Partial discharge pattern recognition of power cable joints using extension method with fractal feature enhancement

This paper proposes a new partial discharge (PD) pattern recognition using the extension method with fractal feature enhancement. First, four common defect types of XLPE power cable joints are established, and a commercial PD detector is used to measure the PD signal by inductive sensor (L-sensor). Next, the feature parameters of fractal theory (fractal dimension and lacunarity) are extracted from the 3D PD patterns. Finally, the matter-element models of the PD defect types are built. The PD defect types can be directly identified by the degree of correlation between the tested pattern and the matter-element based on the extension method. The extension method needs representative features to define the interval of the matter-element. In order to enhance the extension performance, we add fractal features that are extracted from the PD 3D patterns. To demonstrate the effectiveness of the extension method with fractal feature enhancement, the identification ability is investigated on 120 sets of field-tested PD patterns of XLPE power cable joints. Compared with the back-propagation neural network (BPNN) method, the results show that the extension method with fractal feature enhancement not only has high recognition accuracy and good tolerance when random noise is added, but that it also provides fast recognition speed.     

局部放电故障神经网络模式识别及实验研究

阐述了局部放电信号模式识别对高压电器故障诊断的意义。用理想的同轴电极系统放电模型模拟了两种放电模式。将统计数学应用于局部放电信号特征量的提取 ,得到的特征向量 (放电量不对称性Q、相位不对称性Φ、相关系数cc)作为BP神经网络的输入 ,以此对局部放电信号进行模式识别。实验证明这种方法具有很高的识别率。     

Artificial recognition system for defective types of transformers by acoustic emission

An artificial recognition system of defective types for epoxy-resin transformers through acoustic emission (AE) from partial discharge (PD) experiment is proposed. PD detection is an efficient diagnosis method to prevent the failure of electric equipments arising from degrading insulation. However, most of the PD detection methods could be performed only at the shutdown period of equipments. By using AE, the online and real-time detection with defective types could be easily reached. Therefore, in this paper a series of high voltage tests were conducted on pre-faulty transformers to collect the AE signals for recognition system needed. The selected AE features instead of waveform are then extracted from these experimental AE signals for the input characteristic of recognition system. According to these features, effective identification of their defective types can be done using the proposed recognition system that combined particle swarm optimization with an artificial neural network. To demonstrate the effectiveness and feasibility of the proposed approach, the artificial recognition system is applied on both noisy and noiseless circumstances. The experiment showed encouraging results that even with 30% noise per discharge count, an 80% successful recognition rate can still be achieved.     

基于图像处理及降噪的局部放电图谱智能识别方法

局部放电检测是目前电力设备状态评价的主要手段,得到广泛应用推广。由于缺陷图谱的复杂性及现场干扰的多样性,传统的局部放电模式识别方法正确率低,训练时间长。针对上述问题,本文提出了一种基于图像处理技术及数据深度稀疏降噪的电力设备局部放电图谱智能识别方法。首先,运用图像处理技术对检测得到的图谱进行预处理;然后利用深度稀疏降噪自编码器进行数据稀疏降噪;最后对得到的有效去噪的数学模型,利用极限学习机(Extreme Learning Machine, ELM)网络,实现对局部放电的智能分类和识别。利用在变电站现场实测数据对本方法进行验证,证明本方法对含有多样干扰的局部放电信号有更好的识别效果,能很好适用于目前的电力设备图像信息模式识别应用当中。     

Conception of complex probabilistic neural network system for classification of partial discharge patterns using multifarious inputs

Pattern recognition has a long history within electrical engineering but has recently become much more widespread as the automated capture of signal and images has been cheaper. Very many of the application of neural networks are to classification, and so are within the field of pattern recognition and classification. In this paper, we explore how probabilistic neural networks fit into the earlier framework of pattern recognition of partial discharge patterns since the PD patterns are an important tool for diagnosis of HV insulation systems. Skilled humans can identify the possible insulation defects in various representations of partial discharge (PD) data. One of the most widely used representation is phase resolved PD (PRPD) patterns. Also this paper describes a method for the automated recognition of PRPD patterns using a novel complex probabilistic neural network system for the actual classification task. The efficacy of composite neural network developed using probabilistic neural network is examined.     

