基于多源冲突证据信息融合的测试性评估方法
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TH707;TJ06

基金项目:

海军装备技术基础资助项目(191HJ35003)


Testability Evaluation Method of Equipment Based on Information Fusion for Multi⁃source Conflict Evidence
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:

    针对基于先验数据融合的测试性指标评估中存在先验信息互相冲突的问题,提出一种基于多源冲突证据信息融合的测试性评估方法,在传统D?S证据融合方法上,引入兰氏距离进行改进。首先,对各来源不同形式的先验数据,分别利用经验Bayes法和最大熵法对测试性虚拟仿真实验数据、测试性专家经验信息和测试性预计信息进行折合,进而求得对应的测试性指标先验分布参数;然后,通过贝塔函数依次构造其在辨识框架下的基本信任分配函数;最后,通过基于兰氏距离的D?S证据融合改进方法进行信息融合,得到最终评估结果。通过实例分析,验证了笔者提出的方法较传统D?S证据融合方法精度更高。

    Abstract:

    In the testability index evaluation method based on prior data fusion, there is a problem that the prior information conflicts with each other. Thus, a testability evaluation method of equipment based on information fusion multi-source conflict evidence is proposed, introducing the Lance distance to improve the traditional D-S evidence fusion method. Firstly, according to the different forms of a prior data of each source, the empirical Bayesian method and the maximum entropy method are used to obtain the prior distribution parameters of testability indicators, and then, the mass function under the identification framework is constructed by the Beta function. Finally, the final evaluation result is obtained by using the D-S evidence fusion method based on the improved Lance distance. Through the example analysis, it is found that the method proposed in this paper has higher accuracy compared with the traditional D-S evidence fusion method.

    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:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2021-10-31
  • 出版日期: 2021-10-30
您是第位访问者
振动、测试与诊断 ® 2024 版权所有
技术支持:北京勤云科技发展有限公司