Study on settlement prediction of soft ground considering multiple feature parameters based on ISSA-RF model.

By collecting a large amount of data from various preloading engineering projects, a settlement prediction database was established including up to 15 feature parameters, such as final measured time, magnitude of surcharge loading, porosity ratio, internal friction angle, and others. Furthermore, a settlement prediction model of soft foundation based on random forest (RF) model was also developed. To enhance the accuracy of settlement prediction, the improved sparrow search algorithm (ISSA), which incorporates several enhancements such as the use of Logistic-tent chaotic mapping, adaptive nonlinear inertia-decreasing weight parameters, and Levy flight strategy, was proposed to optimize the hyperparameters of the RF model. The optimization results of various algorithms on benchmark functions revealed that the ISSA algorithm excelled in terms of accuracy and stability when compared to conventional algorithms such as particle swarm optimization and butterfly optimization. The ISSA-RF settlement prediction model was subsequently constructed and applied to practical projects. The results demonstrated that the ISSA-RF model exhibited superior prediction accuracy and applicability compared to the RF model. It can therefore provide valuable guidance for the planning and implementation of preloading engineering projects.

Prediction method of longitudinal surface settlement caused by double shield tunnelling based on deep learning.

The deep learning method faces the challenges of small sample data and high dimensional shield operational parameters in predicting the longitudinal surface settlement caused by shield excavation. In this study, various optimization algorithms were compared, and the slime mould algorithm (SMA) was optimally chosen to optimize the hyperparameters of random forest (RF), and SMA-RF was used for dimensionality reduction and feature contribution analysis. A double-input deep neural network (D-DNN) framework was proposed for the prediction of surface settlement, which considers the influence of twin tunnels and effectively increases the high-fidelity data in the database. The results show that SMA performs best among various optimization algorithms; employing features that have a cumulative contribution value exceeding 90% as input can result in high prediction accuracy; there is significant uncertainty in the feature contribution analysis for small sample data; the reduced shield running parameters show a strong nonlinear relationship with surface settlement; compared with S-DNN, D-DNN takes into account the excavation of twin tunnels and expands the database capacity by more than 1.5 times, with an average increase of 27.85% in the R2 and an average decrease of 53.2% in the MAE.