基于卡尔曼滤波器及神经网络的发动机故障诊断

Fault diagnosis for gas turbine engines based on Kalman filter and neural networks

提出了一种基于卡尔曼滤波器及神经网络的航空燃气涡轮发动机气路故障诊断的方法.该方法用卡尔曼滤波器来估计发动机可测参数的变化量,再由神经网络来映射发动机性能参数的变化量,并据此进行发动机气路故障诊断.数字仿真表明,该方法是可行的,有效的.

A method for gas path fault diagnosis of gas turbine engines based on Kalan filter and neural networks was proposed. For the fault diagnosis, the Kalman filter was used to estimate the variations of measurable parameters, while neural network was applied for mapping the variations of performance parameters of gas turbine engines. Digital simulations show that the proposed method is feasible and effective.