A new travelling-wave based scheme for fault detection on overheadpower distribution feeders

The authors present the results of investigations into a new fault location technique for overhead power distribution systems. The scheme is based on detecting fault-induced high-frequency components on distribution lines. This should enable the detection of discharges from the low-level breakdown of insulators, which cannot be detected by conventional methods. The location of a fault is determined by appropriate signal processing of the generated signals on the line. Simulation results are used to illustrate the basic features of the performance of the new scheme on a simple radial 11 kV feeder system     

A novel extension method for transformer fault diagnosis

Dissolved gas analysis (DGA) is one of the most useful techniques to detect incipient faults in power transformers. However, the identification of the faulted location by the traditional method is not always an easy task due to the variability of gas data and operational variables. In this paper, a novel extension method is presented for fault diagnosis of power transformers, which is based on the matter-element model and extended relation functions. Thus, incipient faults in power transformers can be directly identified by the degree of relation. The application of this new method to some transformers has yielded promising results.     

An intelligent and efficient fault location and diagnosis scheme for radial distribution systems

In this paper, an effective fault location algorithm and intelligent fault diagnosis scheme are proposed. The proposed scheme first identifies fault locations using an iterative estimation of load and fault current at each line section. Then an actual location is identified, applying the current pattern matching rules. If necessary, comparison of the interrupted load with the actual load follows and generates the final diagnosis decision. Effect of load uncertainty and fault resistance has been carefully investigated through simulation results that turns out to be very satisfactory.     

A novel fuzzy logic approach to transformer fault diagnosis

Dissolved gas in oil analysis is an well established in-service technique for incipient fault detection in oil-insulated power transformers. A great deal of experience and data in dissolved gas in oil analysis (DGA) is now available within the utilities. Actually, diagnostic interpretations were solely done by human experts using past knowledge and standard techniques such as the ratio method. In this paper, a novel fuzzy logic approach is adopted to develop a computer based intelligent interpretation of transformer faults using Visual basic and C⁺⁺ programming. The proposed fuzzy logic based software as been tested and tuned using over 800 dissolved gas in oil analysis (DGA) case histories. This highly reliable tool has then been utilized in detection and verification of 20 transformer faults. The proposed diagnostic tool is very useful to both expert and novice engineers in DGA result interpretation     

基于概率神经网络的电力变压器故障诊断

提出了一种基于概率神经网络的变压器故障诊断方法,并用遗传算法优化概率神经网络的平滑因子,从而提高概率神经网络诊断的正确率.结果表明,实际的油色谱数据验证了此变压器故障诊断方法的可行性和正确性.     

基于概率神经网络的电力变压器故障诊断

提出了一种基于概率神经网络的变压器故障诊断方法,并用遗传算法优化概率神经网络的平滑因子,从而提高概率神经网络诊断的正确率。结果表明,实际的油色谱数据验证了此变压器故障诊断方法的可行性和正确性。     

极坐标图像法用于检测变压器绕组的微小辐向变形故障

频率响应分析法一直以来被认为是诊断电力变压器绕组变形故障最具潜力的方式,然而,现有频率响应分析法大多仅利用频率响应的幅值信息,而忽略了其相位变化的特性,针对某些故障类型,例如绕组的微小辐向变形故障,仅利用幅值信息的方法,故障诊断的灵敏度并不高。因此,文中提出一种新的极坐标图像法,利用频率响应构造极坐标图像,进而辅助诊断绕组变形故障。通过开展绕组等效电路模型的算例分析,结论证实在传统频率响应分析法不能反映绕组微小辐向变形故障时,此提出的方法可能更有效地检测出绕组故障,极坐标图像法具有更高的诊断灵敏度。     

