摘要
用转子振动试验台模拟了汽轮机典型故障,根据其频域变化特性,采用小波包分析对其建立频域能量特征向量,并根据最佳分解树进行了特征选择。最后用神经网络进行故障状态识别,取得了良好的效果。
Experimental platform is used to simulate typical faults of turbine. Based on the frequency domain feature, energy eigenvector of frequency domain is presented using wavelet packet anal- ysis method, and the way of best tree is used to choose symptom. The fault states are recognized using neural network. The simulatious show that it makes good performance.
出处
《电力科学与工程》
2005年第3期63-65,共3页
Electric Power Science and Engineering
关键词
故障诊断
特征提取
小波包分析
最佳分解树
神经网络
fault diagnosis
symptom extraction
wavelet packelanalysis
best tree
neural networks