基于Kohonen网络的轴系故障诊断研究

Research on Fault Diagnosis System of Ship Shafting Based on Kohonen Neural Network

本文试从Kohonen神经网络在船舶轴系故障诊断中应用研究出发,提出了船舶轴系模拟试验台的结构和监测原理,通过数据采集系统和开发的软件系统,获得轴系振动信号并求得其快速傅里叶变换(FFT)频谱,从频谱图中提取信号能量分布的特征矢量,用Kohonen神经网络对特征矢量进行识别,最终得到正确的故障诊断结果。介绍了Kohonen神经网络的学习和工作算法,并研究了在轴系故障诊断中的具体实施方法。实例验证表明,Kohonen网络是一种很有价值的轴系故障诊断手段。

In order to apply Kohonen Neural Network to fault diagnosis of ship shafting, in this paper the structure and monitoring principal of a ship shafting simulation test bed is studied and discussed. By using the data gathering system and developing the software system, the shafting vibration signal and its FFT chart are obtained. Then the Frequency Chart is analyzed to obtain its eigenvector. The Kohonen Neural Network is used to recognise the eigenvector and conclude the fault reason. In this paper the study and work arithmetic of Kohonen Network is introduced and its actual operating means applied to ship shafting fault diagnosis is exmined closely. A real eample authenticates that Kohonen Neural Network is a meritorious fault diagnosis means of ship shafting.