模糊Kohonen神经网络的旋转机械故障诊断

Fuzzy Fault Diagnosis for Rotating Machinery Based on Kohonen Neural Network

针对传统故障诊断方法不能解决旋转机械故障诊断的模糊性问题,提出一种基于模糊Kohonen神经网络的故障诊断模型,通过模糊量化处理故障样本模式和在Kohonen网络中使用邻域函数自动调整权重程度的改进学习算法,较大提高了网络的学习速度和聚类能力,能对具有模糊性的复合故障进行诊断,是一种适合于复杂旋转机械故障诊断的有效可行的方法。

Aiming to traditional fault diagnosis methods can not solve rotating machinery diagnosis problem,a fault diagnosis method for a fuzzy Kohonen neural network was proposed based on diagnostic working principles.Fuzzy quantifying processing fault sample modle and improving learning algorithm were used,it made neighborhood function autoly adjusting weight degree,network’s leaning speed and clustering capability can be improved greatly.The fuzzy Kohonen network can diagnose single and muitiple faults of fuzziness.It is an effective and suitable method for fault diagnosis of rotating machinery.