The use of fractal features for recognition of 3-D dischargepatterns

This work presents further results on the use of fractal features for recognition of 3-D partial discharge patterns. Two fractal features, the fractal dimension and lacunarity were calculated from 3-D discharge patterns and their power to discriminate among various discharge patterns was analyzed. The results indicate that fractal features possess fairly reasonable discriminating abilities     

Impulse fault classification in transformers by fractal analysis

Transformers are usually subjected to lightning impulse tests after assembly for assessment of their insulation strength. In the case of a fault the resulting winding current gets changed to a certain extent. The pattern of the fault currents depends on the type of fault and its location along the length of the winding. This paper describes the application of the concept of fractal geometry to analyze the properties of fault currents. Fractal features such as fractal dimension, lacunarity used for image surface recognition and the sliding window algorithm used for fractal analysis of waveform have been employed for classification of transformer impulse faults. Experimental results obtained for a 3 MVA transformer and simulation results obtained for 3 MVA, 5 MVA and 7 MVA transformers are presented to illustrate the ability of this approach to classify insulation failures. The results indicate that this new approach possesses reasonable abilities for waveform pattern discrimination.     

交联聚乙烯电缆局部放电灰度图像的模式识别

局部放电模式识别是判断电气设备绝缘状况的重要方法之一。分形理论在局部放电特征的提取上是一种行之有效的方法,通过构造交联聚乙烯(XLPE)电缆局部放电信号的灰度图像,采用逐段搜索确定无标度区域,并采用盒维数与信息维数为特征量作为人工神经网络的输入,对局部放电缺陷进行模式识别。研究表明分形特征在局部放电模式识别上具有良好的效果。     

以盒维数和信息维数为识别特征量的GIS局部放电模式识别方法

研制了5种典型的GIS人工模拟缺陷模型及其局部放电检测系统，通过实验获取了大量局部放电样本数据，构造出GIS局部放电灰度图象；提出有效估计图象盒维数的最少盒计数法；提取了GIS局部放电灰度图象的分形特征——盒维数和信息维数：利用以局部放电灰度图象的盒维数和信息维数作为识别特征量，径向基函数人工神经网络为识别分类器的GIS局部放电模式识别方法，取得了良好的识别效果。     

Can fractal techniques be used for impulse fault pattern discrimination in distribution transformers?

Distribution transformers connected to overhead lines are often prone to lightning strikes and resulting winding damage. For assessment of their insulation strength against such impulse stresses they are usually subjected to lightning impulse tests after assembly. In the case of a fault inside the winding, the shape of the winding current changes as compared to that of a healthy winding. The pattern of the fault current depends on the type of fault and its location along the length of the winding. This paper investigates the potential application of fractal techniques for analysis of such fault current patterns. Fractal features such as fractal dimension and lacunarity commonly used for image and pattern recognition have been employed for classification of distribution transformer impulse faults. Simulation results obtained for a range of distribution transformer digital models are presented to illustrate the ability of this approach to classify insulation failures during impulse testing. The proposed tool has been applied for impulse fault analysis of a scaled-down analog model of a 3 MVA transformer. The results promise potential application of this novel technique for impulse fault pattern recognition in distribution transformers.     

超声波法进行变压器局部放电模式识别的研究

在线识别局部放电模式可以有效地判断局部放电对变压器绝缘的危害程度。文中根据局部放电超声波信号存在的非线性和非平稳特性，提出利用分形理论对局部放电超声波信号的时域脉冲形进行分析，对分形理论及其参数计算方法进行了简单的介绍，在自制的几种典型变压器局部放电模型上进行实验，计算了所得到的局部放电超声波信号的分型参数（分维数和空缺率），得到不同放电形式的分形特征，利用人工神经网络对所得到的分形特征进行模式识别，结果表明利用超声波信号可以有效地判断变压器局部放电模式，为变压器局部放电信号的特征提取和模式识别提供了一种新的研究方法。     

PD recognition by means of statistical and fractal parameters and aneural network

A novel partial discharge (PD) defect identification method is described. Starting with PD data on different families of specimens, a suitable set of parameters are determined and then used as input variables to a neural network for the purpose of identifying the defects within the insulation. In this procedure the statistical Weibull analysis is performed on PD pulse amplitude histograms to obtain the scale parameter α and the shape parameter β. Thereafter, the two statistical operators (skewness and kurtosis) and two fractal parameters (fractal dimension and lacunarity) are evaluated from the PD phase on the discharge epoch histogram and from the 3 dimensional (pulse amplitude/phase/discharge rate) histogram, respectively. Following the exposition of the basic mathematical concepts regarding the above parameters, experimental results are reported on the recognition capability of the method in defining the defect category in a number of different specimens     

局部放电远程识别中的分形图像压缩方法

研究了局部放电图像分形压缩技术 ,分析了解码图像误差对识别结果的影响。大量的样本数据识别结果说明 :采用分形图像压缩技术能获得较高的局放图像压缩比 ,提高了系统对远程计算机存储局放图像的识别速度 ,使局放图像远程识别系统具有更强的实用性     

Artificial neural networks for recognition of 3-d partial dischargepatterns

Partial discharge (PD) measurements have been carried out over the years to assess insulation systems in power apparatus for their integrity and design deficiencies. Digital PD recording, processing and its presentation as 3-d patterns are recent trends in both industry and testing laboratories. Interpretation of these patterns can lead to evaluation of the cause of PD. A need arises to look for methods in the domain of pattern recognition for automating this process. In this context, this paper presents results to demonstrate the possibility of using pattern recognition capabilities offered by a multilayer neural network to recognize 3-d PD patterns     

