论文部分内容阅读
针对利用快速存取记录器(QAR)数据进行民机系统故障诊断问题,以民机引气系统为对象,提出了一种适合多飞行循环数据特点的多元线性回归模型的故障检测方法.首先建立了多飞行循环数据的引气系统性能多元线性回归模型,设计了飞行循环和飞行循环内故障检测方法;然后采用最大后验估计方法进行模型参数估计;最后设计了适合多飞行循环数据的模型参数最大后验估计算法.借助仿真数据和航空公司收集的实际飞行数据对方法进行了验证,结果表明了该方法有效且具有一定工程应用价值.
Aiming at the fault diagnosis of civil aircraft system based on QAR data, this paper proposes a fault detection method for multivariate linear regression model which is suitable for multi-cycle data characteristics, A multi-linear regression model of air-bleed system performance with multi-flight cycle data was designed, and the flight loop and flight fault detection methods were designed. Then the maximum a-posterior estimation method was used to estimate the model parameters. Finally, the model parameters The maximum a posteriori estimation algorithm is validated by simulation data and the actual flight data collected by airlines.The results show that this method is effective and has certain engineering application value.