基于频响曲线稀疏表示的变压器绕组变形模式识别方法

为了提高电力变压器绕组状态监测水平,提出了一种基于频响曲线稀疏表示的变压器绕组变形模式识别方法。文章在构建了Gabor原子的过完备原子库和通过有限元模型仿真得到了正常及变形绕组频响曲线的基础上,将正常情况及变形情况下的绕组频响曲线在过完备原子库上进行稀疏表示,并对所有匹配的Gabor原子分别进行短频傅里叶变换、叠加,得到正常曲线及变形曲线的等效时频分布,然后将两条曲线的等效时频分布值相减,得到可以反映绕组频响曲线变形程度的特征向量。最后,利用支持向量机模型实现了不同绕组变形故障的识别。试验结果表明,提出的方法具有较高的可靠性,适用于绕组变形模式识别。

A Transformer Winding Deformation Pattern Recognition Method Based on Sparse Representation of Frequency Response Curve

In order to improve the condition monitoring level of power transformer winding,a transformer winding deformation pattern recognition method based on sparse decomposition of frequency response curve was proposed in this paper.The over-complete dictionary of Gabor atoms was constructed and the frequency response curves of normal and deformation winding were obtained by the finite element model.On this basis,the frequency response curves of winding under normal conditions and deformation conditions were sparse decomposed in the over-complete dictionary.Then,the short frequency Fourier transform and superposition of all matched Gabor atoms were carried out to obtain the equivalent time-frequency distribution of the normal curve and deformation curve.The time-frequency distribution values of two different curves were subtracted in order to obtain the feature vector,which also could be used as a criterion to reflect the deformation degree of frequency response curve of winding.Finally,the support vector machine (SVM) is used to realize the identification of different winding deformation faults.The experimental results show that the method proposed in this paper has a high reliability and is suitable for winding deformation pattern recognition.