Method for rapid prediction of seismic damage of ballastless track-simple supported bridge system

By constructing a seismic wave and damage database, and using a convolutional neural network model to quickly assess the seismic-induced damage to the high-speed railway track-bridge system, this technology solves the problems of inaccurate assessment and high computational resource consumption in existing technologies, and achieves rapid and accurate damage prediction and train safety assessment.

CN116562644BActive Publication Date: 2026-06-12CENT SOUTH UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CENT SOUTH UNIV
Filing Date
2023-05-10
Publication Date
2026-06-12

AI Technical Summary

⚠Technical Problem

Existing technologies cannot effectively assess the overall seismic damage to high-speed railway track-bridge systems, nor can they analyze the differences between different seismic waves. This results in unreliable post-earthquake traffic safety assessments, high computational resource consumption, and difficulty in meeting the needs of rapid repair and traffic safety assessment during and after earthquakes.

⚗Method used

A seismic wave database and a damage database for CRTSII type ballastless track high-speed railway simply supported beam bridges were constructed. A convolutional neural network was used for training to establish a convolutional neural network prediction model. By inputting real-time seismic wave acceleration time history curves, the seismic-induced damage of the ballastless track-simply supported bridge system was rapidly predicted.

🎯Benefits of technology

It improves the accuracy and effectiveness of assessment and prediction, reduces computational resource consumption, shortens computation time, and enables rapid and accurate assessment of post-earthquake damage distribution, supporting post-earthquake traffic safety assessment and repair.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116562644B_ABST
    Figure CN116562644B_ABST
Patent Text Reader

Abstract

The application discloses a kind of earthquake-induced damage quick prediction method for ballastless track-simple supported bridge system, including obtaining seismic wave acceleration time history curve, constructs seismic wave database and CRTSII type ballastless track structure high-speed railway simple supported beam bridge damage database;Using the seismic wave database and CRTSII type ballastless track structure high-speed railway simple supported beam bridge damage database constructed, for convolutional neural network is trained, constructs convolutional neural network prediction model;For the convolutional neural network prediction model constructed, verification processing is carried out, and the final convolutional neural network prediction model is constructed;Using the final convolutional neural network prediction model constructed, for the real-time seismic wave acceleration time history curve when sudden earthquake, the earthquake-induced damage of ballastless track-simple supported bridge system is quickly predicted.And the calculation efficiency of the application is improved, the consumption of calculation resource is reduced, and the time consumption of calculation is shortened.
Need to check novelty before this filing date? Find Prior Art