One-class Support Vector Machineを用いたクラス集合逐次作成法による回転機の異常予兆検知

カテゴリ: 論文誌(論文単位)

グループ名: 【D】産業応用部門

発行日: 2017/12/01

タイトル(英語): Fault Sign Detection Method for Rotators based on One-class Support Vector Machine with Successive Multi-level Class Construction

著者名: 中尾　浩二（（株）明電舎／横浜国立大学大学院工学府），外山　達斎（（株）明電舎），林　孝則（（株）明電舎），堀　貴雅（（株）明電舎），濱上　知樹（横浜国立大学大学院工学府）

著者名(英語): Koji Nakao (MEIDENSHA CORPORATION/Graduate School of Engineering, Yokohama National University), Tatsushi Toyama (MEIDENSHA CORPORATION), Takanori Hayashi (MEIDENSHA CORPORATION), Takamasa Hori (MEIDENSHA CORPORATION), Tomoki Hamagami (Graduate School of Engineering, Yokohama National University)

キーワード: 回転機，軸受，オンライン診断，ケプストラム，1クラス・サポートベクターマシン，クラス集合逐次作成　　rotator，bearing，on-line diagnosis，cepstrum，one-class support vector machine，sequential construction method of class set

要約(英語): A new fault sign detection method for rotators based on one-class support vector machine is proposed. The vibration of rotators occurs not only during faulty operation, but also during normal operation. Furthermore, faults are rare events, and it is difficult to obtain an indication of fault occurrence beforehand. To overcome this issue, a one-class support vector machine with successive multi-level class construction is proposed. The advantage of this method is that the time varied feature can be classified according to the class-set. The experiments are conducted by using actual rotator data. The results show that the class-set feature is capable of indicating the fault sign.

本誌: 電気学会論文誌D（産業応用部門誌） Vol.137 No.12 （2017）

本誌掲載ページ: 858-865 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejias/137/12/137_858/_article/-char/ja/