Scholarlink

Bridge Health Monitoring (BHM) based on time series data is receiving deep attention from many scientists. Temporal data can describe continuous and long-term structural changes in bridges. It plays a vital role in accurately reflecting the behavior of the structure. Therefore, this paper proposes an effective method for damage detection on cable-stayed bridges using Bidirectional Long Short-Term Memory (Bi-LSTM) networks, which are adept at capturing long-term dependencies in time series data from Structural Health Monitoring (SHM) systems. A cable-stayed bridge model was used to verify the effectiveness of Bi-LSTM for the damage diagnosis problem. The results obtained show that the model can diagnose damage in the considered structure with high accuracy.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Damage Detection in Cable-Stayed Bridges Using Bidirectional Long Short-Term Memory (Bi-LSTM) Networks

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Nguyen Le Minh Đang,
  • Le Van Vu,
  • Nguyen Chi Thanh,
  • Bui Tien Thanh

摘要

Bridge Health Monitoring (BHM) based on time series data is receiving deep attention from many scientists. Temporal data can describe continuous and long-term structural changes in bridges. It plays a vital role in accurately reflecting the behavior of the structure. Therefore, this paper proposes an effective method for damage detection on cable-stayed bridges using Bidirectional Long Short-Term Memory (Bi-LSTM) networks, which are adept at capturing long-term dependencies in time series data from Structural Health Monitoring (SHM) systems. A cable-stayed bridge model was used to verify the effectiveness of Bi-LSTM for the damage diagnosis problem. The results obtained show that the model can diagnose damage in the considered structure with high accuracy.