基于非线性频谱的发电机转子系统故障诊断

Fault Diagnosis of Generator Rotor System Based on Nonlinear Spectrum

为了有效识别火力发电系统发电机转子裂纹故障类型,本文通过Volterra核函数法对发电机故障的频谱特征进行分析,找出不同故障类型对应的频谱值的差异性;同时利用辨识算法对核函数进行求解获取非线性频谱特征,然后通过SVM进行分类,实验结果表明,该方法故障特征提取准确率高,在一定程度上降低了故障误诊率。

In order to effectively identify the types of generator rotor crack faults in thermal power system, this paper uses Volterra kernel function method to analyze the spectrum characteristics of generator faults, and finds out the differences of spectrum values corresponding to different fault types. At the same time, the identification algorithm is used to solve the kernel function to obtain the nonlinear spectrum characteristics,after that, the classification is carried out by SVM. The experimental results show that the method has high accuracy in fault feature extraction and can reduce the rate of fault misdiagnosis to a certain extent.