GIS局部放电信号的联合时频分析

该文通过EMIP—ATP仿真软件，模拟计算了GIS局部放电信号在一个线路间档上的传播情况，为实际GIS局部放电的检测和定位提供了一个理论依据。并把联合时频分析方法应用到GIS局部放电信号的分析与处理上，取得了良好的效果。     

Improved pattern recognition with complex artificial immune system

In this paper, we introduce the application of transformation pattern recognition based on a complex artificial immune system. The key feature of the complex artificial immune system is the introduction of complex data representation. We use complex numbers as the data representation instead of binary numbers used before, besides the weight between different layers. The complex partial autocorrelation coefficients of input antigen which are considered as the antigen presentation are calculated in major histocompatibility complex (MHC) layer of the complex artificial immune system. In the simulations, the transformation of patterns, such as translation, scale or rotation, are recognized in much higher accuracy, and it has obviously higher noise tolerance ability than traditional real artificial immune system and even the complex PARCOR model.     

基于LSTM神经网络的管道缺陷模式识别方法研究

针对复杂环境下,管道振动信号特征微弱难以提取的问题,提出一种基于长短时记忆网络(LSTM)深度学习神经网络的管道缺陷模式识别方法;首先利用改进型自适应噪声的完全集合经验模态分解(ICEEMDAN)对采集的原始信号进行分解得到若干个固有模态函数(IMF)分量,随后根据信息熵理论计算IMF分量的近似熵作为管道典型状态的特征值构造特征向量集合,然后构造LSTM深度学习神经网络训练模型并调节深度神经网络在训练过程中的相关参数进行网络的结构优化,最后将特征向量输入到LSTM神经网络模型进行训练和识别;结果表明:针对管道振动信号特征微弱难以提取的问题,该方法对管道缺陷模式识别的准确率达到了95％,在消除管道振动信号的背景噪声、挖掘特征信息和保证识别准确性方面优势明显.     

GIS设备局部放电特高频信号线性判别分析识别研究

局部放电测量是监测绝缘系统缺陷的典型非破坏性实验方法,提出了一种基于局部放电特高频(UHF)信号的多尺度特征提取能量参数和线性判别分析的识别方法,设计了4种绝缘缺陷模型模拟气体绝缘开关(GIS)设备局部放电现象。对局部放电UHF信号进行小波包多尺度变换,提取出UHF信号的16维能量参数;又对局部放电UHF信号进行了线性判别分析的设计,在局部放电信号特征量中随机选取30组进行10次采样;对其训练分类器的UHF局部放电信号进行模式识别,得到10个相关结果;试验获得最终的30组训练样本正确率平均值较高。研究结果表明线性判别分类器能够有效地将4种局部放电模型分开。     

基于改进深度残差网络的GIS局部放电在线监测白噪声干扰抑制

针对GIS局部放电(partial discharge, PD)监测中背景白噪声较多、GIS局部放电信号干扰较大的问题,应用改进深度残差网络设计一种新的GIS局部放电在线监测白噪声干扰抑制方法。进行局部放电在线监测中白噪声、局部放电脉冲信号的多尺度特性分析,在局部放电脉冲染噪信号中提取白噪声信号。加入感知损失,设计由生成图像网络与损失网络构成的改进深度残差网络,对白噪声信号波形图像实施超分辨率重建。通过SN-EMD算法提取白噪声信号波形图像的模态域特征。通过构建复小波滤波器组,对模态域特征实施滤波处理,实现GIS局部放电在线监测中的白噪声干扰抑制。实验测试结果表明,设计方法去噪后的信噪比最高可达97.22 dB,干扰抑制前后信号的幅值相对误差最高可达63.20 dB,干扰抑制前后信号相关系数一直大于0.75,完成GIS局部放电在线监测白噪声干扰抑制。     

Evolutionary model selection in a wavelet-based support vector machine for automated seizure detection

Support vector machines (SVM) have in recent years been gainfully used in various pattern recognition applications. Based on statistical learning theory, this paradigm promises strong robustness to noise and generalization to unseen data. As in any classification technique, appropriate choice of the kernels and input features play an important role in SVM performance. In this study, an evolutionary scheme searches for optimal kernel types and parameters for automated seizure detection. We consider the Lyapunov exponent, fractal dimension and wavelet entropy for possible feature extraction. The classification accuracy of this approach is examined by applying the MIT (Massachusetts Institute of Technology) dataset and comparing results with the SVM. The MIT-BIH dataset has the electrocardiographic (ECG) changes in patients with partial epilepsy which two types ECG beats (partial epilepsy and normal). A comparison of results shows that performance of the evolutionary scheme outweighs that of support vector machine. In the best condition, the accuracy rate of the proposed approaches reaches 100% for specificity and 96.29% for sensitivity.     

