A method for predicting deformation of subway structures based on bp‑time series fusion

Abstract

The invention discloses a subway structure deformation prediction method based on BP-time series fusion, which includes the following steps: S1: analyzing the variation characteristics of subway structure deformation over time through known subway structure deformation data; S2: constructing time series prediction The model predicts the deformation data of the subway structure; S3: constructs a BP-time series fusion model, and uses the BP neural network model to predict the deformation residual of the subway structure obtained by the time series prediction model, thereby compensating the time series prediction model. The present invention combines the time series model with the BP neural network, and utilizes the advantages of the neural network in nonlinear change data fitting to compensate the error of the time series prediction model, and fully understands the variation characteristics of the deformation of the subway structure over time. Excavation, high prediction accuracy and good stability.

Description

technical field [0001] The invention relates to a subway structure deformation prediction method, in particular to a subway structure deformation prediction method based on BP-time series fusion. Background technique [0002] The structural deformation of the subway during construction and operation is inevitable. Due to the particularity of the tunnel structure, the safety of the subway cannot be guaranteed when deformation occurs. The urban subway project itself produces structural deformation and settlement due to the deformation of the foundation, internal stress and changes in external loads; in addition, in the urban subway that has been built or is being built, the non-metro construction projects above or along the subway tunnel are more and more More and more, these projects have construction procedures and influencing factors such as unloading, loading, precipitation, pumping or vibration, and will also have certain structural deformation, inclination, displacement,...

AI Technical Summary

Problems solved by technology

These subway structural deformation prediction models have their own advantages and disadvantages, but they generally have the problems of low prediction accuracy and poor model stability. According to the characteristics of subway structural deformation

Images