基于多标签随机森林的电能质量复合扰动分类方法

提出一种多标签随机森林(Multi-label Random Forest, ML-RF)分类算法,并将其应用于电能质量复合扰动分类。ML-RF是基于多标签决策树(Multi-label Decision Tree, ML-DT)的集成学习算法,利用子决策树的组合来增强分类器的整体性能。首先对电能质量扰动信号进行平稳小波变换,计算各层分解系数的小波能量熵作为分类特征向量。然后使用Bootstrap自助法和子空间采样构造不同的训练集训练子决策树。最后组合子决策树得到ML-RF分类器,并对复合电能质量扰动进行分类。仿真结果表明,在不同噪声情况下,该方法均能有效进行复合扰动的分类,具有较好的噪声鲁棒性,是复合电能质量扰动分类的一种可行方法。     

基于小波分解和数据挖掘中决策树算法的电能质量扰动识别方法

针对短时电能质量变化和暂态扰动现象的不同特点,提出了一种基于小波分解和数据挖掘中决策树算法的电能质量扰动(power quality disturbance,PQD)识别方法。建立了正弦信号和6 种常见PQD 信号的数学模型,通过小波分解得到了上述信号的特征量,结合决策树方法实现了对PQD 的自动分类,并通过合理选择小波类型、分类算法和去噪方法提高了PQD 的分类精度。实验结果验证了该识别方法的准确性和高效性。     

基于自适应不完全S变换与LOO-KELM算法的复合电能质量扰动识别

针对电能质量复合扰动识别中特征提取效率低、分类器识别能力与学习速度无法同步提高的问题,提出一种基于自适应窗不完全S变换与留一交叉验证优化的核极限学习机(LOO-KELM)算法的复合电能质量扰动识别方法。首先根据选定的主频率点自适应调节S变换窗宽系数,提取具有高时频分辨率的59种电能质量(PQ)特征,再通过留一交叉验证寻找最小预测残差平方和,实现核极限学习机的输出权重优化,最后根据提取PQ特征集与优化后的核极限学习机实现复合扰动的识别与分类。仿真和实测结果表明,所提方法对不同噪声下的16类混合电能质量扰动均具有较高的分类精度,相较于现有复合电能质量识别方法,分类精度更高且训练时间更短。     

基于改进HHT和决策树的电能质量扰动辨识

为了准确辨识电能质量扰动的类型,以实现电能质量问题的有效治理,提出一种基于改进希尔伯特-黄变换(Hilbert-Huang transform,HHT)和决策树的电能质量扰动辨识方法。该方法先采用改进的基于斜率的方法(improved slope based method,ISBM)抑制希尔伯特-黄变换算法的端点效应,然后利用改进的HHT方法进行电能质量扰动信号的分析;从得到的瞬时频率曲线中提取频率成分、扰动持续时间和扰动持续期间频率3个特征量,并从瞬时幅值曲线中获取扰动期间电压幅值;最后构建分类决策树,将这4个特征量作为判断依据,实现扰动信号的分类和识别。根据各类电能质量扰动信号的数学模型,产生大量的测试样本进行仿真测试,结果证明了该方法的有效性和准确性,并且与现有的2种扰动辨识方法进行对比,结果表明该方法具有更高的识别准确率,能准确辨识出电能质量扰动的类型。     

电能质量复合扰动特征选择与最优决策树构建

针对电能质量(power quality,PQ)复合扰动识别中缺少特征选择与最优决策树自动构建方法的不足,提出采用分类回归树的PQ特征选择与最优决策树构建方法。首先,通过S变换提取64种PQ特征,构成原始特征集;然后,采用嵌入式特征选择方法,获取特征Gini重要度及排序,确定最优特征子集;最后,应用1-标准误差规则子树评估法,进行代价复杂度剪枝,获得最优分类树。实验证明,新方法能够根据训练集自动构建最优决策树,并实现最优特征选择;最优决策树可准确识别不同噪声环境下,含多种复合扰动的PQ信号,分类准确率高于概率神经网络和支持向量机方法,具有良好的鲁棒性与抗噪性。     

基于量子行为粒子群优化-人工神经网络的电能质量扰动识别

提出一种基于量子行为粒子群优化(quantum-behaved particle swarm optimization, QPSO)的改进算法,用于优化人工神经网络(artificial neural network, ANN),实现电能质量(power quality, PQ)扰动识别。采用2个神经子网络,分别用于事件型和变化型PQ扰动识别。PQ扰动信号的特征量通过信号的投影分析、动态测度计算、分形技术获取,作为2个子网络的输入量。改进的QPSO算法主要增加了学习因子、粒子聚集度和进化速度等参数,改进了QPSO算法的参数迭代更新过程,从而优化了神经子网络的训练结果。6种典型现场采集的PQ扰动数据识别结果表明,与加入动量因子的前馈式神经网络的训练方法相比,该算法具有更好的收敛性和稳定性。     

DG并网对暂态电压扰动方向判定的影响及其校正算法

计及新能源分布式电源(DG)并网对智能配电网的影响,构建了一种含DG配电网的可延展通用模型。基于模型结构等效变换,分析了引起电能质量监测仪方向误判的影响因素,针对电压暂降型或电压暂升型的电能质量(PQ)扰动源,提出了DG并网对PQ扰动方向判定的影响规律,进而提出了一种基于规律校正的PQ扰动方向判定算法。将多个DG接入IEEE 13和IEEE 34模型,Matlab仿真表明,该算法能提高PQ扰动方向判定的准确率,并具有简明清晰、抗噪声能力强等优点。     

基于深度置信网络的电能质量扰动检测与分类

为准确识别各类电能质量扰动,提出一种新型的、基于深度置信网络(deep belief network, DBN)的电能质量(power quality, PQ)扰动检测和分类方法。该方法为纯数据驱动方法,通过使用DBN对数据样本进行深度学习,从而形成稳定模型用于检测与分类。为了获得足够的样本进行训练,搭建1个周期内的PQ扰动数学模型,进行数据采集;然后对DBN的结构及参数进行设计和选取。为验证该方法的有效性,使用训练好的DBN对常见的PQ扰动信号进行检测和分类,并与现有的常规检测分类方法进行比较。对比仿真结果表明,与现有的检测分类方法相比,该方法具有更高的精度和较强的鲁棒性。     

基于广义S变换的短时电能质量扰动信号分类

提出一种基于广义S变换的短时电能质量扰动信号分类方法。首先对短时电能质量扰动信号进行广义S变换,得到模矩阵,再从模时频矩阵中提取5种统计量特征值,然后利用决策树对扰动信号进行归类,从而实现对短时电能质量扰动信号的自动分类。仿真结果表明,该方法识别正确率高,且对噪声不敏感,适用于实际电网电能质量扰动信号的分析。     

基于生长-修剪优化RBF神经网络的电能质量扰动分类

针对电能质量扰动分类算法中径向基函数(radial basis function,RBF)神经网络隐层神经元的中心点数量、中心点位置、宽度、输出权值的设置问题,提出一种基于网络生长-修剪算法(GAP)的RBF神经网络电能质量扰动分类算法。首先,建立电能质量扰动模型,采用GAP算法实现对RBF神经网络的结构参数优化,设计相应的电能质量扰动分类算法流程图;其次,利用广义S变换、特征值提取、GAP-RBF神经网络对8种电能质量扰动进行处理。通过仿真分析,验证GAP-RBF神经网络对隐层神经元的参数优化能力,并给出优化算法的参数设定范围;仿真和实验结果表明,与同类算法相比,所提算法在保证分类准确度的前提下减少了隐层神经元的数量,且实现了RBF神经网络的参数自优化和继承式学习。     

基于双尺度分形盒维数的电能质量扰动信号识别

提出一种电能质量PQ(Power Quality)扰动信号时域分析方法。在PQ扰动信号分析中,分形维数用来描述信号的不规则性和复杂度。由于引起各种PQ扰动的来源不同,致使扰动信号在不规则性和复杂度上体现出差异,为PQ扰动信号分析提供依据。平面离散信号的传统分形盒维数计算通常基于正方形盒,而对于PQ扰动信号,时间和幅值是完全不同的物理概念,采用基于时间和幅值的双尺度长方形盒对PQ扰动信号计算盒维数,根据PQ扰动信号的周期或准周期特性推导无标度区的长方形盒尺度确定经验公式,并通过具体波形简单验证。典型的PQ扰动信号分析的结果表明,其描述的特征量明显,可以识别扰动。盒维数的简单统计结果可以作为PQ神经网络分类器的输入特征量。     

一种简单的电能质量扰动信号检测方法

提出了一种简单的电能质量扰动检测方法,用于判断采集信号中是否存在电能质量扰动,作为扰动分类的前提。该方法利用当前周期的电压信号与前一个周期信号之间的差值信号来进行电压凹陷、电压凸起及暂态振荡、暂态脉冲等暂态电能质量问题检测,利用差分信号和滤波后低频和高频信号的能量比来检测稳态电能质量问题。该方法实现简单,计算量小,检测全面,可以实时、在线完成,弥补了以往采用小波或小波包变换方法复杂费时以及准测不全面的不足,也弥补了单独采用差值信号方法无法检测稳态电能质量问题的缺陷。仿真和试验结果表明了本文提出方法的可行性和有效性。     

基于小波变换能量分布和神经网络的电能质量扰动分类

提出了基于小波变换能量分布和BP神经网络的电能质量扰动的自动分类方法.利用小波变换对电能质量扰动信号进行多分辨分析,计算各分解层能量分布,求出该能量分布与标准信号能量分布差值并将其作为信号特征量,通过一个3层BP网络得到扰动的类型.该方法将小波变换系数转化为能量分布,减少信号特征的数量,从而简化了神经网络结构.测试结果表明,即使在较强噪声信号背景下,该方法对电能质量扰动类型的识别率仍可达到94.5%,证明了该方法的有效性.     

An effective wavelet-based feature extraction method for classification of power quality disturbance signals

This paper presents a wavelet norm entropy-based effective feature extraction method for power quality (PQ) disturbance classification problem. The disturbance classification schema is performed with wavelet-neural network (WNN). It performs a feature extraction and a classification algorithm composed of a wavelet feature extractor based on norm entropy and a classifier based on a multi-layer perceptron. The PQ signals used in this study are seven types. The performance of this classifier is evaluated by using total 2800 PQ disturbance signals which are generated the based model. The classification performance of different wavelet family for the proposed algorithm is tested. Sensitivity of WNN under different noise conditions which are different levels of noises with the signal to noise ratio is investigated. The rate of average correct classification is about 92.5% for the different PQ disturbance signals under noise conditions.     

A real-time classification method of power quality disturbances

This paper describes a real-time classification method of power quality (PQ) disturbances. With an acceptable computation burden, both the elementary parameters of the power signal and the types of the disturbances in the power signal are obtained easily. The proposed method addresses the selection of discriminative features for detection and classification of PQ disturbances. Five distinguished time-frequency statistical features of PQ disturbances are extracted using RMS (root-mean-square) method and discrete Fourier transform (DFT). Using a rule-based decision tree (RBDT), the nine types of PQ disturbances can be recognized easily and there is no need to use other complicated classifiers. Finally, the proposed method is tested using the simulated waveforms. And some preliminary experimental results of the accuracy characterization of an initial development instrument are reported. The simulation and application results validate the accuracy and efficiency of the proposed method.     

基于S变换和多级SVM的电能质量扰动检测识别

提出了一种基于S变换和多级支持向量机(SVMs)的电能质量扰动检测和识别方法.首先通过S变换对电能质量扰动信号进行时频分析,有效实现对各种扰动的检测输出.然后对检测输出进行时频特征提取,并通过一个N?1级支持向量机器分类器,最后实现N种电能质量扰动信号的分类识别.测试结果表明,该方法能有效识别参数大范围内随机变化的各种电能质量扰动,识别正确率高,且训练时间很短,实时性能好.     

移相电能质量检测法的研究

电能质量检测是电能质量研究的一个重要组成部分,该文提出了一种移相电能质量检测方法。该检测方法原理简单、实时性好,可对电力系统最重要的几种电能质量扰动,包括谐波、电压凹陷、电压凸起、电压波动和暂态振荡,进行检测,且方法本身没有延时,可应用于电能质量实时检测和识别系统中。该文运用大量的仿真数据和某牵引变母线电压现场采样数据对检测有效性进行了验证。     

Fuzzy classifiers for power quality events analysis

The present paper proposes the design of a tool to quantify power quality (PQ) parameters using wavelets and fuzzy sets theory. The tool merges the best characteristics of these two theories in establishing a method to analyze PQ events. The proposed method addresses two issues, such as selection of discriminative features and classifies event classes with minimum error. Wavelet features (WF) of PQ events are extracted using wavelet transform (WT) and fuzzy classifiers classify events using these features. Often the captured signals are corrupted by noise. Also the non-linear and non-stationary behavior of PQ events make the detection and classification tasks more cumbersome. WT has been proven an effective tool for detecting and classifying these. We exploited WT for noise removal to make the task of detection and/or localization of events simpler. In the proposed approach of event classification, fuzzy product aggregation reasoning rule based method has been used. Varieties of PQ events including voltage sag, swell, momentary interruption, notch, oscillatory transient and spikes are considered for performance analysis. Comparative simulation studies revealed the superiority of proposed method compared to WF based fuzzy explicit, fuzzy k-nearest neighbor and fuzzy maximum likelihood classifiers under noisy environment.     

Classification of disturbances in hybrid DG system using modular PNN and SVM

This paper presents the classification of islanding and power quality (PQ) disturbances in grid-connected distributed generation (DG) based hybrid power system. The penetration of DG influences the PQ levels in the distribution networks. Islanding disturbances are separated out from the PQ disturbances based on the selection of suitable threshold value, at the initial stage of classification process. Further, the power quality disturbances are automatically classified into distinct classes based on feature extraction using S-transform followed by training of two classifiers, namely, modular probabilistic neural network (MPNN) and support vector machines (SVMs). Five different types of disturbances are considered for the classification problem. The study reveals that S-transform (ST) in association with MPNN and SVM can effectively detect and classify islanding and PQ disturbances. The proposed methodology uses features instead of real data set and thereby reduces the data size to classify disturbance signal without losing its original property. The accuracy and reliability of proposed classifier is also tested on signals contaminated with noise and PQ disturbances caused due to wind speed variation on an experimental prototype set-up.