基于多数据源的电力变压器分层故障诊断系统设计

在现有变压器在线监测条件普遍不足的前提下,介绍了一种基于多数据源的变压器分层故障诊断系统。该系统充分利用在线监测数据和各种电气试验、运行状况以及专家经验等信息,将人工神经网络和基于事例(case)推理的专家系统结合起来,在不同层次的故障诊断模型中采用不同的智能诊断手段,逐步深入、细化诊断结果,并对系统的数据流和知识流进行合理的总体规划。该系统还提供了模拟变电站数据的仿真器,可用于系统的测试,在一定程度上保证了其可靠性。     

Analysis of power transformer dissolved gas data using the self-organizing map

Incipient faults in power transformers can degrade the oil and cellulose insulation, leading to the formation of dissolved gases. Even though established approaches that relate these dissolved gas information to the condition of power transformers are already developed, it is discussed in this paper that they still contain some limitations. In view of that, this paper introduces an alternative approach for the analysis of dissolved gas data, which can produce more convincing interpretation and fault diagnosis. The proposed approach, which is based on the data mining methodology and the self-organizing map, has been compared and validated using conventional interpretation schemes and real fault-cases, thereby proven to be capable of enhancing the condition monitoring of power transformers.     

The design of a multi-agent transformer condition monitoring system

Online diagnostics and online condition monitoring are important functions within the operation and maintenance of power transformers. This paper describes how a multi-agent system (MAS) for transformer condition monitoring has been designed to employ the data generated by the ultra high frequency (UHF) monitoring of partial discharge activity. It describes the rationale behind the use of multi-agent techniques, and the problems overcome through this technology. Every aspect of the MAS design is discussed. In addition, the design and performance of the intelligent interpretation techniques are detailed.     

电压响应方法在电力变压器状态评估中的应用

Power transformer is one of the most important equipment in the power system.Its operating condition affects the reliability of power supply directly.Therefore,in order to guarantee transformer operation safely and reliably,it is necessary to assess condition of power transformer accurately.Return voltage method based on voltage response measurements is still a new non-intrusive diagnosis method for internal insulation aging of transformer.In this paper the technique and application of return voltage measurement and some results of voltage response measurements of several transformers was introduced.Voltage response measurements were performed on various transformers with different voltage grades,various operating periods,different moisture contents and aging degrees on site.Derived moisture contents from return voltage measurement were compared with the corresponding moisture contents obtained from the analysis of oil samples.Based on on-site experiments and theoretical analysis,the criteria for insulation state of transformer are proposed.Moisture condition of transformer insulation can be determined by using return dominant time constant,and a good correlation between aging degree and the return voltage initial slopes of the aged transformers.Field test performed on several transformers,its interpretation of results are also presented,which proves that return voltage measurements can be used as a reliable tool for evaluating moisture content in transformer insulation.     

On-line monitoring and diagnoses of power transformer bushings

Power transformers have been in service for many years under different conditions. Statistical studies have shown that failures of bushings are one of the main causes for long duration outages of transformers. The development of an instrument for supervising the conditions of transformers bushings is, therefore, of special interest. In this contribution two methods are introduced for monitoring of bushings. In the first method, using summation voltage of transformer bushings from bushing taps with and without neutral point voltage are considered. In the second method a new sensor is used which can give voltage signal as a signal reference from the high voltage conductor in each bushing. Comparing the signal reference with using tap voltage signal can evaluate the condition of transformer bushing. In addition a software for monitoring and diagnostic of transformer bushing is presented.     

Review of condition assessment of power transformers in service

As transformers age, their internal condition degrades, which increases the risk of failure. To prevent these failures and to maintain transformers in good operating condition is a very important issue for utilities. Traditionally, routine preventative maintenance programs combined with regular testing were used. The change to condition-based maintenance has resulted in the reduction, or even elimination, of routine time-based maintenance. Instead of doing maintenance at a regular interval, maintenance is only carried out if the condition of the equipment requires it. Hence, there is an increasing need for better nonintrusive diagnostic and monitoring tools to assess the internal condition of the transformers. If there is a problem, the transformer can then be repaired or replaced before it fails. An extensive review is given of diagnostic and monitoring tests, and equipment available that assess the condition of power transformers and provide an early warning of potential failure.     