A new approach of DGA interpretation technique for transformer fault diagnosis

Dissolved Gas Analysis (DGA) is one of the most common techniques to detect the incipient faults in the oil-filled power transformers. In this paper, a new approach of DGA technique is proposed to overcome the conflict that takes place in the traditional interpretation techniques for transformer fault diagnosis. The new approach is based on the analysis of 386 dissolved gas samples data set that collected from the Egyptian electric utility chemical laboratory as well as from credited literatures. These data sets are used to build the technique model and also as a tested data set to get the technique’s accuracy. The new approach DGA diagnoses the transformer fault types based on the gas concentration percentage limit of the sum of main five gases (Hydrogen (H₂), Methane (CH₄), Ethan (C₂H₆), Ethylene (C₂H₄), and Acetylene (C₂H₂)) and some suggested gases ratios depending on the sample data set analysis. The validation of the proposed approach of DGA technique is satisfied by comparing its results with the results of the IEC Standard Code, Duval triangle and Rogers methods for the collected data set. The results refer to the ability and reliability of the new approach in transformer faults diagnostic.     

电力变压器状态在线监测和故障诊断的新方法

介绍一种电力变压器绝缘在线监测和故障诊断的新思路，一方面通过在线油色谱分析仪检测6种故障特征气体含量和产气率，运用模糊理论及专家系统等人工智能技术对电力变压器的绝缘状态进行跟踪监测，另一方面尝试用参数辨识的方法进行变压器三相电气量的在线监测，依据变压器绕组结构及参数在故障前后会改变的原理，用参数辨识的方法，进行变压器绕组故障及其故障部位的识别，实现故障局部定位，提高变压器状态监测和故障诊断的准确性。     

有源电子式互感器故障诊断技术的研究与应用

作为继电保护和自动化装置的信息源头,电子式互感器的运行性能直接影响整个电网,由于受到环境和电磁辐射的影响,其输出信号的稳定性是智能变电站普及推广应用的瓶颈。通过对电子式互感器运行中的故障类型进行分类,采用分段函数模拟不同的故障类型,利用小波理论分析对故障信号进行除噪处理,再通过小波分解对除噪后的信号进行故障检测定位,归纳为小波-神经网络的故障诊断分析方法。该方法能够直接判别漂移偏差故障、固定偏差故障和变比偏差故障,对提高智能变电站运行可靠性具有前瞻性的意义。     

电力变压器的智能故障诊断研究

将基于改进遗传算法（IGA）和误差反向传播（BP）算法相结合构成的IGA-BP混合算法用于训练神经网络。该混合算法有效克服常规BP和传统GA算法独立训练神经网络的缺陷,并应用于电力变压器溶解气体分析的智能故障诊断。实验诊断结果表明,IGA-BP混合算法的收敛速度快于BP及GA算法,并且具有较高的诊断准确率。     

A fault location technique for rural distribution feeders

This work presents a digital fault location technique for rural distribution feeders, using the voltage and current data at a single location. Rural distribution feeders include single-phase, two-phase, and three-phase laterals off a main three-phase primary distribution feeder. The fault location scheme presented here attempts to account for the multiphase laterals, the unbalanced conditions, and the unsymmetrical nature of distribution feeders by continually updating voltage and current vectors at set locations within the system. The updated voltage and current vectors are the estimates of the 60-Hz phasor quantities obtained using a recursive optimal estimation algorithm. The distance to the fault is then estimated using a method based on the apparent impedance approach and the updated voltage and current vectors. Another consideration is the ability to determine the fault location on a lateral. A simulation of an actual rural distribution feeder using the Electromagnetic Transients Program (EMTP) is used to test the approach     

面向对象的变压器绝缘故障诊断知识库

本文介绍了面向对象技术的基本理论,首次将其引入到变压器绝缘故障诊断专家系统中,并结合神经网络模糊理论等智能诊断方法和规程导则以及大量的专家经验建立了面向对象结构的变压器绝缘故障诊断知识库,提出了一种新颖的专家系统知识库的构造方式。     

A neural network-based scheme for fault diagnosis of power transformers

This research presents an artificial neural network (ANN)-based scheme for fault diagnosis of power transformers. The scheme is designed to detect the fault, estimate the faulted side, classify the fault type and identify the faulted phase.The proposed fault diagnosis scheme (FDS) consists of three hierarchical levels. In the first level, a pre-processing of input data is performed. In the second level, there is an ANN which is designed to detect the fault and determine the faulted side if any. In the third level, there are two sides diagnosis systems. Each system is dedicated to one side and consists of one ANN in series with four paralleled ANNs (for fault type classification).The proposed FDS is trained and tested using local measurements of three-phase primary voltage and primary and secondary currents. These samples are generated using EMTP simulation of the High Dam 15.75/500 kV transformer substation in Upper Egypt. All the possible fault types were simulated. The fault locations and fault incipience time were varied within each fault type. Testing results proved that the performance of the proposed ANN-based FDS is satisfactory.     

电力变压器故障诊断的可拓集法

基于可拓理论,在传统油中溶解气体分析DGA(Dissolved Gas Analysis)三比值法基础上,提出一种可拓集变压器故障诊断方法。首先,建立三比值法的物元模型,然后给出点对区间的可拓相关函数,利用该函数计算进行变压器故障诊断。仿真计算证明该方法能克服传统三比值法的编码不全,不能诊断多重故障的缺陷,提高了诊断精度。     

变压器一次接线对微机型主变差动保护的影响

针对一起35kV变电站主变差动保护异常情况,通过对本变电站一次接线和二次回路检查及保护装置相应校验,对带负荷测相量的数据进行认真分析,确认变压器一次接线的变化是引起差动保护异常的根本原因,改变变压器一次接线并重新进行了带负荷测相量工作,确认相量无误后投入差动保护,主变微机型差动保护装置正常运行;并由此引出对各种一次接线引起Y/△-11变压器接线组别变化的相量分析,可以根据所测差动保护相量快速判断故障.     

牵引变压器绕组改进型频率响应建模与径向变形故障分析

以一台QYS-R-(31500+25000)/220牵引变压器为研究对象,提出一种基于集总参数电路的考虑绕组间全电容参数的改进型频率响应模型,通过与实测曲线进行对比,验证了模型正确性;然后对变压器的牵引绕组和高压绕组分别进行了向内的曲翘变形和向外的鼓包变形这2种径向变形故障仿真,重点分析了不同变形故障对电容参数的影响;最后通过对变化的频率响应曲线进行分析。分析结果表明:牵引变压器牵引绕组和高压绕组发生径向变形故障时,特征诊断频带不同,但在各自的特征频带内频响曲线呈现相同的变化规律,即随着故障程度的增加,频率响应曲线向低频方向移动,并且幅值不断增大。     

220kV变压器内部故障的色谱分析与诊断

本文采用溶解气体色谱分析法,跟踪分析了一台有潜伏性故障220kV变压器油中溶解气体的成份、特征气体含量和变化趋势。根据试验结果提出了故障诊断的步骤和方法,首先排除非故障产气的可能性,然后根据特征气体含量进行故障性质识别,再运用三比值法判断故障类型和进行状况诊断,最后应用有关参考文献综合进行故障部位估算。经现场设备检查和故障排除证实该判断方法和结果是正确的。     

数据挖掘技术在变压器故障诊断中的应用

为克服支持向量机在求解二次规划问题时运算过程复杂、计算时间过长、收敛速度缓慢的问题,提出一种基于加权最小二乘的SVM变压器故障诊断方法,并通过粒子群算法对参数进行优化,可以充分保证计算速度和较高故障判断精度。实例分析验证了该模型能确定变压器故障种类,且具有较高的正确率。     

混合神经网络在变压器故障诊断中的应用

针对变压器故障诊断准确率低的问题提出了粒子群-自组织映射-学习矢量化(PSO-SOM-LVQ)混合神经网络算法。为了获取更加有效的SOM神经网络拓扑结构,首先采用PSO算法对SOM神经网络的权值向量加以改进,在此基础上融入LVQ神经网络,弥补了无监督学习SOM神经网络的不足。这种PSO、SOM和LVQ相结合的混合神经网络算法提高了变压器故障诊断的精度,减少了故障诊断的误差。通过仿真,对SOM、PSO-SOM和PSO-SOM-LVQ这3种算法进行了对比。对比结果表明,PSO-SOM-LVQ混合神经网络算法准确度最高,其故障诊断准确率为100%。由此可见,采用PSO-SOM-LVQ混合神经网络算法可有效提高变压器故障诊断的性能。