講演名 2017-11-23
ニューラルネットワークとパラメトリック推定法を用いた単一ドップラーライダのための高精度風ベクトル推定法
松尾 太郎(電通大), 孫 光鎬(電通大), 桐本 哲郎(電通大),
PDFダウンロードページ PDFダウンロードページへ
抄録(和) Doppler light detection and ranging (LIDAR) systems measure the wind velocity along the line-of-sight direction by processing the frequency shift of received signals. These systems are useful tool for real-time wind monitoring during aircraft taking off and landing. A wind vector reconstruction method for a single LIDAR is essential for wind field visualization. The conventional velocity volume processing (VVP) and velocity azimuth display (VAD) methods have been developed for a single LIDAR model, which suffer from inaccuracy in the case of local air turbulence. To address with such problem, the neural network augmented parametric estimation method using typical turbulence models such as tornado and microburst, have been proposed in our research. Aiming at more accurate for vector reconstruction, this paper introduces the adaptively size optimization of analysis area into parametric approach. The proposed method enhances the accuracy for wind vector reconstruction in the turbulence case from a numerical simulation.
抄録(英) Doppler light detection and ranging (LIDAR) systems measure the wind velocity along the line-of-sight direction by processing the frequency shift of received signals. These systems are useful tool for real-time wind monitoring during aircraft taking off and landing. A wind vector reconstruction method for a single LIDAR is essential for wind field visualization. The conventional velocity volume processing (VVP) and velocity azimuth display (VAD) methods have been developed for a single LIDAR model, which suffer from inaccuracy in the case of local air turbulence. To address with such problem, the neural network augmented parametric estimation method using typical turbulence models such as tornado and microburst, have been proposed in our research. Aiming at more accurate for vector reconstruction, this paper introduces the adaptively size optimization of analysis area into parametric approach. The proposed method enhances the accuracy for wind vector reconstruction in the turbulence case from a numerical simulation.
キーワード(和)
キーワード(英) Single LIDARLocal air turbulenceNeural NetworkParametric estimation
資料番号 SANE2017-68
発行日 2017-11-16 (SANE)

研究会情報
研究会 SANE
開催期間 2017/11/23(から2日開催)
開催地(和) マレーシア(ボルネオ島)
開催地(英) Malaysia (Borneo Island)
テーマ(和) ICSANE2017
テーマ(英) ICSANE2017
委員長氏名(和) 福島 荘之介(電子航法研)
委員長氏名(英) Sonosuke Fukushima(ENRI)
副委員長氏名(和) 森山 敏文(長崎大) / 灘井 章嗣(NICT)
副委員長氏名(英) Toshifumi Moriyama(Nagasaki Univ.) / Akitsugu Nadai(NICT)
幹事氏名(和) 小幡 康(三菱電機) / 毛塚 敦(電子航法研)
幹事氏名(英) Yasushi Obata(Mitsubishi Electric) / Atsushi Kezuka(ENRI)
幹事補佐氏名(和) 秋田 学(電通大) / 夏秋 嶺(東大)
幹事補佐氏名(英) Manabu Akita(Univ. of Electro-Comm.) / Ryo Natsuaki(Univ. of Tokyo)

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-JTITLE
タイトル(和) ニューラルネットワークとパラメトリック推定法を用いた単一ドップラーライダのための高精度風ベクトル推定法
サブタイトル(和)
タイトル(英) A Neural Network Augmented Parametric Estimation Method for Accurate Wind Vector Reconstruction Using Single Doppler LIDAR
サブタイトル(和)
キーワード(1)(和/英) / Single LIDARLocal air turbulenceNeural NetworkParametric estimation
第 1 著者 氏名(和/英) 松尾 太郎 / Taro Matsuo
第 1 著者 所属(和/英) 電気通信大学(略称:電通大)
The University of Electro-Communications(略称:UEC)
第 2 著者 氏名(和/英) 孫 光鎬 / Guanghao Sun
第 2 著者 所属(和/英) 電気通信大学(略称:電通大)
The University of Electro-Communications(略称:UEC)
第 3 著者 氏名(和/英) 桐本 哲郎 / Tetsuo Kirimoto
第 3 著者 所属(和/英) 電気通信大学(略称:電通大)
The University of Electro-Communications(略称:UEC)
発表年月日 2017-11-23
資料番号 SANE2017-68
巻番号(vol) vol.117
号番号(no) SANE-321
ページ範囲 pp.27-31(SANE),
ページ数 5
発行日 2017-11-16 (SANE)