运用模糊神经网络来区分变压器励磁涌流和内部故障

变压器励磁涌流和内部故障的鉴别一直是变压器差动保护中的一个热点问题在几种传统的识别励磁涌流方法的基础上,结合模糊神经网络这一新型的人工智能技术,综合利用这几种原理对电气量的采样值分别提取形成网络的特征输入量,并采用了Simpson模糊极小-极大神经网络来形成区分励磁涌流和内部故障的模糊模式分类器运用EMTP程序通过大量的仿真计算获取网络的训练和测试样本,结果表明,训练后的网络能快速地区分变压器各种运行工况下的励磁涌流和内部故障,对测试样本的正确率达到100%。     

基于波形记忆和模糊极小--极大神经网络的变压器励磁涌流和内部短路的鉴别

传统的区分变压器励磁涌流和内部短路的各种方法存在原理性缺陷，不能满足现代超高压电力系统的要求，此文根据内部故障和单纯涌流这两种情况下波形的不同，提出了波形记忆的原理并采用了一种模糊神经网络模型——模糊极小-极大神经网络来对这两种波形进行记忆和鉴别。运用EMTP程序对变压器各种内部故障或涌流的情况进行较为全面的仿真的以形成网络的训练样本，通过学习和测试，表明该网络所形成的新算法能够正确鉴别变压器各咱运行工况下的励磁涌流和内部短路，所需的鉴别时间小于20ms。     

基于人工神经网络的变压器励磁涌流的鉴别

研究了基于神经网络方法的电力变压器励磁涌流鉴别。对变压器励磁涌流及故障电流进行了数字仿真,比较了两者在物理特性上的区别。利用Matlab的人工工具箱,分别建立了BP和RBF神经网络模型,对励磁涌流和故障电流的样本进行训练及测试。结果表明,人工神经网络可以正确地区分励磁涌流和故障电流,RBF神经网络能更加快速、准确地判断出变压器的故障。     

电力变压器励磁涌流判别的自适应小波神经网络方法

励磁涌流识别一直是电力变压器差动保护中比较关注的问题。文中提出了一种基于自适应小波神经网络实现变压器励磁涌流判别的新方法。结合励磁涌流和内部故障电流的特点，构建了一个四层的自适应小波神经网络模型，并对其具体的实现方法进行了详细的分析；利用ATP—EMTP程序进行仿真计算生成训练样本和测试样本，对所构建的网络进行了训练和测试，结果表明自适应小波神经网络能准确、可靠地识别出变压器的励磁涌流状态。     

单相牵引变压器励磁涌流鉴别研究

利用BP神经网络区分了牵引变压器的励磁涌流和故障电流,并利用仿真数据和试验变压器录波样本对神经网络性能进行了测试。     

基于小波理论的变压器励磁涌流与故障电流的识别

变压器内部故障与励磁涌流一般都伴随着复杂的电磁暂态过程,普通的信号处理方法难以准确地区分这两种现象.文章利用小波理论对变压器的励磁涌流与内部故障电流的信号进行分析处理,根据小波变换结果之间差异性的显著特征来构成区分励磁涌流和内部故障电流的判据,以识别是否故障电流.     

基于小波包和改进BP神经网络的变压器励磁涌流识别方法

根据励磁涌流和内部故障电流的波形特征存在巨大差异,提出一种基于小波包和改进BP网络的识别励磁涌流的新算法。利用小波包对励磁涌流和故障电流信号进行分解和重构,提取小波包重构系数,计算各频段的能量并进行归一化处理,构造能量特征向量,作为BP网络的输入样本,进行训练和测试,提出保护判据。经过PSCAD/EMTDC和MATLAB软件对大量样本进行仿真验证,证明该方案能够快速准确地识别励磁涌流和内部故障电流。     

区分变压器励磁涌流和内部短路的

提出一种基于积分算法的波形对称原理,以区分电力变压器的励磁涌流和内部短路。该方法利用积分处理以提取变压器内部故障的短路电流的波形对称特征。在此基础上,给出了应用模糊集理论区分变压器的励磁涌流和内部短路的模糊数学模型和判据。EMTP仿真表明,该原理简单可靠,效果良好,具有实用价值。     

基于变压器功率因数对励磁涌流和内部故障电流的识别

针对变压器采用纵差动保护会受到励磁涌流的影响而误动作,以及励磁涌流和内部故障时的短路电流的区分问题,提出一种根据变压器两侧三相瞬时功率因数的变化关系来识别励磁涌流和内部故障的方法.该方法简单、便捷,从能量的角度进一步揭示了变压器励磁涌流与内部故障电流本质不同.     

基于小波-DHNN识别变压器励磁涌流

变压器主要采用纵联差动保护,如何防止因涌流造成的误动已成为关键性问题。对于该问题,提出一种基于小波-DHNN识别励磁涌流的新的研究方案。利用小波变换对采样信号进行分析,得出励磁涌流的小波系数较内部故障电流有非常明显的差异,并且畸变特点伴随整个衰减过程。分析后的信号通过离散型Hopfield网络测试与识别,从而区分励磁涌流和内部故障电流。通过PSCAD和MATLAB仿真软件进行建模仿真,结果表明,该方法能可靠的识别励磁涌流和内部故障电流,并且准确率高达100%。     

Power Transformer Differential Protection Based On Optimal Probabilistic Neural Network

In this paper, the optimal probabilistic neural network (PNN) is proposed as the core classifier to discriminate between the magnetizing inrush and the internal fault of a power transformer. The particle swarm optimization is used to obtain an optimal smoothing factor of PNN which is a crucial parameter for PNN. An algorithm has been developed around the theme of the conventional differential protection of the transformer. It makes use of the ratio of voltage-to-frequency and amplitude of differential current for the determination of operating condition of the transformer. The performance of the proposed heteroscedastic-type PNN is investigated with the conventional homoscedastic-type PNN, feedforward back propagation (FFBP) neural network, and the conventional harmonic restraint method. To evaluate the developed algorithm, relaying signals for various operating condition of the transformer, including internal and external faults, are obtained by modeling the transformer in PSCAD/EMTDC. The protection algorithm is implemented by using MATLAB.     

正序有功功率差作为变压器励磁涌流判据的研究

针对当前变压器保护由于励磁涌流判据存在的某些方面的不足而出现的误动率相对较高的问题,提出应用正序有功功率差作为鉴别励磁涌流和故障电流的方法。推导该方法的动作判别式,并运用电力系统故障分析理论对该方法在励磁涌流和内部故障时的动作特性进行详细的分析,同时用EMPT仿真证明了该方法的有效性。     

A Morphological Scheme for Inrush Identification in Transformer Protection

This paper presents a novel morphological scheme for the identification of transformer magnetizing inrush. The scheme decomposes a current signal into multiresolution levels based on synthesis and analysis operators of mathematical morphology. It is able to discriminate between inrush and internal fault currents even in the case of an inrush with a low second harmonic component and an internal fault current with a high second harmonic component. Simulation studies have been undertaken to evaluate the scheme based on a three-phase high-voltage power transformer operating under different conditions, which is simulated with an Alternative Transients Program. The testing results show that the proposed scheme is able to identify inrush currents reliably and provides an alternative solution for transformer differential protection.      

Fuzzy logic-based relaying for large power transformer protection

Power transformer protective relay should block the tripping during magnetizing inrush and rapidly operate the tripping during internal faults. The frequency environment of power system has been made more complicated and the quantity of 2nd frequency component in inrush state has been decreased because of the improvement of core steel. Then, traditional approaches will likely be maloperated in the case of magnetizing inrush with low second harmonic component and internal faults with high second harmonic component. This paper proposes a new relaying algorithm to enhance the fault detection sensitivities of conventional techniques by using a fuzzy logic approach. The proposed fuzzy-based relaying algorithm consists of flux-differential current derivative curve, harmonic restraint, and percentage differential characteristic curve. The proposed relaying was tested with relaying signals obtained from Salford EMTP simulation package and showed a fast and accurate trip operation.     

基于最小二乘矩阵束的励磁涌流识别方案

准确、快速地切除变压器故障直接影响电力系统能否持续安全稳定运行,励磁涌流的鉴别正是变压器保护中的重要一环。为了有效辨识励磁涌流与故障电流,避免变压器差动保护的不正确动作,利用变压器励磁涌流与短路故障电流频域信息的差异,提出了一种基于最小矩阵束算法的励磁涌流识别新方案,以变压器两侧的差动电流作为信号量,通过矩阵束算法分析采样信号中不同频率的分量,计算含衰减因数的电流能量信息熵识别励磁涌流。仿真试验证明了新判据具有原理清晰、抗干扰能力强等优点,能够正确区分励磁涌流和故障电流,为后续研究及工程应用提供借鉴和参考。     

神经网络理论在变压器故障诊断中的应用

把专家知识与神经网络计算相结合,用变压器原副边正序和负序电流分量的方向进行变压器的故障诊断,克服好传统的二次谐波制动特性劝保护在涌流伴随故障状态下的动作延时,能正确识别变压器的内部故障,励磁涌流、外部故障及空载合于内部故障等不同状态。用此原理构成的变压器保护动作时间最快可为半个周期,可适合于任意连接方式的双绕组变压器,且不受系统参数的影响,具有广泛的实用性和很强的容错能力,大量仿真结果证明了此方法     

Testing and performance of transformer differential relays

The phenomenon of transformer magnetizing inrush current has been discussed in many papers throughout the years. A brief review of magnetizing inrush is given to provide the basis of need for transient testing. Previous studies have shown that inrush currents contain harmonic components of the fundamental waveform. Conventional philosophy has been to utilize the second harmonic current to provide inhibited operation of differential relays because of its dominance. Manufacturers have used various designs regarding higher order harmonics. The use of second and third, as well as the inclusion of all harmonics, have been seen over the years. The relay considered in this article utilized the second harmonic current to provide restraint on magnetizing inrush. The reasons for this are discussed. The authors discuss relay transient testing, EMTP transient testing, factory transient tests, EMTP testing facility, transformer differential EMTP tests, and EMTP transformer modeling. Several case studies relating to transformer differential relays are then discussed     

跟踪式二次谐波涌流制动改进方法

针对二次谐波制动原理存在的问题,提出一种新的二次谐波制动原理。通过判断变压器的开关位置和差流大小来改变涌流闭锁二次谐波门槛值,在空载合闸和故障切除恢复电压的过程中监视变压器内部故障和励磁涌流,达到在不会拒动的情况下更准确地判断励磁涌流、防止保护误动的目的。该方法具有实时跟踪的功能,克服了单一定值不能实现可靠制动的缺点。验证表明新方法具有较高的可靠性和灵敏性,可以克服传统制动方法的缺点,实现对励磁涌流现象的可靠制动。