Modeling method of digital regression model of temperature-dependent deflection monitoring reference value of main beam of cable-stayed bridge

Abstract

The invention discloses a digital regression model modeling method for a temperature-induced deflection monitoring reference value of a main beam of a cable-stayed bridge. The digital regression model modeling method comprises the following steps: acquiring temperature characteristic time sequence data and temperature-induced deflection time sequence data; carrying out normalization processing on the data, and establishing a training set and a test set; building a digital regression model driven by the long and short term memory neural network, wherein the number of layers of the model is two; and finally, checking the effectiveness of the digital regression model. According to the method, the mechanical mechanism and the nonlinear performance of the deep learning technology are combined, the established neural network has interpretability, implementation is occultable, and the high-precision cable-stayed bridge temperature-induced deflection reference value can be obtained.

Description

technical field [0001] The invention belongs to the field of bridge structural performance monitoring, and is a digital regression model modeling method for the temperature-induced deflection monitoring reference value of the main girder of a cable-stayed bridge. An input-output regression model was established between the temperature-induced vertical deflection of the cable-stayed bridge girder. Background technique [0002] The vertical deflection of the main girder of a cable-stayed bridge is the most intuitive representation of the stiffness performance of the cable-stayed bridge. Affected by the complex temperature field acting on the cable-stayed bridge, the main girder of the cable-stayed bridge will produce significant deflection changes, both oblique Temperature-induced deflection of the bridge. If the regression model between the temperature field and the temperature-induced deflection of the main girder of the cable-stayed bridge can be established, the temperatu...

AI Technical Summary

Problems solved by technology

[0003] At present, in the field of bridge health monitoring at this stage, commonly used methods can be divided into the following two types from data-driven and model-driven: (1) Based on the measured monitoring data, the linear regression method is used to establish the relationship between the main girder temperature and the temperature-induced deflection. Regression model, obtain the regression prediction expression, use the regression expression to complete the work of inputting the temperature of the main beam and output the reference value of the temperature-induced deflection, this method is simple to operate and has strong real-time performance in the actual application process, but only the temperature of the main beam is considered , resulting in poor modeling accuracy and unable to meet the needs of high-precision application scenarios; (2) Based on the principle of geometric deformation coordination, the mechanism equations that affect the temperature-induced deflection of cable-stayed bridges are derived based on mechanical principles, and the analytical solutions obtained from the equations are used as Benchmark model of temperature-induced deflection, but this method is too theoretical, and still unable to overcome the nonlinear behavior between temperature characteristics and temperature-induced deflection, resulting in a large lack of real-time performance and accuracy

Images