基于小波多尺度变换的局部放电图像识别方法

局部放电模式识别是一种高电压设备绝缘故障诊断的有效方法。文中基于小波多分辨理论,提出了一种对局部放电(?)-q-n灰度图像进行模式识别的新方法。该方法对局部放电待识别图像和参考图像进行小波多尺度分解,然后对某一尺度上形成的低频子图像进行相似度以及模式贴近度计算,按照模式贴近度最大的原则进行模式识别。文中对放电模型实验获得的放电样本进行了模式识别并计算出基于4种小波基的多尺度图像分解的局部放电图像的识别率,分析了小波分解尺度及4种小波正交性及光滑连续性对识别率的影响。分析表明,选择正交小波和合适的分解尺度,文中提出的方法能够获得良好的效果。

New Method for Recognition of Partial Discharge Based on Wavelet Multi-resolution Analysis

Partial discharge pattern recognition is considered as an effective tool for insulation fault diagnosis on high voltage electric equipment. Based on the multi-resolution analysis of wavelet theory, a new image recognition method is proposed to apply in gray intensity image recognition formed by partial discharge phase resolved distribution pattern. Firstly, the awaiting recognition image of partial discharge and the reference one are decomposed by wavelet transform, and then pattern similarity-degree and adjacency-degree are calculated from the correlation coefficients of low-frequency sub-image at some scale. The discharge samples extracted from discharge model experiment are processed to pattern recognition by maximum pattern adjacency-degree. In addition, in terms of the recognition rate of multi-resolution image decomposition with four typical wavelet functions, the influence of wavelet decomposition scale, wavelet orthogonality and its smoothing continuity to recognizing rate is further analyzed. The results show that the method proposed could obtain a satisfied recognition effect by choosing the right orthogonal wavelet and suitable decomposition scale.