This paper focuses on enhancing the prediction of vertical soil displacement during deep excavation using Artificial Neural Networks (ANN). Precise prediction of soil movement is essential to ensure the stability of the construction site and surrounding infrastructure. Traditional methods, such as the Finite Element Method (FEM), while accurate, are time-consuming and computationally intensive. In contrast, ANN offers fast and reliable predictions, making it a valuable tool for real-time decision-making. This study integrates FEM-based data to train the ANN model, ensuring the ANN captures complex, non-linear interactions between input variables like depth, pore water pressure, and coordinates. The model is trained and evaluated using performance metrics such as MAE, MSE, RMSE, and R2. With a high correlation coefficient R2 = 0.969238, the ANN model provides predictions with minimal error, demonstrating its effectiveness in replicating real-world measurements. The combined approach of ANN and FEM leverages the strengths of both methods, with FEM offering detailed physical insights and ANN optimizing computational efficiency. The results indicate that ANN-based models can serve as an efficient predictive tool in large-scale construction projects, improving safety by anticipating potential soil displacement issues. Future research will focus on expanding the model's applicability across different soil conditions and enhancing prediction capabilities with other machine learning algorithms.

The excavation and maintenance of buried natural gas pipelines can lead to deformation and stress redistribution of the pipelines and even cause secondary damage to the pipes with issues. To clarify the impact of excavation unloading on buried pipelines, this study established a finite element three-dimensional pipe-soil model, investigated the mechanical response of pipelines under layered excavation and evaluated various parameters impacting the response. The parameters analyzed include the diameter-thickness ratio of the pipe, excavation length and width, thickness of top covering soil, elastic modulus of soil, specific weight of soil and initial displacement of the pipeline. The study results showed that the pipeline bulges upwards during excavation unloading, the pipe top in the middle is under tension, and the bottom of the pipe is under compression. Therefore, the axial stress and vertical displacement both increase first and then decrease, and they are distributed symmetrically along the pipeline axis; excavating the initially compressed pipeline leads to high strain areas in the pipeline and even local buckling. The response to slope excavation is more pronounced than that to straight trench excavation; the additional response of the pipeline increases with the increase of diameter-thickness ratio, excavation width, thickness of pipe top covering soil and specific weight of soil, but it decreases with the increasing soil elastic modulus. The additional response is closely related to excavation length and the initial displacement. The results of this study can provide a reference for pipeline construction, maintenance, and safety assessment.