局部放电识别中分维数分布的研究

本文将分形理论应用于局部放电模式识别 ,从统计图谱中提取分形特征。在局部放电模式试验基础上 ,采用计盒数的分形维数算法 ,从大量的局部放电样本中提取分形网格维数特征参数 ,提高了局部放电模式的准确性。     

基于时频分析与分形理论的GIS局部放电模式识别特征提取方法

识别局部放电(PD)的缺陷类型是评估电气设备绝缘状况的一项重要指标,通过特高频传感器(UHF)可获取局部放电信号。然而,传统的基于统计参数的信号特征提取方法存在高维数和无效信息过多的缺点,该文提出了一种基于时频分析和分形理论的气体绝缘组合电气(GIS)局部放电模式识别特征提取方法。首先利用小波变换对局部放电信号获取能量的时频分布图;然后运用差分盒计数法(DBC)对能量分布图进行分形维数的特征提取,并采用线性判别分析(LDA)对特征向量进行降维处理;最后利用支持向量机(SVM)对局部放电缺陷类型进行分类。为验证所提出算法的有效性,在实验室252 kV GIS局部放电仿真实验平台的模型气室内设置了尖端放电、自由微粒放电、沿面放电和悬浮电极放电4种典型缺陷类型,由特高频传感器采集各类缺陷的局部放电信号,后由该文算法进行分类。实验结果表明,采用该文所提特征提取方法对4种典型缺陷类型的识别准确率超过96%,显著优于传统的基于统计参数的信号特征提取方法。     

基于小波与分形理论的电力设备局部放电类型识别

根据小波理论建立了表征局部放电脉冲信号的三维时频谱图,该三维谱图综合反映了局放脉冲信号的3个基本特征:时间分量、频率分量和放电能量的分布。采用了分形理论从所建立的三维时频谱图中提取放电特征,并构成识别特征量,采用误差反传神经网络对局部放电信号的类型进行模式识别。试验结果表明,该方法可有效区分局部放电的类型。     

基于GLCM和LBP的局部放电灰度图像特征提取

针对变压器局部放电模式识别中传统统计谱图特征提取维数高、识别率差等问题,提出基于灰度共生矩阵和局部二值模式的局部放电灰度图像纹理特征提取方法。该方法从宏观角度将灰度图像转化为灰度共生矩阵并获取其8维特征,从微观角度计算邻域像素相对灰度响应并获取其10维特征量。搭建四种局部放电实验模型,通过脉冲电流法采集局部放电信号;结合两类特征,以支持向量机作为分类器来识别放电类型并用传统特征提取方法作为对比。结果表明利用该方法提取灰度图像特征在避免特征灾难的同时仍有较高识别率,能有效识别四种放电模型,验证了该方法的有效性。     

小波与分形理论的互补性及其在局部放电模式识别中的应用研究

研究应用于电气设备局部放电模式识别及故障诊断的放电特征量提取方法,是电气设备状态维护技术研究中的难题之一。该文从尺度变换的角度,研究了小波与分形理论的互补性;并从局部放电信号小波分解后的能量谱图提取放电特征,用于局部放电模式识别。研究结果表明：选用适当的小波函数和尺度函数,将局部放电信号的逼近信号能量谱和精细的结构能量谱的分形维数作为局部放电模式特征,能够有效地应用于局部放电模式识别中。该项研究结果具有较高的理论和应用价值。     

基于灰度图像分形特征的局部放电模式识别

提出了用灰度图像分维数作为局部放电识别特征量的识别方法,并采用Elman神经网络对变压器局部放电模式进行了识别。     

Fractal image compression for classification of PD sources

The fractal image compression technique has a unique feature due to which physical position of blocks/regions in the input image can be extracted directly from the compressed data. Applying this technique, φ-q-n partial discharge (PD) patterns (treated as an image) are compressed and stored as affine transformations. These transformations then are used directly to extract the embedded pattern features, which are classified by a neural network. The novel route to PD pattern classification described in this paper thus addresses both the tasks of compression and feature extraction in a single step. The task of compression is essential to store and handle large quantities of pattern data acquired, especially during on-line monitoring of PD in power apparatus. Results presented illustrate that this approach can address satisfactorily the tasks of compression and classification of PD patterns     

Fractal analysis of electrical trees

Recently, fractal characteristics in pattern formation have been attracting much attention. A number of books and papers have been published on the fractal analysis of random patterns or structures occurring in nature. The geometrical patterns of dielectric breakdown, which include lightning, surface discharges and electrical trees, are known to be of a fractal nature. Their fractal patterns can be analyzed numerically using fractal dimensions. In this paper, a survey of the fractal analysis of electrical trees, both in experiment and in computer simulation, is given. Several methods for estimating the fractal dimension are summarized. The stochastic models for discharge patterns based on computer simulation are also summarized. Fractal analysis of real electrical trees in polymeric insulating materials is reviewed. For the experimental tree patterns, the fractal analysis of the projected 2-D and the reconstructed 3-D patterns is presented     

Use of a mixed-Weibull distribution for the identification of PDphenomena [rotating machines]

The interaction between partial discharge (PD) phenomena occurring in insulating systems is investigated in this paper. In particular, the recognition of two PD phenomena simultaneously active is approached by means of a five-parameter additive Weibull distribution. Various shapes of the PD height distribution, obtained from measurements performed on specimens of stator bars and windings of ac rotating machines, are considered. It is shown that the proposed probability function fits well the partial discharge height distributions. The probability distribution relevant to each concurring PD phenomenon can be derived, analysed and identified. Moreover, the standard average quantities are estimated for each phenomenon