A Real-Time Hybrid Test Method for Fire in Large-Scale Substructures of Bridge Cables

By combining LSTM and GAN technologies, a real-time hybrid experimental method for fires in large-scale substructures of bridge cables was developed, achieving high-fidelity, real-time thermo-mechanical coupling analysis of fire scenarios in long-span bridges. This method solves the problems of low computational efficiency and insufficient accuracy in traditional methods and provides high-precision experimental support.

CN120706196BActive Publication Date: 2025-10-31CHINA UNIV OF MINING & TECH +6
3 Cites 0 Cited by

Patent Information

Application Number
CN202511195636.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-08-26
Publication Date
2025-10-31
Estimated Expiration
2045-08-26

AI Technical Summary

Technical Problem

Existing technologies struggle to achieve high-fidelity, real-time thermal coupling analysis in long-span bridge fire scenarios. Traditional experimental methods suffer from low computational efficiency, failing to meet long-cycle loading requirements. Furthermore, existing systems lack sufficient precision to achieve second-level thermal coupling interaction.

Method used

A real-time hybrid test method for fire in large-scale substructures of bridge cables was adopted, combining physical experiments with a fast numerical model based on LSTM. The LSTM-PID intelligent control system achieves second-level thermo-mechanical coupling interaction, and an improved generative adversarial network (GAN) is used to generate a high-precision temperature field. A multi-module T-shaped flame envelope combustion system and a variable speed angle controllable fan system are combined to simulate real fire scenarios.

Benefits of technology

It achieves second-level thermal coupling interaction, improves calculation speed and accuracy, enables real-time monitoring and control of structural response under fire, provides high-fidelity fire scene reproduction and high-precision test results, and supports fire-resistant design of long-span bridges.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

This invention discloses a real-time hybrid test method for large-scale substructure fire testing of bridge cables, belonging to the field of bridge fire resistance performance testing technology. The entire bridge is divided into a physical test substructure and an LSTM numerical substructure. The numerical substructure is constructed based on a multi-scale gated residual LSTM, achieving high-precision prediction of boundary forces or displacements of the cable system under fire conditions within seconds through parallel multi-branch networks, dynamic feature selection gates, and residual cross-layer connections. Combined with an LSTM-PID intelligent control system, the prediction commands are converted into displacement / stress and temperature fields into loading signals, synchronously integrating a time-delay compensation mechanism to drive the through-hole jacks, burners, and fans in real time, reproducing non-uniform wind-fire coupling scenarios and forming a three-dimensional visualized fire response for the entire bridge. This invention breaks through the traditional finite element calculation speed bottleneck, achieving second-level thermo-mechanical coupling interaction, providing a high-precision and high-reliability test method and platform for the fire resistance design of long-span bridges.
Need to check novelty before this filing date? Find Prior Art