基于特征子集的变压器局部放电小样本类型识别

Partial discharge type recognition of small sample for power transformer based on feature subsets

针对变压器局部放电有效经验样本缺乏时的小样本类型识别问题,提出了一种基于特征子集的集成概率神经网络分类方法 FS-EPNN。首先从4种变压器实验模型放电数据中提取了基于局部放电相位分布二维谱图的44个统计特征。其次,为了避免如PCA等传统降维方法造成的分类信息丢失,将样本的所有特征进行划分并组合成多个低维特征子集,然后根据相应特征子集下的所有样本分别构造基于PNN的基分类器,最后采取投票表决规则集成各基分类器结果识别样本的放电类型。实验结果表明,在小样本情况下,该方法与BPNN、基于PCA的PNN和单PNN方法相比进一步提高了局部放电类型的识别率。

Partial discharge（ PD） type recognition for power transformer involves small sample problem because of lack of effective training instances. In this paper,a novel ensemble probabilistic neural network（ PNN） based on feature subsets（ a. k. a. FS-EPNN） was proposed for classifying PD types. Firstly,forty-four statistical characteristic parameters were extracted from two-dimension diagram histograms based on the phase resolved partial discharge data of 4transformer experimental models. Secondly,in order to reduce the feature dimensionality of samples,we split the entire feature set and grouped features into a certain number of feature subsets instead of traditional dimension reduction approach such as PCA,which may cause the information loss. Then,an equal number of PNN classifiers were built according to training instances under each feature subset. Finally,the type of PD was determined by simple majority voting. Experimental results show that,the proposed FS-EPNN outperforms BPNN,PNN based on PCA and single PNN in terms of recognition accuracy for PD.