基于模糊聚类算法的油纸绝缘缺陷识别

采用典型模糊聚类算法(FCM)对电力变压器油纸绝缘缺陷进行诊断,研究不同绝缘缺陷的局部放电超高频信号特征识别问题。根据变压器内部绝缘缺陷特征,文章构建典型油纸绝缘缺陷模型,通过提取局部放电超高频信号特征量,构建综合识别矩阵,对缺陷进行识别。采用模糊C-均值聚类算法分别对信号小波去噪前后两种综合特征矩阵进行聚类分析及识别。对比结果表明,小波包多尺度超高频网格维数和能量参数能有效区分4种绝缘缺陷;小波去噪方法提高了正确识别率、最小识别率、识别稳定性、算法稳定性和收敛性。验证了模糊C-均值算法对油纸绝缘缺陷识别的适用性。

Defect Recognition of Oil-paper Insulation by Fuzzy C-means Algorithm

By means of fuzzy C-means(FCM)algorithm,this paper researches the problem of distinguishing charac-teristic vectors of partial discharge(PD)ultra-high frequency(UHF)signals from different defects in oil-paper insu-lation.According to the internal insulation defects in transformer,4 kinds of PD models characterizing typical defects of oil-paper insulation were designed.The multi-scale wavelet packet grid dimensions and energy parameters making up the characteristic vectors are both extracted from UHF signals of PD models.So this paper establishes comprehen-sive characteristic recognition matrixes, cluster data and recognizes defects from it.Two matrixes are clustered and recognized respectively with and without the wavelet de-noising by using fuzzy C-means algorithm.Both the clustering results and characteristics show that it is available to distinguish the difference between PD models characterized by the wavelet packet multi-scale UHF grid dimensions and energy parameters.The correctness ratios,minimum ratios,rec-ognition stability,stability of the algorithm and astringency could be effectively enhanced by wavelet de-noising meth-od;and the Fuzzy C-means algorithm applied to the insulation defect recognition could also be verified by wavelet de -noising method.