A Study on Intelligent Monitoring and Prediction of Foundation Deformation Based on the Internet of Things and the LSTM Model

To address the problems of poor timeliness, high labor costs, and insufficient data analysis capabilities in traditional foundation deformation monitoring methods, this paper proposes an intelligent monitoring and prediction system based on the combination of the Internet of Things (IoT) and the Long Short-Term Memory (LSTM) model. The system enables real-time, continuous acquisition and remote transmission of foundation deformation data through a network of high-precision sensors deployed in the monitoring area.Furthermore, an LSTM-based deep learning model is constructed to train on the collected multi-source time-series data, modeling the non-linear coupling relationships between deformation and various influencing factors to accurately predict future deformation trends. Taking the measured data of a deep foundation pit project as an example for experimental verification, the results show that the system can stably and reliably obtain on-site data, and the established LSTM prediction model is superior to the traditional ARIMA model and Support Vector Machine (SVM) model in terms of indicators such as Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), and the prediction accuracy can meet the requirements of engineering early warning. This research provides a novel, intelligent, and automated approach to the safety monitoring and risk assessment of foundation engineering.