中文摘要：

提出一种航空发动机耦合转子系统故障检测的免疫神经网络模型。该模型根据耦合转子系统振动特点，利用免疫识别原理构造神经网络检测器，该检测器用于捕获振动信号的异常模式特征。通过训练将振动信号的故障模式信息存储于分布的检测器中，当检测器与待检测信号样本匹配时则激活该检测器，根据检测器的激活情况发现故障。双转子振动实验结果表明：该方法对于由双转子耦合特性所造成的信号突变具有较高的灵敏度和分辨率，能够有效地检测转子系统常见的故障模式。

英文摘要：

A new vibration fault detection model of aeroengine coupled dual-rotor system was proposed based on immune-neural networks. In this model, neural networks-based detectors were constructed based on the principle of immune recognition. These detectors were used to capture the anomalous pattern features of vibration signal. Taking advantage of neural networks training, the information of fault patterns was stored in the distributed neural networks-based detectors. When a detector was matched up with a feature sample, the detector was stimulated. Through the relevant stimulated detectors, a fault could be found out. Vibration experiments results of dual-rotor system shows that the proposed model has high resolution for locations of signal singularities, which are caused by characteristics of coupled rotor system. This method is contributive for rotor system monitoring.