difficult to achieve real-time disaster early warning, missing the best time for structural reinforcement and causing great potential safety hazards. Based on specific engineering cases, this study obtains and analyzes the actual response data of the foundation pit project through real-time monitoring, and uses different neural network models to predict the deformation of the soil around the foundation pit. The results show that when the LSTM model is predicted backward to 25 days, the RMSE value is 0.395, and the accuracy of the model is significantly higher than that of BP and GA-BP neural networks. The maximum relative error is less than 0.06 in the range of 2.5 - 6.0 m key monitoring depth, which meets the construction safety requirements. The model is used to predict the horizontal displacement of soil in the key monitoring interval of X1 monitoring point in the medium and long term. It is found that the maximum deformation value in this area is controlled within a very low range of 1.0 mm, which is far lower than the warning value stipulated in the relevant engineering specifications. In theory, the risk of large-scale deformation or failure of foundation pit engineering is excluded. Based on the above deformation prediction analysis, the prediction and evaluation of the effectiveness of supporting measures are realized, which can provide reference for the establishment and optimization of early warning mechanism of foundation pit deformation in similar projects. This study is of great significance for the early warning of foundation pit stability and the elimination of hidden dangers, which is helpful to further improve the quality and efficiency of engineering, reduce costs, and promote the scientific and standardized construction of foundation pit engineering.