Method for evaluating earthquake damage degree of reinforced concrete column based on machine learning

Abstract

The invention provides a method for evaluating the earthquake damage degree of a reinforced concrete column based on machine learning. The method comprises the steps: firstly obtaining an apparent earthquake damage parameter and a component parameter according to a whole-process apparent damage image of a pseudo-static test of a reinforced concrete column component; then, according to the pseudo-static test hysteretic curve data of the reinforced concrete column component, establishing a comprehensive evaluation index of the earthquake damage degree of the reinforced concrete column, which has fixed upper and lower limits and can accurately reflect the nonlinear accelerated accumulation phenomenon of the component in the overall damage development process; and finally, establishing a deep neural network model of comprehensive evaluation indexes of apparent seismic damage parameters, component parameters and seismic damage degrees, and inputting the apparent damage parameters and size information of the component into a trained machine learning model to directly predict the seismic damage degree of the component. Finally, intelligent evaluation of the earthquake damage degree of the reinforced concrete column is achieved, and meanwhile the defects that a manual evaluation method based on expert experience wastes time and labor and is insufficient in accuracy and safety are overcome.

Description

technical field [0001] The invention belongs to the fields of structural engineering, earthquake engineering, artificial intelligence, computer vision, machine learning, etc., and in particular relates to a method for evaluating the earthquake damage degree of reinforced concrete columns based on machine learning. Background technique [0002] Reinforced concrete columns are the most basic vertical load-bearing components in various engineering structures such as buildings, bridges, and hydraulic engineering. Their damage and performance degradation during earthquakes affect the local and overall safety of the structure. For the seismic design and post-earthquake reinforcement of reinforced concrete column members, establishing a reasonable damage degree quantification and mechanical performance degradation index is the most important thing in the research of seismic system. At present, countries have different standards for the classification of building seismic performance...

AI Technical Summary

Problems solved by technology

[0015] Aiming at the above problems, the present invention proposes a method for evaluating the degree of earthquake damage of reinforced concrete columns based on machine learning. By establishing a deep neural network model of apparent earthquake damage parameters, member parameters and comprehensive evaluation indicators of earthquake damage, the surface of the member is Input the visual damage parameters and size information into the trained machine learning model to directly predict the degree of earthquake damage, and finally realize the intelligent evaluation of the earthquake damage degree of reinforced concrete columns, and also overcome the time-consuming, laborious and accurate manual evaluation method based on expert experience and the disadvantages of insufficient security

Images