Presentation | 2019-12-22 Study on hammering test system using artificial intelligence Tsubasa Fukumura, Atsushi Ito, Katsuhiko Hibino, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Social infrastructure such as bridges and tunnels is very important in economic activities, but in recent years aging has progressed and demand for inspection work is expected to expand. Among inspection work, it is possible to inspect by abnormal sound which can’t be visually observed, such as the inside of concrete wall, by change of sound by hammering sound. In the inspection called this hammering test, the distinction of abnormal sound depends on the feeling of the person performing the hammering sound, and there is a possibility that the results may be inconsistent. In addition, since hammering is performed manually, there is also a problem that it takes time to perform a wide range of examination. Therefore, in this paper, we describe a system for a small hammering tone inspection device which can analyze and judge sounds hit the wall with a hammer with artificial intelligence and judge an abnormal part even for unskilled people. In addition, we will raise the issues and consider a new system using GPU and transfer learning to improve work efficiency and accuracy. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Social infrastructure / Hammering test / Deep learning / Transfer Learning / GPU |
Paper # | TL2019-44 |
Date of Issue | 2019-12-15 (TL) |
Conference Information | |
Committee | TL |
---|---|
Conference Date | 2019/12/22(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Hiroshi Sano(Tokyo Univ. of Foreign Studies) |
Vice Chair | Tadahisa Kondo(Kogakuin Univ.) / Kazuhiro Takeuchi(Osaka Electro-Comm. Univ.) |
Secretary | Tadahisa Kondo(Kobe Gakuin Univ.) / Kazuhiro Takeuchi(Kyoto Inst. of Tech.) |
Assistant | Nobuyuki Jincho(Miidas) / Akinori Takada(Ferris Univ.) / Akio Ishikawa(KDDI Research) |
Paper Information | |
Registration To | Technical Committee on Thought and Language |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Study on hammering test system using artificial intelligence |
Sub Title (in English) | |
Keyword(1) | Social infrastructure |
Keyword(2) | Hammering test |
Keyword(3) | Deep learning |
Keyword(4) | Transfer Learning |
Keyword(5) | GPU |
1st Author's Name | Tsubasa Fukumura |
1st Author's Affiliation | Utsunomiya University(Utsunomiya-u) |
2nd Author's Name | Atsushi Ito |
2nd Author's Affiliation | Utsunomiya University(Utsunomiya-u) |
3rd Author's Name | Katsuhiko Hibino |
3rd Author's Affiliation | Port electric Inc.(Port Inc) |
Date | 2019-12-22 |
Paper # | TL2019-44 |
Volume (vol) | vol.119 |
Number (no) | TL-352 |
Page | pp.pp.7-12(TL), |
#Pages | 6 |
Date of Issue | 2019-12-15 (TL) |