基于自组织映射网络的故障诊断推理方法研究

从故障诊断基本形式出发，结合飞机刹车系统故障的各类特点，研究了基于Kohonen自组织映射网络理论的故障推理模型，并且应用到起落架刹车系统故障诊断中。该方法只需选择听，具有代表性的故障样本训练神经网络，他将代表故障的信息输入给训练好的神经网络，根据神经网络的输出结果，就可以判断出发生故障的类型。该模型除能识别已训练过的故障，还能识别未训练过的故障，并且聚类能力强，速度快，因此，很符合复杂系统的故障诊断。

FAILURE DIAGNOSIS INFERENCE BASED ON SELF-ORGANIZING MAP

The paper studied inference methods in fault diagnosis based on the principles of Kohonen self -organizing map neural network and built the fault diagnosis model for aircraft brake system, according to basic formulation of fault diagnoses and features of its failure and failure type. It need not set up a complicated mathematical model, and also need not do complicated mathematical calculation and data processing. All you need do is select enough typical fault samples to trained neural network, the type of shown fault can be judged by the output of the neural network. It can not only discriminate faults for which it has been trained, but also such for which it hasn' t been trained. It has a strong grouping capability, works quickly and is therefore suitable for fault diagnoses of complicated systems.