Pattern recognition in a compartmental model of a CA1 pyramidal neuron.

Computer simulation of a CA1 hippocampal pyramidal neuron is used to estimate the effects of synaptic and spatio-temporal noise on such a cell's ability to accurately calculate the weighted sum of its inputs, presented in the form of transient patterns of activity. Comparison is made between the pattern recognition capability of the cell in the presence of this noise and that of a noise-free computing unit in an artificial neural network model of a heteroassociative memory. Spatio-temporal noise due to the spatial distribution of synaptic input and quantal variance at each synapse degrade the accuracy of signal integration and consequently reduce pattern recognition performance in the cell. It is shown here that a certain degree of asynchrony in action potential arrival at different synapses, however, can improve signal integration. Signal amplification by voltage-dependent conductances in the dendrites, provided by synaptic NMDA receptors, and sodium and calcium ion channels, also improves integration and pattern recognition. While the biological sources of noise are significant when few patterns are stored in the associative memory of which the cell is a part, when large numbers of patterns are stored the noise from the other stored patterns comes to dominate the pattern recognition process. In this situation, the pattern recognition performance of the pyramidal cell is within a factor of two of that of the computing unit in the artificial neural network model.     

Robust Heteroscedastic Probabilistic Neural Network for multiple source partial discharge pattern recognition – Significance of outliers on classification capability

Among various insulation diagnostic techniques utilized by researchers and personnel handling power equipment, partial discharge (PD) recognition and analysis has emerged as a vital methodology since it is inherently a non-intrusive testing strategy. Of late, the focus of researchers has shifted to the identification and classification of multiple sources of PD since it is most often encountered in practical insulation systems of power apparatus. Researchers have carried out studies to recognize multi-source PD and expounded the difficulties experienced in discriminating such discharge patterns. It has also been observed that identification of such patterns becomes increasingly difficult with the degree of overlap. Review of recent research studies indicates that classification of fully overlapped patterns is yet an unresolved issue and that techniques such as Mixed Weibull Functions, neural networks (NN) and Wavelet Transformation have been attempted with reasonable degree of success for single source and partially overlapped PD patterns only.This research study focuses on extending the previous work attempted by the authors in utilizing the novel approach of Heteroscedastic Probabilistic Neural Network (HRPNN) for classification of single source PD patterns to that of multiple PD sources also. Further, a Robust Heteroscedastic Probabilistic Neural Network (RHRPNN) is implemented for the classification of multi-source PD patterns. The RHRPNN utilizes the jackknife procedure for handling problems associated with training the neural network due to the presence of outliers, thus providing a compact yet effective set of centers in terms of probability density functions. In addition to the previously utilized traditional statistical operators in the pre-processing phase, a Two Pass Split Window (TPSW) scheme has also been developed to study and compare the classification capability of the RHRPNN with that of HRPNN. Detailed analysis of the performance of RHRPNN is carried out to ascertain the influence of the smoothing parameter in classifying PD patterns, to determine the role played by the pre-processing techniques during classification and to find the significance of the parsimonious set of centers in eliminating the effect of outliers during classification. Finally, the ability of the HRPNN and the RHRPNN in classifying large dataset multiple source PD patterns obtained from varying applied voltages is analyzed for its further applicability in real-time PD pattern recognition studies.     

形状的全尺度可视化表示与识别

目的视觉目标的形状特征表示和识别是图像领域中的重要问题。在实际应用中,视角、形变、遮挡和噪声等干扰因素造成识别精度较低,且大数据场景需要算法具有较高的学习效率。针对这些问题,本文提出一种全尺度可视化形状表示方法。方法在尺度空间的所有尺度上对形状轮廓提取形状的不变量特征,获得形状的全尺度特征。将获得的全部特征紧凑地表示为单幅彩色图像,得到形状特征的可视化表示。将表示形状特征的彩色图像输入双路卷积网络模型,完成形状分类和检索任务。结果通过对原始形状加入旋转、遮挡和噪声等不同干扰的定性实验,验证了本文方法具有旋转和缩放不变性,以及对铰接变换、遮挡和噪声等干扰的鲁棒性。在通用数据集上进行形状分类和形状检索的定量实验,所得准确率在不同数据集上均超过对比算法。在MPEG-7数据集上精度达到99.57%,对比算法的最好结果为98.84%。在铰接和射影变换数据集上皆达到100%的识别精度,而对比算法的最好结果分别为89.75%和95%。结论本文提出的全尺度可视化形状表示方法,通过一幅彩色图像紧凑地表达了全部形状信息。通过卷积模型既学习了轮廓点间的形状特征关系,又学习了不同尺度间的形状特征关系。本文方法...     

基于注意力机制学习的变电设备缺陷检测方法

针对现有的变电站缺陷图像检测识别算法鲁棒性弱问题,提出一种基于注意力机制学习的变电设备缺陷图像检测识别方法。所提方法以卷积神经网络作为缺陷图像特征提取的骨架网络,融合注意力机制原理,进一步提升缺陷图像特征的可辨识性。首先,构建注意力机制的卷积神经网络特征提取模型,提取不同注意力机制下变电站缺陷图像特征;其次,设计一种自适应特征学习函数,将不同注意力机制下的特征融合成为新的高质量变电缺陷图像特征;最后,将不同注意力机制下的缺陷图像特征输入到分类模型,实现变电站缺陷图像检测。所提方法增强了变电设备缺陷图像检测的准确性与鲁棒性,实验结果显示,所提方法的mAP达到了70.4%。     

Translation, rotation, and scale invariant pattern recognition byhigh-order neural networks and moment classifiers

The classification and recognition of two-dimensional patterns independently of their position, orientation, and size by using high-order networks are discussed. A method is introduced for reducing and controlling the number of weights of a third-order network used for invariant pattern recognition. The method leads to economical networks that exhibit high recognition rates for translated, rotated, and scaled, as well as locally distorted, patterns. The performance of these networks at recognizing types and handwritten numerals independently of their position, size, and orientation is compared with and found superior to the performance of a layered feedforward network to which image features extracted by the method of moments are presented as input.     

基于听皮层神经元感受野的强噪声环境下说话人识别

针对说话人识别易受环境噪声影响的问题,借鉴生物听皮层神经元频谱-时间感受野（STRF）的时空滤波机制,提出一种新的声纹特征提取方法。在该方法中,对基于STRF获得的听觉尺度-速率图进行了二次特征提取,并与传统梅尔倒谱系数（MFCC）进行组合,获得了对环境噪声具有强容忍的声纹特征。采用支持向量机（SVM）作为分类器,对不同信噪比（SNR）语音数据进行测试的结果表明,基于STRF的特征对噪声的鲁棒性普遍高于MFCC系数,但识别正确率较低;组合特征提升了语音识别的正确率,同时对环境噪声具有良好的鲁棒性。该结果说明所提方法在强噪声环境下说话人识别上是有效的。     

基于融合特征与支持向量机的控制图模式识别

为了提高控制图模式识别的精度, 将控制图模式的原始特征与形状特征相融合得到分类特征, 并采用支持向量机进行模式分类的控制图模式识别。融合所得特征既保持了控制图模式的原始特征所蕴涵的模式全局特性信息, 又通过引入形状特征对部分易混淆模式的局部几何特性进行强化, 使不同模式间的区分度得到有效提高; 而以支持向量机作为模式分类器保证方法在高维度特征和小样本条件下也能获得较好的识别性能。仿真实验结果表明所提方法的识别精度相比其他几种基于形状特征的控制图模式识别方法有明显提高。     

基于听皮层神经元感受野的强噪声环境下说话人识别

针对说话人识别易受环境噪声影响的问题，借鉴生物听皮层神经元频谱-时间感受野（STRF）的时空滤波机制，提出一种新的声纹特征提取方法。在该方法中，对基于STRF获得的听觉尺度-速率图进行了二次特征提取，并与传统梅尔倒谱系数（MFCC）进行组合，获得了对环境噪声具有强容忍的声纹特征。采用支持向量机（SVM）作为分类器，对不同信噪比（SNR）语音数据进行测试的结果表明，基于STRF的特征对噪声的鲁棒性普遍高于MFCC系数，但识别正确率较低；组合特征提升了语音识别的正确率，同时对环境噪声具有良好的鲁棒性。该结果说明所提方法在强噪声环境下说话人识别上是有效的。