基于核自适应滤波的多操纵面飞机多模型舵面故障诊断

Multiple-model actuator fault diagnostic for multi-effectors aircraft based on kernel adaptive filtering

针对多模型自适应估计方法中精确的飞机数学模型难以获得和模型存在非线性等问题,引入核自适应滤波器(KAF)替换卡尔曼滤波器,提岀了一种新的多模型自适应估计故障诊断方法。通过核方法将复杂的非线性系统映射到高维特征空间中,在该空间中设计线性自适应滤波器,无需预先知道精确的飞机数学模型,通过控制输入信号和姿态输出信号的训练数据训练核自适应滤波器,进而在线估计飞机的飞行状态,完成飞机舵面的故障检测与隔离。扩展了KAF的使用范围,改进了传统的状态估计故障诊断方法。研究成果可为降低飞机因舵面故障而引起的事故,提高飞机的生存性提供理论和技术支撑,具有一定的军事意义和良好的应用价值。

In the traditional multiple model adaptive estimation algorithm,due to the difficulty of acquiring precision math model of aircraft and the strong nonlinearity of mathematical model,there are some errors in the results of fault diagnostic.In this paper,the kernel adaptive filter(KAF)is introduced to replace the Kalman filter,a new multi-model adaptive estimation fault diagnosis method is proposed.Based on the kernel methods,the complex nonlinear system is mapped to the high-dimensional feature space,then the adaptive filter is designed in the high-dimensional feature space without the need to know the aircraft model in advance.The offline input control signal and output attitude signal are used to train the KAF,then the estimation of flight state and actuator fault detection and isolation can be realized online.This research results can provide theoretical and technical support for reducing the accident caused by the actuator fault and improving the survivability of the aircraft.It has certain military significance and excellent application value.