Dissolved gas analysis: It can save your transformer

The use of dissolved gas analysis (DGA) to monitor the in-service behavior of transformers is discussed. Sampling techniques are briefly considered, and two commercial hydrogen-in-oil detectors are described. The first allows the hydrogen concentration to be measured at intervals of a few hours by a portable gas collector that can be connected to semipermeable tubes. Continuous remote monitoring from the substation is possible with the second model, which uses a fuel-cell-type detector. The use of DGA for fault diagnosis is examined, and acceptable gas levels are indicated. The use of expert systems to facilitate decision making on the basis of DGA results is discussed, as is international cooperation in sharing data and experience and reaching agreement on methods of analysis and interpretation. Further applications of DGA are indicated     

基于频域介电谱试验的750kV变压器绝缘状况评估

电力变压器运行的可靠性在很大程度上取决于其绝缘系统,绝缘性能降低,寿命便缩短。从经济性和安全性考虑,希望尽可能延长变压器的使用年限,又确保其安全稳定运行,则要对其进行绝缘诊断和寿命评估。通过分析电力变压器绝缘状态的诊断原理与方法,介绍了一种基于频域介电谱(FDS)技术进行绝缘诊断的新型试验方法。采用FDS法对兰州东变电站750 kV变压器进行了初步的现场测量,并分析了测量结果,结果表明,该变压器纸板水分含量合格,绝缘状况良好,且测量结果与预防性试验吻合良好。FDS有望成为一种新的预防性试验方法,具有良好的应用前景。     

Partial discharge monitoring for power transformer using UHF sensors. Part 2: field experience

Because of the large capital value of power transformers and their critical role in the electricity network, there is an increasing need for non-intrusive diagnostic and monitoring tools to assess their internal condition. The UHF technique is being applied increasingly to monitor partial discharges (PD) in power transformers and has been shown to be much more sensitive than acoustic techniques when the signal path passes through solid insulation. Field trials were performed on five power transformers ranging in size from 18 to 1000 MVA and in voltage from 25 to 400 kV. The results of PD tests on power transformers provide sufficient evidence to justify making provision for UHF sensors on new transformers to facilitate their monitoring when required during the service lifetime.     

变压器故障特征量可信度的关联规则分析

变压器在线监测得到的多个特征量对于不同故障类别的潜在信息量不一样,量化各特征量与特定故障类型之间的关联度将对变压器的潜在故障诊断和预测都有着很重要的作用。为此,利用布尔型离散化方法和基于ChiMerge算法的多值离散化方法分别对变压器在线监测的连续数据进行离散化,再利用改进的Apriori关联规则数据挖掘算法计算多个变压器在线监测特征量与各个故障类型之间的可信度。最后在实例中进行了多个特征量与多个故障类型的可信度的计算,结果表明特定特征量与故障类型之间确实存在不同的关联程度,量化关联程度能有效提高故障诊断算法的效率;另外还在实例中进行了多值的关联规则挖掘,结果表明关联规则可以应用在对故障类型划分较细的变压器故障诊断。     

变压器独立监测装置统一数据读取和通信方法

现有变压器监测及检测装置独立运行、规范不一致，造成数据无法共享，难以在同一个系统中实现基于多参数的变压器综合诊断，为此提出了统一数据读取和通信方法。设计了在线监测装置统一通信框架，提出了私有协议与智能变电站状态监测系统站内I0规范的转化方法。为解决I0规范不便于读取较大数据文件的问题，提出了数据与MODBUS地址之间的多对一映射方法。给出了局部放电检测装置数据的统一XML文件格式及私有格式数据向该格式的转化方法。选取典型厂家的在线监测和离线检测装置进行实验，验证了方法的可行性，该方法可推进独立监测装置孤立数据的共享应用。     

基于深度置信网络和多维信息融合的变压器故障诊断方法

为了综合多维度信息,快速准确判断变压器缺陷,同时解决多维度信息融合权重难以确定的问题,文中基于深度学习理论,采用稀疏受限玻尔兹曼机搭建了用于故障诊断的深度学习故障分类模型,结合大型变压器的多维度监测量,提出了一种基于深度置信网络和多维度信息融合的变压器故障诊断方法。该方法能够利用变压器海量的无标签多维监测数据作为学习样本,只需对少量带标签数据进行辅助优化,根据变压器实时在线多维监测数据,被训练后的模型能够对变压器本体状态做出准确的故障诊断。对某市220 k V主变进行诊断测试,结果表明,文中提出方法的故障诊断准确率较现有方法高约4%,验证了该方法的可行性和有效性。     

Deriving an equivalent circuit of transformers insulation for understanding the dielectric response measurements

Preventive diagnosis and maintenance of transformers have become more and more popular in recent times in order to improve the reliability of electric power systems. Dielectric testing techniques such as return voltage measurement (RVM) and polarization-depolarization current (PDC) measurement are being investigated as potential tools for condition assessment of transformer insulation. A better understanding and analysis of the dielectric test results are only possible with a clear understanding of the physical behavior of the insulation system in response to moisture and aging. A circuit model, which describes the dielectric behavior of the transformer's main insulation system, has been parameterized in this paper. The values of the parameters of the model have been identified from the dielectric tests. A correlation has been developed between the physical condition of the insulation and the equivalent model parameters that enable a clear and transparent interpretation of the dielectric test results.     

有载分接开关机械性能的在线监测与故障诊断系统设计

设计了电力变压器有载调压分接开关 (OLTC)机械性能的在线监测与故障诊断系统 ,包括硬件和软件两大部分。本设计将数据处理与故障诊断技术集成在远程计算机的综合分析软件中 ,具有丰富的实时显示和数据库存储功能 ,能满足 OL TC的实际运行监测需要 ,为其实现状态维修提供了技术手段。     

基于纳秒脉冲技术的超/特高压设备绕组变形带电检测研究

绕组变形检测作为超/特高压绕组设备(变压器/高压电抗器)的检验项目,采用传统的离线检测,无疑限制了主要依靠带电检测/在线监测信号支持的电气设备状态评价。根据新疆电网750 k V变压器/高压电抗器状态评价需要,提出实现该类设备带电检测/在线监测设想,采用在高/低压套管末屏位置加装耦合电容和隔离装置,在高压套管侧注入激励纳秒脉冲而在低压套管侧检测其响应信号,构建绕组变形故障诊断的特征曲线。通过建模理论研究纳秒脉冲法检测绕组变形故障并首次设计现场耦合电容环和隔离装置对新疆乌北变电站750 k V高压电抗器进行3种试验电压实测和分析,研究结果表明,该方法实现超/特高压设备绕组变形故障的带电检测技术是可行的。     

变压器状态监测组件功能整合研究和性能提升设计

传统变压器状态监测组件IED较多,信息交互复杂,装置误报警率高,系统可靠性低。针对上述问题,提出了一种整合型变压器状态监测智能组件性能提升方案。通过对在线监测装置的硬件和软件功能集成及油色谱装置的优化设计,可有效减少变压器状态监测组件的IED数量和提高系统可靠性。基于Xenomai的Linux实时系统的研究,结合嵌入式SQLite数据库和Web Service应用技术,实现变压器在线监测系统的采集功能集成化和诊断流程标准化设计。所设计的智能组件整合了油色谱在线监测、铁心接地电流监测和特高频(UHF)局部放电监测等监测功能,已在重庆220 kV虎啸智能变电站中得到应用,效果良好,充分体现了未来智能监测组件向结构紧凑化、通信标准化和状态可视化的方向发展,具备较好的推广前景。     

A new fuzzy logic approach to identify power transformer criticality using dissolved gas-in-oil analysis

Dissolved gas analysis (DGA) of transformer oil is one of the most effective power transformer condition monitoring tools. There are many interpretation techniques for DGA results however all current techniques rely on personnel experience more than analytical formulation. As a result, the current techniques do not necessarily lead to the same conclusion for the same oil sample. A significant number of DGA results fall outside the proposed codes of the ratio-based interpretation techniques and cannot be diagnosed using these methods. Moreover, ratio methods fail to diagnose multiple fault conditions due to the mixing up of produced gases. To overcome these limitations, this paper introduces a new fuzzy logic approach that aids in standardizing DGA interpretation and identifies transformer critical ranking based on DGA data. The approach relies on incorporating all traditional DGA interpretation techniques (Roger, Doerenburg, IEC, key gas and Duval triangle methods) into one expert model. In this context, DGA results of 338 oil samples of pre-known fault conditions that were collected from different transformers of different rating and different life span are used to establish the model. Traditional DGA interpretation techniques are used first to analyze the DGA results to evaluate the consistency and accuracy of each method in identifying various faults. Results of this analysis were then used to develop the proposed fuzzy logic model. The model is validated using another set of DGA data that were collected form previously published papers.     

变压器故障诊断中信息融合技术的应用

电力变压器的可靠性直接影响供电的稳定,为此结合电力变压器故障诊断的具体情况,从信息融合的角度提出了基于信号类型及不同特征向量组合的集成诊断模型。该模型利用基于故障机理内在因素的专家系统,采用匹配知识规则,通过模糊推理,得特征向量与变压器故障信息间的关联性质,完成故障诊断,且诊断完成后,利用数据挖掘技术将诊断过程中的特征量、推理过程、结果以编码形式存入专家系统规则库。该模型将油中溶解气体、电气参数等特征量结合作为故障判据,评估变压器状态,并利用评估结果丰富专家系统的规则库。在讨论了多传感器信息融合技术用于变压器在线故障诊断时的具体实现方法后通过实例进行分析说明:利用来自传感器的各种故障信息进行融合,作为变压器故障诊断的判据,提高了诊断的可靠性和准确性,这将对提高电网安全性能及电气设备的诊断自动化与智能化水平起到推动作用。     

Apparatus for Online Power Transformer Winding Monitoring Using Bushing Tap Injection

Online transformer condition monitoring techniques based on transfer function methods, such as transmission-line diagnostics and swept frequency-response analysis, require the injection of a known test signal into the transformer. On larger power transformers, a practical method is to use the available bushing tap connection. In this paper, we will discuss a custom high-power signal generator that injects high-frequency signals on the bushing tap of the transformer under investigation, as well as a circuit to replace the bushing tap short and allow online operation of the system. Finally, the system is demonstrated on a 650 kV transformer.