基于加权模糊核聚类的发电机组振动故障诊断

对模糊C均值(fuzzy C-means，FCM)在机组振动故障诊断中存在不足，提出了一种加权模糊核聚类方法(weighted fuzzy kernel clustering，WFKC)。该方法用Mercer核将样本从输入空间映射到高维特征空间，在特征空间进行聚类，同时考虑到不同特征对聚类结果的不同影响，利用基于样本相似度的加权方法对特征进行加权，在特征空间实现加权模糊聚类。用3组标准测试数据集验证了该方法的聚类效果和分类准确性。最后将该方法应用于发电机组故障诊断，应用实例表明所提出的方法有效，诊断结果可靠。

Vibration Fault Diagnosis of Generating Set Based on Weighted Fuzzy Kernel Clustering

A new weighted fuzzy kernel clustering(WFKC) method is proposed, in order to avoid the drawbacks of fuzzy C-means (FCM) in handling vibration fault diagnosis of generating set. In this method, samples in original space are mapped to high-dimension feature space by Mercer kernel, and then a similarity based weighting method is used to assign weight to features of the transferred samples, and finally weighted fuzzy clustering in feature space is realized. Experiments on three testing data sets have been designed to verify the validity and accuracy of WFKC. In the end, WFKC has been also applied in practice to analyze vibration fault diagnosis of turbine-generator set, and the result demonstrates that WFKC is valid and efficient in vibration fault diagnosis of generating set.