跳到主要导航 跳到搜索 跳到主要内容

Application of unsupervised linear discriminant analysis for condition monitoring of rotating machinery

  • Xi'an Jiaotong University
  • Xinjiang University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

2 引用 (Scopus)

摘要

As a popular feature extraction method, Linear Discriminant Analysis (LDA) is used to deal with the discrimination recognition directly. However, a supervised method like LDA is difficult to apply in online condition monitoring of rotating machinery due to the lack of data label. In this paper an unsupervised LDA method integrated with Principle Component Analysis (PCA) and K-Means clustering is proposed to simplify the application of LDA for the rotating machinery dataset. The proposed method was analyzed and verified for the actual rotating machinery dataset collected from rotor shaft under different fault condition. K-nearest neighbor was adopted to show the effectiveness of the proposed unsupervised LDA method in extracting features from rotor dataset. The result shows that the new method not only can identify different conditions of the rotors, but also can be easily applied to online condition monitoring for rotating machinery.

源语言英语
主期刊名Proceedings of 2017 9th International Conference On Modelling, Identification and Control, ICMIC 2017
出版商Institute of Electrical and Electronics Engineers Inc.
页43-48
页数6
ISBN(电子版)9781509065738
DOI
出版状态已出版 - 2 7月 2017
活动9th International Conference on Modelling, Identification and Control, ICMIC 2017 - Kunming, 中国
期限: 10 7月 2017 → 12 7月 2017

丛书

姓名Proceedings of 2017 9th International Conference On Modelling, Identification and Control, ICMIC 2017
卷2018-March

会议

会议9th International Conference on Modelling, Identification and Control, ICMIC 2017
国家/地区中国
市Kunming
时期10/07/17 → 12/07/17

学术指纹

探究 'Application of unsupervised linear discriminant analysis for condition monitoring of rotating machinery' 的科研主题。它们共同构成独一无二的学术指纹。

引用此