故障逻辑与贝叶斯时变评价网络融合的民机空调系统健康评估方法

打开文本图片集

中图分类号：V271.1 文献标志码：A DOI： 10.12305/j.issn.1001-506X.2026.03.13

Abstract：To effctively achieve health assessment of civil aircraft airconditioningsystem under limited sample conditionsand addressthechallengeofevaluating stateinthetime dimension of airconditioningsystem，anassessment method that integrates fault logic withaBayesiantime-varying evaluation network is proposed.Firstly，basedonthe system operatingprinciples，athre-level evaluation framework of“monitoring indicators-components-system”isconstructed，and afaultlogic diagram is employedtoclarifytherelationships between monitoring indicatorsandcomponentstates.Secondly， atime-varyingcomprehensively weighted fuzzycomprehensive evaluation method isestablishedby introducinga temporal factor and information entropy independence weight coefficient coupling weighting strategy，enabling quantify health status of components in the time dimension.Thirdly，a game-equilibrium-driven Bayesian network is incorporated to map component states tothe system state，forming the Bayesian time-varying coupling weighted fuzzy comprehensive evaluation model（BTCW-FCEM） for dynamic assssment of system-level health.Finally，case studies on single component and composite component faults are conducted usingoperational monitoring data from a domesticcivil aircraft airconditioning system，validating the high accuracyand eficiencyof modelindynamic health assessment.The resultsshow that the BTCWFCEMoutperforms multiplecomparative models in terms of accuracy，precision，recall，andF1 score in various fault scenarios，providingreliable technicalsupportforhealth monitoring andfault waingofcivil aircraft airconditioning systems.

Keywords：Bayesian network；civil aircraft air conditioning system；health assessment；fault logic diagram；fuzzy evaluation

0引言

民用飞机空调系统作为飞机最重要的子系统之一，其主要功能是维持舱内适宜的压力和温度，为乘客和机组人员提供舒适安全的飞行环境[1-2]。（剩余20915字）