WEKO3
アイテム
回転機械設備の状態監視・診断法に関する研究 －構造系異常振動のメカニズム解明と知的診断法－
http://hdl.handle.net/10076/0002001037
http://hdl.handle.net/10076/000200103756b9c6ac-7f2f-4d49-8c26-f8bc71c937bc
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
2018DB0304.pdf (4.3 MB)
|
|
| Item type | 学位論文 / Thesis or Dissertation(1) | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2024-11-07 | |||||||||||
| タイトル | ||||||||||||
| タイトル | Study on Condition Monitoring and Diagnosis Method of Rotating Machinery – Vibration Mechanism Clarification and Intelligent Diagnosis Method for Structural Fault of Rotating Machinery | |||||||||||
| 言語 | en | |||||||||||
| タイトル | ||||||||||||
| タイトル | 回転機械設備の状態監視・診断法に関する研究 －構造系異常振動のメカニズム解明と知的診断法－ | |||||||||||
| 言語 | ja | |||||||||||
| 言語 | ||||||||||||
| 言語 | eng | |||||||||||
| 資源タイプ | ||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_db06 | |||||||||||
| 資源タイプ | doctoral thesis | |||||||||||
| アクセス権 | ||||||||||||
| アクセス権 | open access | |||||||||||
| アクセス権URI | http://purl.org/coar/access_right/c_abf2 | |||||||||||
| 著者 |
関, 照議
× 関, 照議
|
|||||||||||
| 抄録 | ||||||||||||
| 内容記述タイプ | Abstract | |||||||||||
| 内容記述 | In order to effectively detect and identify the structure faults of rotating machinery, especially the precise diagnosis of structure faults at low speeds, in this study, we first proposed two kinds of dynamic model for shaft misalignment of rotating machinery as an entry point, the models will be used for vibration analysis of shaft misalignment state. Subsequently, we proposed a new kind of dedicated symptom parameters for structure faults of rotating machinery. Based on these symptom parameters, fault diagnosis method for structure faults of rotating machinery by multi-positional and multi-directional signals fusion and sequential successive multivariate analysis can be realized. The method can realize the detection and type discrimination of structure faults. Finally, we propose a precision diagnosis method that combines signal processing method which used empirical mode decomposition and sample entropy, with deep belief neural network (DBN). The advantage of this method is that the empirical signal decomposition method can be used to decompose the diagnosed signal into a plurality of intrinsic mode functions with high Signal to noise ratio (SNR), and then use the sample entropy as a criterion to screen the signals which containing a large amount of fault information. The screened signal are reconstructed into a new vibration signal. At last, the vibration signal is classified (precise diagnosis) by the deep learning method (DBN) which has strong pattern recognition function in the field of pattern recognition. The method has higher diagnostic precision than conventional methods. According to the experimental data measured by the rotating machinery in the abnormal states of each structure faults, the effectiveness of each method will be verified. |
|||||||||||
| 言語 | en | |||||||||||
| 内容記述 | ||||||||||||
| 内容記述タイプ | Other | |||||||||||
| 内容記述 | 本文/三重大学大学院 生物資源学研究科 共生環境学専攻 環境・生産科学講座 環境情報システム工学教育研究分野 | |||||||||||
| 内容記述 | ||||||||||||
| 内容記述タイプ | Other | |||||||||||
| 内容記述 | 87p | |||||||||||
| 書誌情報 |
発行日 2019-03-25 |
|||||||||||
| フォーマット | ||||||||||||
| 内容記述タイプ | Other | |||||||||||
| 内容記述 | application/pdf | |||||||||||
| 著者版フラグ | ||||||||||||
| 出版タイプ | VoR | |||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||
| 出版者 | ||||||||||||
| 出版者 | 三重大学 | |||||||||||
| 出版者（ヨミ） | ||||||||||||
| 値 | ミエダイガク | |||||||||||
| 学位名 | ||||||||||||
| 学位名 | 博士(学術) | |||||||||||
| 学位授与機関 | ||||||||||||
| 学位授与機関識別子Scheme | kakenhi | |||||||||||
| 学位授与機関識別子 | 14101 | |||||||||||
| 学位授与機関名 | 三重大学 | |||||||||||
| 学位授与年月日 | ||||||||||||
| 学位授与年月日 | 2019-03-25 | |||||||||||
| 学位授与番号 | ||||||||||||
| 学位授与番号 | 甲学術第1960号 | |||||||||||
| 資源タイプ（三重大） | ||||||||||||
| 値 | Doctoral Dissertation / 博士論文 | |||||||||||
