Deep neural network for detecting earthquake damage to brace members installed in a steel frame

Takuzo Yamashita, Masayuki Kohiyama, Kenta Watanabe

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


We are developing an artificial intelligence system for structural health monitoring that can detect local damage in a building structure by using the E-Simulator numerical simulation system that is being developed by the Japanese National Research Institute for Earth Science and Disaster Resilience. In this study, we confirmed the applicability of a multiclass classifier using a deep neural network to address the problem of identifying damage patterns in braces installed in a steel frame. Experimental data obtained from shaking table tests were used for training and testing. Cross-validation tests were conducted for several cases with different numbers of sensors, sensor degrees of freedom, and nodes in the hidden layers of the network. The results demonstrated that the accuracy of the damage pattern detection from the constructed classifier exceeded 77% when the appropriate hidden layers were selected and reached 87.9% for the best case.

Original languageEnglish
Pages (from-to)56-64
Number of pages9
JournalJapan Architectural Review
Issue number1
Publication statusPublished - 2021 Jan


  • damage detection
  • deep neural network
  • steel structure
  • structural health monitoring

ASJC Scopus subject areas

  • Architecture
  • Environmental Engineering
  • Modelling and Simulation


Dive into the research topics of 'Deep neural network for detecting earthquake damage to brace members installed in a steel frame'. Together they form a unique fingerprint.

Cite this