講演名 | 2021-11-12 GPR data processing methods based on extrem gradient boosting algorithm to detect the backfill grouting of shield tunnel Xiongyao Xie(Tongji Univ.), Li Zeng(Tongji Univ.), Biao Zhou(Tongji Univ.), |
---|---|
PDFダウンロードページ | PDFダウンロードページへ |
抄録(和) | Shield tunnel method is currently the most important method for tunnel excavation in soft soil areas. With the construction and operation of a large number of tunnels in China, a certain degree of structural disease has appeared in the tunnels. How to control the settlements of tunnels and take corresponding measures to ensure the safety of operations has attracted great attention from design and operation management departments. In this chapter, FDTD numerical simulation of backfill grouting by GPR is performed. The GPR images of grouting layers with different thicknesses of 400MHz antenna and 900MHz antenna were simulated respectively, and the theory of integrated learning XGBoost is established. The XGBoost model was trained with numerical modeling data to obtain regression models of grouting layers of different thicknesses under 400 MHz and 900 MHz GPR, and the results showed that the GPR data could be classified and pattern recognized well under this circumstance. |
抄録(英) | Shield tunnel method is currently the most important method for tunnel excavation in soft soil areas. With the construction and operation of a large number of tunnels in China, a certain degree of structural disease has appeared in the tunnels. How to control the settlements of tunnels and take corresponding measures to ensure the safety of operations has attracted great attention from design and operation management departments. In this chapter, FDTD numerical simulation of backfill grouting by GPR is performed. The GPR images of grouting layers with different thicknesses of 400MHz antenna and 900MHz antenna were simulated respectively, and the theory of integrated learning XGBoost is established. The XGBoost model was trained with numerical modeling data to obtain regression models of grouting layers of different thicknesses under 400 MHz and 900 MHz GPR, and the results showed that the GPR data could be classified and pattern recognized well under this circumstance. |
キーワード(和) | Metro / Shield tunnel construction / simultaneous grouting / GPR / None-destructive test / machine learning / XGBOOST(Extreme Gradient Boosting) |
キーワード(英) | Metro / Shield tunnel construction / simultaneous grouting / GPR / None-destructive test / machine learning / XGBOOST(Extreme Gradient Boosting) |
資料番号 | SANE2021-59 |
発行日 | 2021-11-04 (SANE) |
研究会情報 | |
研究会 | SANE |
---|---|
開催期間 | 2021/11/11(から2日開催) |
開催地(和) | オンライン開催 |
開催地(英) | Online |
テーマ(和) | ICSANE2021/地下電磁計測ワークショップ |
テーマ(英) | ICSANE2021/Workshop on subsurface electromagnetic measurement |
委員長氏名(和) | 森山 敏文(長崎大) |
委員長氏名(英) | Toshifumi Moriyama(Nagasaki Univ.) |
副委員長氏名(和) | 田中 真(東海大) / 網嶋 武(三菱電機) |
副委員長氏名(英) | Makoto Tanaka(Tokai Univ.) / Takeshi Amishima(Mitsubishi Electric) |
幹事氏名(和) | 夏秋 嶺(東大) / 二ッ森 俊一(電子航法研) |
幹事氏名(英) | Ryo Natsuaki(Univ. of Tokyo) / Shunichi Futatsumori(ENRI) |
幹事補佐氏名(和) | 北村 尭之(三菱電機) |
幹事補佐氏名(英) | Takayuki Kitamura(Mitsubishi Electric) |
講演論文情報詳細 | |
申込み研究会 | Technical Committee on Space, Aeronautical and Navigational Electronics |
---|---|
本文の言語 | ENG |
タイトル(和) | |
サブタイトル(和) | |
タイトル(英) | GPR data processing methods based on extrem gradient boosting algorithm to detect the backfill grouting of shield tunnel |
サブタイトル(和) | |
キーワード(1)(和/英) | Metro / Metro |
キーワード(2)(和/英) | Shield tunnel construction / Shield tunnel construction |
キーワード(3)(和/英) | simultaneous grouting / simultaneous grouting |
キーワード(4)(和/英) | GPR / GPR |
キーワード(5)(和/英) | None-destructive test / None-destructive test |
キーワード(6)(和/英) | machine learning / machine learning |
キーワード(7)(和/英) | XGBOOST(Extreme Gradient Boosting) / XGBOOST(Extreme Gradient Boosting) |
第 1 著者 氏名(和/英) | Xiongyao Xie / Xiongyao Xie |
第 1 著者 所属(和/英) | Tongji University(略称:Tongji Univ.) Tongji University(略称:Tongji Univ.) |
第 2 著者 氏名(和/英) | Li Zeng / Li Zeng |
第 2 著者 所属(和/英) | Tongji University(略称:Tongji Univ.) Tongji University(略称:Tongji Univ.) |
第 3 著者 氏名(和/英) | Biao Zhou / Biao Zhou |
第 3 著者 所属(和/英) | Tongji University(略称:Tongji Univ.) Tongji University(略称:Tongji Univ.) |
発表年月日 | 2021-11-12 |
資料番号 | SANE2021-59 |
巻番号(vol) | vol.121 |
号番号(no) | SANE-236 |
ページ範囲 | pp.144-148(SANE), |
ページ数 | 5 |
発行日 | 2021-11-04 (SANE) |