航空学报 > 2018, Vol. 39 Issue (3): 221706-221706   doi: 10.752/S1000-6893.2017.21706

通用航空机队设备可靠性动态识别模型

陈勇刚, 熊升华, 贺强, 贺元骅   

  1. 中国民用航空飞行学院 民航安全工程学院, 广汉 618307
  • 收稿日期:2017-08-29 修回日期:2017-10-27 出版日期:2018-03-15 发布日期:2018-04-10
  • 通讯作者: 陈勇刚,E-mail:chenygscms@126.com E-mail:chenygscms@126.com
  • 基金资助:
    国家自然科学基金(U1633203);民航飞行技术与飞行安全科研基金(F2015KF01);中国民航飞行学院科研基金(J2014-32)

Dynamic recognition method for reliability of general aviation fleet equipment

CHEN Yonggang, XIONG Shenghua, HE Qiang, HE Yuanhua   

  1. College of Civil Aviation Safety Engineering, Civil Aviation Flight University of China, Guanghan 618307, China
  • Received:2017-08-29 Revised:2017-10-27 Online:2018-03-15 Published:2018-04-10
  • Supported by:
    National Natural Science Foundation of China (U1633203); CAAC Scientific Research Base on Aviation Flight Technology and Safety (F2015KF01); Civil Aviation Flight University of China Scientific Research Foundation (J2014-32)

摘要: 通用航空机队设备可靠性是通航单位安全运行的前提条件,是影响运营单位经济效益的重要因素之一。根据通航单位机队设备可靠性数据统计、分析及实际使用情况,采用ATA100章节名称作为指标源。综合可变模糊识别方法和权重阶梯朴素贝叶斯分类器模型的优势,构建了通用航空机队设备可靠性动态识别模型。为了避免主观给定指标权重导致的不合理,应用熵权法客观获取指标权重。最后利用实例测试样本验证了权重阶梯朴素贝叶斯分类器的合理性,并基于该方法对待识别样本进行了可靠性状态识别。实例分析表明:基于权重阶梯朴素贝叶斯分类器的通用航空机队设备可靠性状态识别模型具有较强的可行性和合理性,为通用航空机队设备可靠性状态提供了一种科学的识别方法。

关键词: 通用航空, 机务维修, 模糊识别, 熵权法, 朴素贝叶斯分类器

Abstract: Reliability of general aviation fleet equipment is a precondition for safe operation of the airline company, and is one of the important factors that affect the economic benefits of the company. According to the statistics, analysis and actual usage of reliability data of general aviation fleet equipment, the index system is constructed according to the ATA100 chapter name. Based on the advantages of the variable fuzzy recognition method and the weight ladder naive Bayesian classifier model, a dynamic recognition model for reliability of general aviation fleet equipment is constructed. To avoid the irrationality caused by the subjective given index weight, the entropy weight method is used to obtain the index weight objectively. An example is used to verify the rationality of the weight ladder naive Bayesian classifier model, and reliability recognition of the identified sample is carried out based on the proposed method. Analysis of the example shows that the weight ladder Bayesian classifier reliability recognition model for general aviation fleet equipment is feasible and reasonable, providing a scientific method for reliability recognition of general aviation fleet equipment.

Key words: general aviation, aircraft maintenance, fuzzy recognition, entropy weight method, naive Bayesian classifier

中图分类号: