A Data-Driven Indirect Approach for Predicting the Response of Existing Structures Induced by Adjacent Excavation

A data-driven indirect approach for predicting the response of existing structures induced by excavation is hereby proposed based on making full use monitoring data during excavation, which can predict deformation history research object excavation. In this article, a machine-learning-based model framework implementing constructed and treatment key issues in design implementation method described detail including theoretical framework, mode method, dimensionality reduction parameters, normalization model. On basis, three models are provided to settlement buildings adjacent namely SVM model, BP BP–SVM Relying an project subway Xuzhou, Jiangsu Province, China, verified, some conclusions obtained.