摘要
发动机故障诊断是飞机故障预测和健康管理的重要内容,为了充分利用发动机的相图特征对发动机转子系统进行故障诊断,提出了一种相图和神经网络相结合的发动机转子系统故障诊断方法;在分析不同状态下发动机的整机振动信号参数在不同范围随机变化导致相轨迹分布不同的基础上,提取发动机振动相图特征值,借助BP神经网络良好的状态分类功能,对发动机转子系统进行故障诊断;实践表明该方法能有效去除噪声对故障信息的干扰,诊断准确率较高,判别速度较快,具有一定的实用价值。
Fault diagnosis of airplane engine is one of the most important aspects of Prognostics and Health Management （PHM）. In or- der to increase the accuracy of engine diagnosis by making full use of the characteristics of phase plot of the engine, a fault diagnosis method of engine rotor is brought forward, which is based on the combination of phase plot and neural network. At first the overall vibration signal parameter＇s random changes in different ranges are anglicized when the engine is in different state, which can lead to the different distribution of the phase trajectories, and then the eigenvalues of engine＇s vibration phase plot are extracted and classified by BP neural network. At last the result can be used in the diagnosis of the engine rotor system. Simulation shows that this method can not only effectively remove interfer- ence of noise on the fault information, but also have higher precision and faster speed.
出处
《计算机测量与控制》
CSCD
北大核心
2012年第8期2055-2057,2060,共4页
Computer Measurement &Control
关键词
振动
相图
BP神经网络
故障诊断
vibration phase plot BP neural network fault diagnosis
