为提高航空发动机传感器故障诊断的准确率和可靠性,使用改良的D-S证据理论,对基于神经网络和卡尔曼滤波的2个诊断子系统的诊断结果进行决策融合;仿真结果显示,在发动机稳定状态下,经过融合,整个系统降低了误诊率,改善了诊断性能;文章还针对加强噪声强度的情况下,通过调整2个子系统的权重,在保证准确率的同时提高了系统的抗噪声性能;研究表明D-S理论可以比单独应用单一诊断算法的子系统更具好的诊断效能.%In order to improve accuracy and reliability of aeroengine sensors fault diagnosis. In this paper Dempster-Shatter theory is used to build a new diagnosis system by blending and tuning the output of BP neural network based diagnosis sub-system and that of kalman filter based sub-system. In the engine steady state, test results show that the system can diagnose and detect the faults of aeroengine sen-sors with more precision and efficiency than either single sub-system. In adiition. This new D-S theory and two nerual network and kal-man filter based diagnosis system can be used to obtain better ability of rejecting noise than the two sub- systems, wih adjusting the weights of the diagnosis decisions of two sub-systems.
展开▼