摘要
为了区分航空发动机气路故障诊断过程中出现的相似故障,提高诊断准确率,提出了一种基于SOM神经网络和协同学理论的故障诊断方法;首先对测量数据进行归一化处理,建立自组织神经网路初步诊断系统,对于难以区分的相似故障引入协同学理论,进一步判断对应的故障类型,最后根据实际数据对此故障模型进行实例仿真;仿真结果显示,基于SOM和协同学的发动机气路故障诊断方法具有较高的诊断准确率和抗噪能力。
In order to distinguish similar failures of the aero-- engine gas path fault diagnosis and improve the diagnostic accuracy, a method of fault diagnosing based on SOM Network and Synergetic was put forward. Firstly, the measurement data was normalized and the initial diagnosis system based on SOM was established, then introduced the Synergetic theory to distinguish similar failures and further deter- mined the corresponding fault type, finally analyzed this fault model based on actual data. The experimental results show that the aero--en- gine gas path fault diagnosis method based on SOM and Synergetic haero--as high diagnostic accuracy and noise immunity.
出处
《计算机测量与控制》
北大核心
2014年第2期319-320,328,共3页
Computer Measurement &Control
基金
中央高校基本科研业务费中国民航大学专项资助(ZXH2010C002)
