Citation

Yamada R, Iwasaki A, Endo Y, Nakano K, Tsujimoto K, Yamagishi T. Struct. Saf. Reliabil. 2023; 10: 328-329.

Copyright

(Copyright © 2023, Steering Committee on Japan Conference on Structural Safety and Reliability)

DOI

10.60316/jcossar.10.0_328

PMID

unavailable

Abstract

This study concerns a method for diagnosing bridge anomalies using machine learning. In this study, bridge abnormality diagnosis method using convolutional neural network (CNN) from acceleration responses is proposed. Spectrogram images of acceleration responses are applied to image classification by CNN. By classifying spectrograms for each bridge condition, bridge anomalies are detected and the condition is identified. In order to improve the accuracy of damage classification, a two-step classification method is used: first, a classification is performed in the major damage category, and then the sub-categories are identified within the major category. The two-step classification improved the accuracy of damage identification in the sub-category of girder damage, indicating that the two-step classification is effective in improving the identification accuracy of this method.

Proceedings of the Japan Conference on Structural Safety and Reliability (JCOSSAR)

Language: en

Keywords

Convolutional neural network; Damage identification; Machine learning; Structural health monitoring; Vibration analysis