Domain adaptation for acoustic inspection of concrete structures

混凝土结构声学检测的域适应

• 批准号: 21K17829
• 负责人: ルイ笠原 純ユネス
• 金额: $ 2.91万
• 依托单位: The University of Tokyo
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Early-Career Scientists
• 财政年份: 2021
• 资助国家: 日本
• 起止时间: 2021-04-01 至 2024-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-21K17829/
• 关键词: Inspection; Domain adaptation; Clustering; Weak supervision; ドメイン適応; インフラ点検; コンクリート構造物; 非破壊検査; 機械学習

This research aims at the automation of the hammering test for the inspection of concrete structures. Supervised learning approaches have theissue that when the concrete structure differs between training and deployment of the system, the performance is degraded (domain gap).This year, efforts have been shifted towards approaches based on Deep Learning for outlier detection, namely Autoencoder-type approaches, which have been gaining attention in the field. The potential of combining such methods with the weak supervision framework are being currently investigated.

本课题旨在实现混凝土结构锤击检测的自动化。监督学习方法的问题是，当系统的具体结构在训练和部署之间不同时，性能会下降（领域差距）。今年，人们的努力转向了基于深度学习的异常值检测方法，即自动编码器类型的方法，这在该领域受到了越来越多的关注。目前正在研究将这些方法与薄弱的监管框架结合起来的可能性。

项目成果

Weakly Supervised Acoustic Defect Detection in Concrete Structures Using Clustering-Based Augmentation

• DOI: 10.1109/tmech.2021.3077496
• 发表时间: 2021-12-01
• 期刊: IEEE-ASME TRANSACTIONS ON MECHATRONICS
• 影响因子: 6.4
• 作者: Kasahara, Jun Younes Louhi;Fujii, Hiromitsu;Asama, Hajime
• 通讯作者: Asama, Hajime

Multi-modal Classification Using Domain Adaptation for Automated Defect Detection Based on the Hammering Test

使用域适应进行基于锤击测试的自动缺陷检测的多模态分类

• DOI: 10.1109/sii52469.2022.9708607
• 发表时间: 2022
• 期刊: Proceedings of the 2022 IEEE/SICE International Symposium on System Integration (SII2022)
• 作者: Ushiroda Keitaro;Louhi Kasahara Jun Younes;Yamashita Atsushi;Asama Hajime
• 通讯作者: Asama Hajime