基于条件规则及故障树的舱音分析诊断

Cockpit Voice Analysis and Diagnostic Based on Conditional Rules & Fault Tree Analysis

基于多个典型舱音样本声,依据舱音辨听传统方法、小波变换等现代分析方法,得到风切变音频、近地音频警告等不同舱音背景声及其频率等特征信息。提出利用条件规则和故障树对舱音特征进行分析、诊断,以区别近似舱音或不同舱音的近似特征,为准确掌握飞行事故原因、分析诊断飞行事故、保障飞行安全具有一定借鉴作用。

Based on typical cockpit voice samples, through traditional distinguishing ＆ listening method by audio software in laboratory and Wavelet Transform modern methods, some cockpit voices and background sounds such as wind shear audio and near ground audio warning are differentiated, and their special characteristics such as frequency value, spectral density are also obtained. Conditional rules and fault tree principles are applied to distinguish these special characteristics and diagnose for approximate or different background sounds of cockpits voices. Through all above researches, the new analyzing approaches are put forward in the paper, which are suitable for diagnosing flight accidents and the accurate causes of the accidents. This can provide certain references to ensure flight safety.