基于MMD的故障可诊断性定量评价方法
作者:
作者单位:

海军航空大学

作者简介:

通讯作者:

中图分类号:

TP277

基金项目:


Quantitative Evaluation Approach of Fault Diagnosability Based on Maximum Mean Discrepancy
Author:
Affiliation:

Naval Aviation University

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:

    提出了一种基于最大均值差异(Maximum mean discrepancy,MMD)的故障可诊断性定量评价方法.\;该方法无需构建任何系统模型,通过度量不同故障模式下测量数据之间的距离定量评价故障可诊断性,适用于结构复杂不易于建模且能够获取测量数据的复杂系统.\;首先,将测量数据通过特征核映射到可再生核希尔伯特空间(Reproducing kernel Hilbert space, RKHS)中,以MMD作为多元分布距离度量指标,将故障可诊断性定量评价问题转换为多元分布在RKHS中的距离度量问题.\;然后,通过数学推导分析了测量噪声强度对故障可诊断性评价结果的影响.\;最后,通过仿真实例验证了本文方法的有效性.

    Abstract:

    This paper proposes an approach to quantitative evaluation of fault diagnosability based on Maximum mean discrepancy (MMD). The approach quantitative evaluates the fault diagnosability by measuring the distance between measurement data under different fault conditions without building any system model. It is suitable for the system with complex structures that are difficult to build models and can obtain measurement data. First, the measurement data is mapped to the reproducing kernel Hilbert space (RKHS) through the characteristic kernel. MMD is taken as the distance measure of multivariate distributions and the fault diagnosability quantitative evaluation is transformed into the distance measurement of multivariate distributions in RKHS. Then, the influence of measurement noise intensity on the result of fault diagnosability evaluation is analyzed by mathematical derivation. Finally, the validity of the proposed approach is verified by simulation analysis.

    参考文献
    相似文献
    引证文献
引用本文
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:2021-12-20
  • 最后修改日期:2022-12-04
  • 录用日期:2022-05-17
  • 在线发布日期: 2022-06-13
  • 出版日期: