Defect topology identification in concrete plates by machine learning based on self-attention using hammering response data
-
- Shimada Masaya
- Department of Mechanical Engineering, Graduate School of Nagaoka University of Technology
-
- Kurahashi Takahiko
- Department of Mechanical Engineering, Graduate School of Nagaoka University of Technology
-
- Murakami Yuki
- Department of Civil Engineering, National Institute of Technology, Nagaoka College
-
- Ikeda Fujio
- Department of Mechanical Engineering, National Institute of Technology, Nagaoka College
-
- Iyama Tetsuro
- Department of Mechanical Engineering, National Institute of Technology, Nagaoka College
Bibliographic Information
- Other Title
-
- Self-attentionに基づく機械学習によるコンクリート床版打撃時の加速度応答を用いた内部欠陥のトポロジー同定
- Effectiveness of data augmentation method for identified results
- 同定結果へのデータオーギュメンテーションの効果
Abstract
The aging of concrete structures in Japan is becoming increasingly serious. Periodic inspection is necessary to prevent accidents caused by aging. One of the methods used to inspect concrete is the hammering test. In this research, we aim to develop a system to identify the topology of defects in concrete by machine learning based on the acceleration response data obtained from the hammering test. As a machine learning model, we build a neural network based on self-attention. Furthermore, we propose a data augmentation method for this task and test its effectiveness.
Journal
-
- Research Reports of National Institute of Technology, Nagaoka College
-
Research Reports of National Institute of Technology, Nagaoka College 57 (0), 25-30, 2021
National Institute of Technology, Nagaoka College
- Tweet
Details 詳細情報について
-
- CRID
- 1390012578706770944
-
- ISSN
- 24323241
- 00277568
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
-
- Abstract License Flag
- Allowed