• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Zhang, Tao (Zhang, Tao.) (学者:张涛) | Xue, Huiyuan (Xue, Huiyuan.)

收录:

CPCI-S

摘要:

In this paper, the gearbox as the research object, under the conditions of strong interference signal acquisition and analysis, denoising, eigenvalue extraction, pattern recognition and fault prediction has very important practical significance. Aiming at the problem of end effect in Empirical Mode Decomposition (EMD), an improved method for the continuation of the even-extended cosine window function (EECW) of signal sequences is proposed. Firstly, the signal sequence is continually extended to realize the smooth transition between the extension data and the original signal, avoiding the jump of the instantaneous frequency of the signal. Secondly, there is the problem of continuation error for this extension method. (Or slow speed) to the internal development of data to ensure the correct decomposition of the signal valid data to improve the accuracy of the decomposition of the signal to achieve the improvement of EMD algorithm. Through the simulation analysis and fault diagnosis, it is shown that the method can effectively suppress EMD endpoint effect and realize the effective diagnosis of rotating machinery fault. The experimental results show that the proposed method has high precision and good performance

关键词:

EMD Endpoint Effect Fault Diagnosis Feature Extraction Secial Armored Vehicle Gearbox SVM

作者机构:

  • [ 1 ] [Zhang, Tao]Beijing Univ Technol, Fac Informat Technol, Beijing Engn Res Ctr IoT Software & Syst, Beijing, Peoples R China
  • [ 2 ] [Xue, Huiyuan]Beijing Univ Technol, Fac Informat Technol, Beijing Engn Res Ctr IoT Software & Syst, Beijing, Peoples R China

通讯作者信息:

  • [Xue, Huiyuan]Beijing Univ Technol, Fac Informat Technol, Beijing Engn Res Ctr IoT Software & Syst, Beijing, Peoples R China

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

PROCEEDINGS OF THE 2017 INTERNATIONAL CONFERENCE ON MECHANICAL, ELECTRONIC, CONTROL AND AUTOMATION ENGINEERING (MECAE 2017)

ISSN: 2352-5401

年份: 2017

卷: 61

页码: 298-305

语种: 英文

被引次数:

WoS核心集被引频次: 0

SCOPUS被引频次:

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 2

在线人数/总访问数:512/2899931
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司