Given that Indonesia is a seismically active country, there is a high likelihood that buildings will be severely impacted by strong earthquakes, highlighting the importance of effective earthquake disaster management. Earthquake disaster management includes early warning systems, damage estimation, and emergency response measures. This study reports on the implementation of earthquake disaster management in an educational building in Indonesia, which integrates an Earthquake Early Warning System (EEWS) and a Structural Health Monitoring (SHM) system. Since its deployment in August 2023, the system was first triggered by the Garut Earthquake on April 27, 2024. Analysis shows that the on-site EEWS accurately predicted the intensity experienced by the structure, providing a warning time of 23.7 s before the peak ground acceleration occurred. The rapid safety assessment from the SHM system indicated that the building remained safe after the earthquake, as the observed story drift remained within allowable limits. This study demonstrates that both the on-site AI-based EEWS and the SHM system performed effectively during the Garut Earthquake.

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

Performance of On-Site AI EEWS and SHM During the Garut Earthquake on April 27, 2024

  • Ika Bali,
  • Danny Gho

摘要

Given that Indonesia is a seismically active country, there is a high likelihood that buildings will be severely impacted by strong earthquakes, highlighting the importance of effective earthquake disaster management. Earthquake disaster management includes early warning systems, damage estimation, and emergency response measures. This study reports on the implementation of earthquake disaster management in an educational building in Indonesia, which integrates an Earthquake Early Warning System (EEWS) and a Structural Health Monitoring (SHM) system. Since its deployment in August 2023, the system was first triggered by the Garut Earthquake on April 27, 2024. Analysis shows that the on-site EEWS accurately predicted the intensity experienced by the structure, providing a warning time of 23.7 s before the peak ground acceleration occurred. The rapid safety assessment from the SHM system indicated that the building remained safe after the earthquake, as the observed story drift remained within allowable limits. This study demonstrates that both the on-site AI-based EEWS and the SHM system performed effectively during the Garut Earthquake.