欢迎访问润滑与密封官方网站!

咨询热线:020-32385313 32385312 RSS EMAIL-ALERT
显微磨粒图像识别知识规则提取及其应用研究
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学基金项目(61179057)


Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对新研制的多功能油液磨粒智能检测系统MIDCS中的磨粒图像识别问题,引入数据挖掘方法获取了磨粒图像识别的知识规则,实现对磨粒类别的智能识别。利用MIDCS系统获取实际航空发动机运行过程中由于滚动轴承磨损而产生的大量典型磨粒,基于图像分析方法提取16个磨粒特征参数,形成标准案例库;利用Weka软件的决策树算法自动提取知识规则,并对知识规则进行优化和简化;对所提取得到的知识规则进行验证和分析。结果表明,所提取的磨粒识别规则符合磨粒识别的统计规律,识别规则不仅简洁,而且具有很高的精度。基于Weka软件的规则提取方法大大提高了MIDCS系统的磨粒识别自动化和智能化水平,对于利用MIDCS进行航空发动机滚动轴承疲劳磨损故障诊断,具有重要的工程实用价值。

    Abstract:

    Aimed at the wear particle recognition problem of the new Multiple Intelligent Debris Classifying System (MIDCS), data mining method was introduced in order to obtain the knowledge rules of wear particle recognition, and the expert system theory was used to realize the intelligent recognition of debris classes. A large number of typical debris caused by rolling bearing wear in the actual aeroengine operational process was obtained by MIDCS, 16 debris characteristic parameters were extracted based on the image analysis method, and the standard case library was formed. The decision tree algorithm of the Weka software was used for automatic extraction of the knowledge rules, and the knowledge rules were optimized and simplified. The extracted knowledge rules were verified and analyzed. The results show that the rules agree well with the wear particles recognition statistical laws, the extracted rules is very brief and correct, the extraction method based on Weka software can be used in the debris class recognition of MIDCS well,and the automation and intelligent level of MIDCS debris class recognition are greatly improved. It is of significant engineering value for the aeroengine rolling bearing fatigue wear fault diagnosis by using MIDCS.

    参考文献
    相似文献
    引证文献
引用本文

王洪伟,陈果,林桐,汪瑾,陈立波.显微磨粒图像识别知识规则提取及其应用研究[J].润滑与密封,2015,40(10):86-91.
.[J]. Lubrication Engineering,2015,40(10):86-91.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2016-01-08
  • 出版日期: