航空学报 > 2024, Vol. 45 Issue (22): 230297-230297   doi: 10.7527/S1000-6893.2024.30297

基于双层变权的异构数据融合及可靠性分析

张帆1,2, 丛玮3, 田润操4, 王鹏1,2()   

  1. 1.中国民航大学 民航航空器适航审定技术重点实验室,天津 300300
    2.中国民航大学 科技创新研究院,天津 300300
    3.中国民航大学 电子信息与自动化学院,天津 300300
    4.中国民航大学 安全科学与工程学院,天津 300300
  • 收稿日期:2024-02-18 修回日期:2024-04-07 接受日期:2024-05-07 出版日期:2024-11-25 发布日期:2024-05-14
  • 通讯作者: 王鹏 E-mail:pwang@cauc.edu.cn
  • 基金资助:
    国家重点研发计划(2021YFB1600601);研究生科研创新项目(2023YJSKC09014)

Heterogeneous data fusion and reliability analysis based on two-layer variable weights

Fan ZHANG1,2, Wei CONG3, Runcao TIAN4, Peng WANG1,2()   

  1. 1.Key Laboratory of Civil Aircraft Airworthiness Technology,Civil Aviation University of China,Tianjin  300300,China
    2.College of Electronic Information and Automation,Civil Aviation University of China,Tianjin  300300,China
    3.Science and Technology Innovation Research Institute,Civil Aviation University of China,Tianjin  300300,China
    4.College of Safety Science and Engineering,Civil Aviation University of China,Tianjin  300300,China
  • Received:2024-02-18 Revised:2024-04-07 Accepted:2024-05-07 Online:2024-11-25 Published:2024-05-14
  • Contact: Peng WANG E-mail:pwang@cauc.edu.cn
  • Supported by:
    National Key Research and Development Program of China(2021YFB1600601);Graduate Research Innovation Project(2023YJSKC09014)

摘要:

随着航空产品可靠性不断提高,正常试验条件下难以收集到大样本的失效数据,导致仅依靠单一数据源进行可靠性分析的精度较低。对此,提出考虑双层变权的异构数据融合及可靠性分析方法。首先,通过异构数据的标准差度量其自身可信度,同时,引入基于模糊面积的支持度函数度量异构数据之间的相似度,从两方面确定异构先验数据的融合权重。进一步,建立双参数威布尔分布分析模型,利用Bayes理论融合异构数据,最终采用分步采样法对目标产品进行可靠性分析。结果表明:利用双层变权分析法确定融合权重,可有效缩减单一数据源存在的不确定性,提高可靠性评估的精度,具有重要的工程应用价值。

关键词: 异构数据融合, 双层变权分析法, Bayes理论, 双参数威布尔分布, 分步采样法, 可靠性分析

Abstract:

Continuous improvements in reliability of aerospace products make it difficult to collect large samples of failure data under normal test conditions, resulting in low accuracy of reliability analysis relying only on a single data source. In this regard, a heterogeneous data fusion and reliability analysis method considering two-layer variable weight is proposed. First, the standard deviation of the heterogeneous data measures its own reliability, and meanwhile, the support function based on the fuzzy area is introduced to measure the similarity between the heterogeneous data, so as to determine the fusion weights of the heterogeneous a priori data from two aspects. Further, a two-parameter Weibull distribution analysis model is established, the heterogeneous data fused using Bayes theory, and the reliability analysis of the target product finally conducted with the stepwise sampling method. The results show that the determination of fusion weights adopting two-layer variable weight analysis can effectively reduce the uncertainty existing in a single data source and improve the accuracy of reliability assessment, exhibiting important engineering application value.

Key words: heterogeneous data fusion, two-level variable weight analysis method, Bayes theory, two-parameter Weibull distribution, stepwise sampling method, reliability assessment

中图分类号: