基于组合神经网络的输电线故障类型识别

准确的输电线路故障类型识别是实现故障测距的前提,文中在高压输电线路故障分析的基础上,构建了由Kohonen自组织特征映射神经网络模型和BP网络模型组合而成的类型识别网络模型,来实现输电线路的故障检测及故障类型识别。经理论分析和大量的EMTP仿真表明：此网络模型较单一网络模型,所需训练样本少,学习时间短,并且在各种故障模式下,均能可靠、准确实现输电线路故障类型的识别,不受故障过渡电阻、故障初始角、系统运行方式、故障点位置等因素的影响。     

基于组合神经网络的输电线故障类型识别

准确的输电线路故障类型识别是实现故障测距的前提 ,文中在高压输电线路故障分析的基础上 ,构建了由Kohonen自组织特征映射神经网络模型和BP网络模型组合而成的类型识别网络模型 ,来实现输电线路的故障检测及故障类型识别。经理论分析和大量的EMTP仿真表明 :此网络模型较单一网络模型 ,所需训练样本少 ,学习时间短 ,并且在各种故障模式下 ,均能可靠、准确实现输电线路故障类型的识别 ,不受故障过渡电阻、故障初始角、系统运行方式、故障点位置等因素的影响     

基于多判据神经网络的单相自适应重合闸的研究

提出了一种基于多判据神经网络的电力系统单相自适应重合闸优化方案,该方法能够正确进行瞬时故障和永久故障的区分.当瞬时性故障发生时,在短路点电弧熄灭后的恢复电压阶段,断开相各电气量的关系与永久性故障将有本质的不同.在详细分析断开相工频电气量的基础上,用滤波后的采样值通过预处理层构成3种判据,利用神经网络将它们的自适应赋予权值,最后得出正确的结果.经过大量的仿真试验,该方案获得了满意的效果.     

基于DWT-PNN的柔性直流输电系统故障检测方法

柔性直流输电系统故障极大地影响了电力系统的稳定性.现有输电线路故障检测方法存在阈值选取困难、对过渡电阻阻值变化敏感、检测时间长等问题.提出一种基于小波能量占比的使用概率型神经网络(PNN)进行故障类型检测与位置判别的方法.通过对不同故障类型下的母线和线路测量电压进行快速傅里叶分析得出暂态电压频率特性,再利用离散小波变换(DWT)求得不同尺度下的小波能量特性,通过大量的离线仿真数据对PNN进行训练,根据PNN的输出结果实现故障类型与故障位置的精确判定.在PSCAD/EMTDC仿真环境下搭建了四端柔性直流电网电磁暂态模型进行仿真验证,结果表明所提方法可以准确地对高阻接地故障的故障类型与位置判别进行检测,不受过渡电阻阻值影响.     

宽带无线Mesh在输电线路在线监测的应用研究

从智能输电线路在线监测业务及通信需求分析出发,结合无线Mesh通信技术特性。提出高可靠性无线Mesh系统建设方案及输电线路在线监测系统塔上供电方案,为宽带无线Mesh在输电线路在线监测中的应用提供参考。在输电线路在线监测应用中。通过具有多跳组网的高可靠性宽带无线Mesh技术,采用双链路备份方案实现高压输电线路的宽带无线网络覆盖,可有效提高输电线路无线网络健壮性,实时监控电力输电线路及杆塔运行状态。     

Signal analysis‐based fault classification and estimation of fault location of an unbalanced network using S‐transform and neural network

This paper demonstrates a technique for the diagnosis of the type of fault and the faulty phase on an overhead transmission line, followed by locating the particular fault on the affected phase. The power system network considered in this study is a three‐phase transmission line with unbalanced loading simulated in the PowerSim Toolbox of MATLAB. S‐transform is used to compute the energy components of the voltage signals of the three phases of the transmission line. These features are used as input vectors of a probabilistic neural network (PNN) for fault detection and classification. Detection of the faulty phase(s) is followed by estimation of fault location. The voltage signal of the affected phase is processed to generate the S‐matrix. The frequency components of the S‐matrices for different fault locations are used as input vectors for training a backpropagation neural network (BPNN). The results are obtained with satisfactory accuracy and speed. All the simulations have been done in MATLAB environment for different values of fault locations, fault resistances, and fault inception angles. The effect of noise on the simulated voltage signals has been investigated. The analysis has been further extended by implementing the proposed method in a modified version of IEEJ West 10 machine system model. © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

一种基于PMU的线路自适应故障测距算法

提出一种新的基于相量测量单元(PMU)的输电线路故障测距的自适应算法。该算法利用PMU装置获得高压线路两端的电压和电流相量,在线计算线路参数,解决了线路实际参数与电力局所提供参数的不同、线路参数在运行过程中的不确定性等问题。采用前置带通滤波器与全波傅氏算法相结合的滤波算法,提取相当精确的突变量基频分量,用于输电线路故障测距。大量的EMTP仿真计算结果和实际系统参数验证结果表明,该测距算法不受系统的运行方式、故障点过渡电阻、故障类型、故障距离等因素的影响,具有很高的测距精度。     

基于计算机和无线通信技术的高压输电线路工频接地在线监测系统

介绍一种新的监测高压输电线路工频接地的几何故障定位系统--BIM-100型在线监测系统.它将带有无线通信功能的突发电流监测器逐个安装在输电线路的杆塔上,并构成一个无线通信接力平台.当高压输电线路发生短路故障时,利用无线通信平台将短路发生的塔号和监测到的电流值,通过局域网传送到网络管理系统,同时通过手机短信息通知有关人员及时进行故障处理,实现了电力系统输电线路状态检修的目的.     

基于多尺度行波功率的T接线路故障识别方法

为提高T接输电线路故障识别算法的精确性与可靠性,提出了一种基于多尺度行波有功功率和概率神经网络的T接输电线路故障识别方法.基于S变换分别计算区内3个行波保护单元多频率下的初始行波平均有功功率,并以此组成T接输电线路故障特征向量样本集.建立概率神经网络故障识别模型,并利用T接线路故障特征样本集对其进行训练和测试,从而识别...     

一种基于暂态电流的故障测距方法

输电线路故障的准确测距对于维持电力系统稳定起到了非常重要的作用。文章以R－L输电线路模型为基础,提出了一种基于暂态电流信号的三相故障测距定位方法。该方法首先对发生电压凹陷时间内的三相电流信号滤除基频分量,再对处理后的电流信号进行绝对值修正,接着对该信号进行对数变换;最后根据对数变换后的数据求出斜率,再由斜率定位发生故障线缆距离。该方法计算量小,仿真实验表明定位故障距离精确度较高,具有应用及推广的前景。     

Positional protection of transmission systems using GlobalPositioning System

This paper presents a new technique for the protection of power transmission systems by using the Global Positioning System (GPS) and fault generated transients. In the scheme, the relay contains a fault transient detection system together with a communication unit, which is connected to the power line through the high voltage coupling capacitors of the CVT. Relays are installed at each busbar in a transmission network. These detect the fault generated high frequency voltage transient signals and record the time instant corresponding to when the initial travelling wave generated by the fault arrives at that busbar. The communication unit is used to transmit and receive coded digital signals of the local information to and from the associated relay(s) in the system. At each substation, the relays determine the location of the fault by comparing the GPS time stamps measured locally with those received from the adjacent substations. Extensive simulation studies presented in the paper demonstrate the feasibility of the scheme     

Design of an ANN tuned adaptive UPFC supplementary damping controller for power system dynamic performance enhancement

A supplementary damping controller for a unified power flow controller (UPFC) is designed for power system dynamic performance enhancement. To maintain a good damping characteristic over a wide range of operating conditions, the gains of the UPFC supplementary damping controller are adapted in real time, based on online measured transmission line loadings (active and reactive power flows). To speed up the online gain adaptation process, an artificial neural network is designed. A major feature for the proposed adaptive UPFC supplementary damping controller is that only physically measurable variables (active and reactive power flows over the transmission line) are employed as inputs to the adaptive controller. To demonstrate the effectiveness of the proposed adaptive UPFC supplementary damping controller, computer simulations are performed on a power system subject to a three-phase fault. It is concluded from the simulation results that the proposed adaptive UPFC supplementary damping controller can yield satisfactory dynamic responses over a wide range conditions. The electromechanical mode with an oscillation frequency around 0.78 Hz has been effectively damped by the proposed damping compensators.     

High speed transmission system directional protection using anElman network

Detection of the direction of a fault on a transmission line is essential to the proper performance of a power system. It would be desirable to develop a high speed and accurate approach to determine the fault direction for different power system conditions. To classify forward and backward faults on a given line, a neural network's abilities in pattern recognition and classification could be considered as a solution. To demonstrate the applicability of this solution, neural network technique is employed and a novel Elman recurrent network is designed and trained. Details of the design procedure and the results of performance studies with the proposed network are given and analysed in the paper. System simulation studies show that the proposed approach is able to detect the direction of a fault on a transmission line rapidly and correctly. It is suitable to realize a very fast transmission line directional comparison protection scheme     

基于HHT小电流接地故障选线与在线故障定位方法

小电流接地系统发生单相接地故障,系统仍可运行1~2小时,要求在不断电的情况下,实现故障选线,并对故障进行定位。提出一种基于HHT小电流接地故障选线与在线故障定位的方法,利用奇异性检测法判断各线路在故障时刻的极性,实现故障选线,在线路参数未知的情况下,采用合闸时产生的操作过电压行波在线测量行波波速,单相接地故障发生后,利用HHT寻找电压行波瞬时频率突变时刻,并运用单端测距法实现对架空线、电缆和电缆-架空线混合线路故障定位。最后,对算例进行数值仿真,仿真结果验证了该方法的可行性和实用性。     

配电网接地选线方式的研究与探讨

在讨论零序电流法、谐波电流法、注波法和残差增量法选线的优缺点的基础上根据补偿电网的特点和要求提出了复合型选线方式 ,即利用现代计算机技术对配电网的运行状态进行信息融合 ,在线检测其零序电流、谐波、暂态电流 ,并综合分析 ,必要时增值谐波电流 ,以增大检测信号 ,提高选线准确率。     

Low cost microcontroller based fault detector,classifier, zone identifier and locator for transmission lines using wavelet transform and artificial neural network: A hardware co-simulation approach

A low cost, fast and reliable microcontroller based protection scheme using wavelet transform and artificial neural network has been proposed and its effectiveness evaluated in real time. The proposed scheme, based on the hardware co-simulation approach performs all the functions of transmission line protection i.e. fault detection/classification, fault zone/section identification and location estimation. The fault detection/classification and zone identification algorithms use fundamental frequency current component to estimate a fault index. The fault location estimation module uses wavelet transform coefficients in hybridization with a parallel artificial neural network structure. For hardware implementation, a 8-bit ATmega microcontroller is used and interfaced with the simulated power system model using Integrated Development Environment (IDE). The scheme is tested on a power system model of 400 kV, 50 Hz three phase double circuit line with source at both the ends. Laboratory tests have been performed in real time for 20,000 fault cases including evolving faults with varying fault resistance, fault inception angle, fault distance, direction of power flow angle and its magnitude. The tests confirm the suitability and reliability of proposed scheme even with Current Transformer (CT) saturation. The implementation of the proposed approach on a low cost microcontroller with the lesser execution time, makes the prototype ideal for implementation on a digital platform (digital relay), thus leading to financial viability and sustainability of the protection scheme.     

Bayesian networks-based approach for power systems fault diagnosis

In this paper, three element-oriented models based on simplified Bayesian networks with Noisy-Or and Noisy-And nodes are proposed to estimate the faulty section of a transmission power system. The three models are used to test if any transmission line, transformer, or busbar within a blackout area is faulty. They can deal with uncertain or incomplete data and knowledge relating to power system diagnosis, so they are flexible. The structures and initial parameters of the Bayesian networks depend on the prior knowledge of the domain experts. The parameters can be revised by using an error back propagation algorithm similar to the back-propagation algorithm for artificial neural networks. The fault diagnosis models do not vary with the change of the network structure, so they can be applied to any transmission power system. Furthermore, they have clear semantics, rapid reasoning, powerful error tolerance ability, and no convergence problem during the diagnosing procedure. Experimental tests show that the approach is feasible and efficient, so the prototype program based on the approach is promising to be used in a large transmission power system for online fault diagnosis.     

混合三端直流输电线路故障测距方法研究

对混合三端直流输电系统而言,准确、可靠的故障测距方法可确保故障线路快速恢复,提高供电可靠性。为了解决混合三端直流输电系统结构复杂性强、线路故障定位难度大等问题,提出了小波包能量谱结合BP神经网络的测距方法。具体的定位方法实现步骤如下:首先在故障发生时快速进行故障选线。然后把发生故障时在测量点采集到的电压故障分量经过小波包分解重构得到小波包能量,并将其作为输入样本通过BP的非线性拟合能力进行训练。最后将反映故障位置的小波包能量代入即可输出相应的故障距离。仿真结果表明,该方法耐过渡电阻能力强,定位的准确度高。     

Fault Detection and Localization Methodology for Self-healing in Smart Power Grids Incorporating Phasor Measurement Units

Recent developments in several fields of engineering have accelerated the evolution of smart power grids encompassing both transmission and distribution systems across the globe. Self-healing, a crucial operational function of a smart power grid, requires detection as well as localization of the transmission line faults in the power network in real time. A support vector machine based fault-localization methodology has been proposed to accurately detect and localize any type of transmission line faults for the entire smart power grid. This methodology identifies the transmission line fault in smart power grid and precisely pinpoints the bus to which the faulty branch is connected. Afterward, the faulty branch is discriminated, and the distance of fault location from the bus related to the fault is estimated. The methodology relies on frequency-domain analysis of the equivalent voltage phasor angle and equivalent current phasor angle using fast Fourier transform. The proposed methodology has been corroborated using extensive case studies conducted on 7- and 13-bus power systems. The major contribution of the proposed methodology is that it can identify and localize all types of transmission line faults using phasor measurement unit measurements. The methodology can be applied for transmission systems as well as distribution systems.     

Recursive functional expansion technique for computer-based impedance and differential protection

The development of a recursive functional expansion algorithm for extracting the desired frequency components from transient power system relaying signals is presented. The applications of this algorithm to impedance detection in transmission line protection and to harmonic restraint in transformer differential protection are discussed. The recursive algorithm generates fast fault detection timings for transmission lines and does not have restrictions on sample rate, data window or spacing of samples with respect to time. For power transformer differential protection, the combined second- and fifth-harmonic amplitude of the differential current is compared with the fundamental amplitude to arrive at a trip decision.