变压器油中溶解气体浓度的区间预测

应用灰色关联度分析方法确定了与待预测状态量关联度较高的因素,并利用熵理论建立了具有客观权重的组合预测模型。预测区间可有效量化由不确定因素引起的油中溶解气体浓度波动,应用比例系数法和粒子群优化算法建立了一定置信水平下油中溶解气体浓度的区间预测模型,且不受传统区间预测方法中必须服从正态分布的限制。实例结果验证了所提模型的有效性。     

基于SDS-SSA-LSTM的变压器油中溶解气体浓度预测

油中溶解气体浓度预测对变压器早期故障检测至关重要。为了提高预测精度,本文提出了奇异谱分析(SSA)结合长短期记忆网络(LSTM)的预测模型。首先针对传统序列分解做法中的数据泄露问题,提出一种基于SSA逐步分解的采样策略,然后基于该策略将特征复杂的原始油中溶解气体浓度序列分解为特征相对单一的趋势分量与波动分量,最后利用LSTM网络对各个分量分别进行单步和多步预测。累加各分量的预测值,得到原气体浓度的预测结果。算例表明,相较于单一LSTM,本文所提模型在实验天数内整体的预测精度更高。     

基于LSTM网络的变压器油中溶解气体浓度预测

电力变压器作为电力系统中传输和变换电能的主要设备,其安全稳定性运行在电网中起着重要的作用。对变压器油中溶解气体浓度变化的趋势进行预测,可为其运行状态评估提供重要依据,鉴于此提出了一种基于长短期记忆网络(LSTM)的变压器油中溶解气体浓度预测模型。该模型克服了传统神经网络在序列预测方面存在的"梯度消散"问题,利用油中溶解气体的序列数据对长短期记忆网络进行训练,得到最优的预测模型参数。以变压器油中溶解的7种特征气体浓度为输入,以待预测气体的浓度为输出。通过算例分析表明,相比于传统的机器学习预测方法支持向量机(support vector machine, SVM)与反向传播神经网络(back propagation neural network,BPNN),本文所提的LSTM预测模型更能准确地预测油中溶解气体的浓度。     

Breakdown of transformer oil

Some of the factors affecting the dielectric strength of transformer oil are investigated. These factors include the stabilization phenomenon, oil and electrode pretreatment, the effect of oil velocity, the effect of a capacitance parallel to the test cell, and the effects of electrode area and gap spacing. The experimental apparatus and procedure are described, and the results are presented for each of the above factors. Suggestions for future research are offered     

Technical report-particles in transformer oil

Attention is drawn to a parameter that plays a crucial role in determining the breakdown strength of transformer oil, yet which tends to be ignored. This parameter is the settling time, which can mean either the time interval between two consecutive measurements or the time for which an oil sample is stored before measurements begin. The term is used here in the former sense. Research carried out with Bruce profile electrodes and for gap spacings of 1 and 4 mm showed that settling times between measurements of 1 and 5 mm gave widely differing breakdown strength results. The breakdown strength with 1-min settling time was inferior to that for a settling time of 5 min. A particle counting analysis performed on two oil samples supports the hypothesis that short settling times do not allow either the bubbles from the previous breakdown to be dissolved or the decomposition products to settle under the influence of gravity, thereby increasing the probability of breakdown     

Properties of streamers in transformer oil

The electrical characteristics of creeping discharges and single creeping streamers in transformer oil first are compared with those of streamers developing in the liquid bulk. The distribution of electric potential along the channel of a single negative creeping streamer is determined using a capacitive probe technique. Then the distribution of the space charge associated with each streamer channel is discussed and the electric field around the channels is estimated. A strong correlation between the mean potential gradient and the capacitance of the streamer channels is found. The different results and considerations tend to support the hypothesis of the same basic physical mechanism for both creeping discharges and streamers developing in the bulk     

Investigations of transformer oil characteristics

In this paper, the behavior of various critical parameters of transformer oil is interpreted with a view to enhancing its life time. Systems abnormalities such as excess loading, switching, and ambient conditions are responsible for the accelerated aging and sudden failure of transformer. The level of insulation plays a significant role in the life expectancy of the transformer. The diagnostics of the critical parameters for the defined ranges of aging of transformer oil attempts to determine the level of insulation and serve to ensure its efficient operation. The approach includes formulation of suggestions for determining the insulation level of the power transformer. © 2012 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

在线色谱在电力变压器油分析中的应用分析

本文介绍色谱在线监测技术的基本原理和关键组成,通过实例对色谱在线监测和实验室离线分析进行数据比对。数据表明,在线监测技术可以反映变压器运行状态和故障发展的趋势。     

绝缘油颗粒度检测全密封取样装置的开发应用

针对超高压输变电设备开展绝缘油颗粒度检测中遇到的取样问题,分析了环境因素对取样的影响,开发了绝缘油颗粒度检测全密封取样装置。应用结果表明：该装置具有减少取样中间环节,避免环境及人为因素对取样的影响,提高颗粒度检测方法的准确率和精密度的特点,满足了超高压电气设备绝缘油颗粒度交接试验对取样的要求。     

大型变压器绝缘油中硫腐蚀的危害及防护对策研究

针对电网大型变压器在运行中发现的硫腐蚀问题,初步分析了产生硫腐蚀的原因及对设备安全运行的危害;在此基础上开展了防护对策的研究,提出了向运行设备绝缘油中添加钝化剂以避免硫腐蚀发生的解决方法,介绍了钝化剂技术在华东电网500kV变压器上的具体应用情况.     

变压器油中的金属含量值得重视

主变压器运行中油中烃含量的变化已引起普遍的重视 ,并运用三比值法来发现和解决问题。但变压器油中金属含量 ,尤其是铜、铁含量的变化尚未引起足够的重视 ,特别是溶融的金属会使变压器绝缘下降形成事故隐患。四川广元电业局一台SFPSZ9 1 2 0 0 0 0 /2 2 0主变 ,在预防性试验时曾发现绝缘电阻明显下降 ,直流泄漏增长甚快 ,介质损增大 ,当时疑为受潮引起 ,经多次多种方法干燥处理后 ,绝缘电阻等指标未能好转。比较该主变 6年前的出厂试验和 3年前的交接试验报告 ,低压绕组对地绝缘电阻和吸收比 ,由 1 80 0 /75 0 =2 .4降至 85 0 /5 0 0 =1 …     

变压器油中的糠醛萃取新技术

针对目前国内没有专用的变压器油糠醛萃取设备问题,研制了专用的变压器油糠醛萃取装置,方便了变压器油的糠醛萃取工作,为变压器固体绝缘老化的诊断分析提供了手段和方法,实现了对变压器固体绝缘老化的有效监督,从而为变压器设备的状态检修工作提供了有利的技术支持。应用测试结果表明,糠醛的萃取效率达95%以上,萃取效果十分明显。     

A hybrid transformer model for determination of partial discharge location in transformer winding

Partial discharges are well known as a source for insulation degradation in power transformers. A hybrid transformer model is introduced to simulate the transformer winding transient response. Transformer structural data is used to determine the hybrid model parameters. Calculations of the hybrid transient model parameters are based on the parameters of the lumped parameter equivalent transformer model and electromagnetic rules. Modern computation techniques and optimizations are employed beside this model for PD location using the multi conductor transmission line model and also to analyze its propagation aimed at achieving (i) more reliable simulation results (ii) less computational time (iii) accurate results for a wide range of frequency. The simulation results on a 66 kV, 25 MVA fully interleaved winding are presented. The measurement results on this winding are employed to validate this model     

油浸变压器用植物油

在ll篇文献的基础上，综述了变压器用绝缘植物油的研究现状，分析比较了植物油和矿物油的特性，指出了植物油绝缘的诸多优点和变压器用植物油存在的问题。得出植物油其生物降解率高，符合环保要求，具有良好的应用前景的结论。     

变压器渗漏油原因及防治措施

变压器渗漏油问题长期以来一直困扰着供电运行部门,不仅影响达标创优工作,而且影响安全运行.如何解决变压器渗漏油问题,是多年来电力部门在生产实际中的一大难题.本文分析了造成变压器渗漏油的诸多原因,制定并完善了防止变压器渗漏油的各项工艺措施、技术措施,并联系实际慎密进行了施工处理.     

变压器油性能检验的必要性

本文综述了变压器油的质量性能、技术要求和检验标准，并通过实例分析了变压器油的运行情况和变坏的原因，提出了应采取的预防措施。