2023 Fiscal Year Annual Research Report
Domain adaptation for acoustic inspection of concrete structures
| Project/Area Number |
21K17829
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
ルイ笠原 純ユネス 東京大学, 大学院工学系研究科(工学部), 特任講師 (20885412)
|
|---|
| Project Period (FY) |
2021-04-01 – 2024-03-31
|
| Keywords | Inspection / Machine learning / Non-destructive testing |
|---|
| Outline of Annual Research Achievements |
This research aims at the automation of the hammering test for the inspection of concrete structures. Previous approaches based on supervised learning lacked practicability due to the high cost of training data. Thus this research focused on alleviating that cost, notably through domain adaptation, for the automation of the hammering test.
This year, attention was brought on the hardware side of the system, consisting of a UAV for hammering inspection. To solve the acoustic noise issue inherent to such robots, a noise suppression method based on prediction from propeller acceleration was proposed. Additionally, the use of a force sensor mounted on the tip of the hammer was explored and yielded highly promising results.
|
