@inproceedings{oai:jaxa.repo.nii.ac.jp:00004280,
 author = {森澤, 征一郎 and 野々村, 拓 and 大山, 聖 and 藤井, 孝藏 and 大林, 茂 and Morizawa, Seiichiro and Nonomura, Taku and Oyama, Akira and Fujii, Kozo and Obayashi, Shigeru},
 book = {宇宙航空研究開発機構特別資料, JAXA Special Publication: Proceedings of 44th Fluid Dynamics Conference / Aerospace Numerical Simulation Symposium 2012},
 month = {Mar},
 note = {第44回流体力学講演会/航空宇宙数値シミュレーション技術シンポジウム2012 (2012年7月5日-6日. 富山国際会議場大手町フォーラム), 富山市, 富山県, 44th Fluid Dynamics Conference / Aerospace Numerical Simulation Symposium 2012 (July 5-6, 2012. Toyama International Conference Center), Toyama Japan, Key features from acoustics waves generated from a supersonic jet impinging on three kinds of inclined flat plates are extracted by applying two types of data mining techniques. One is cluster analysis which consists of self-organizing map and k-means method, and the other is proper orthogonal decomposition (POD) with Fourier transformation. The flow data is taken from the numerical simulation data in the previous study. First, the cluster analysis is applied to the dataset based on the normalization of the sound pressure level spectra on symmetrical plane. The results show the apparent characterization of regions based the frequencies of acoustics waves. Clusters corresponding to three kinds of acoustics waves are clearly generated. Next, POD is applied to two-dimensional pressure distribution in the acoustics fields. The results reveal the source locations where strong acoustics waves are generated. These results agree with the previous obse""" rvations. Thus, this study shows the capability of data mining to extract key features of acoustics waves generated from the flow field., 形態: カラー図版あり, Physical characteristics: Original contains color illustrations, 資料番号: AA0061958040, レポート番号: JAXA-SP-12-010},
 pages = {237--242},
 publisher = {宇宙航空研究開発機構(JAXA), Japan Aerospace Exploration Agency (JAXA)},
 title = {データマイニングによる斜め平板に衝突する超音速ジェットから発生する音響波の理解},
 volume = {JAXA-SP-12-010},
 year = {2013}
}