【作者】 任丰瑞；

【导师】 张靠社； 李志斌；

【作者基本信息】 西安理工大学 ， 电气工程， 2009， 硕士

【摘要】 电力变压器是电力系统中最关键的设备之一,它承担着电压变换、电能分配与传输,并提供电力服务。因此,变压器的正常运行是对电力系统安全、可靠、优质、经济运行的重要保证,必须最大限度防止和减少变压器故障和事故的发生。对电力设备进行在线监测与故障诊断,是实现设备预知性维修的前提,是保证设备安全运行的关键。变压器油中溶解气体的成分和含量则能有效体现运行变压器内部的绝缘故障情况。论文分析讨论了常规油色谱和在线油色谱分析时,不同取样点对变压器油色谱分析的影响,特别对变压器在线油色谱分析在确定和选择取样点时,一定要考虑变压器油循环方式、运行状态、变压器结构及油流分布、故障部位及严重程度等情况。详细介绍了在变压器内部故障或异常情况下,油中溶解气体的特征及含量、故障严重程度、故障类型同特征气体含量的关系。虽然变压器油中溶解气体分析是变压器绝缘监督的一个重要手段,但放电和过热两类故障共存时的故障难分辨会导致诊断正判率较低。本文对多种故障类型作了详细分析后使用基础粒子群算法优化BP神经网络的DGA方法,选择油中典型气体作为神经网络的输入,然后利用训练好的粒子群算法优化后的神经网络进行变压器故障类型诊断。试验结果表明,该方法具有很好的分类效果,较好地解决了变压器放电和过热共存时故障的难分辨问题,对故障诊断的正判率较高。更多还原

【Abstract】 The electric power transformer is one of the equipments of the key in the electric power system, it undertakes the electric voltage transformation, electric power allotment with deliver, and provide the electric power service. Therefore, the normal work of the transformer is the important assurance to the electric power system safety, credibility, superior quality, economic work, we must prevent the electric power transformer from the breakdown and the occurrence of the troubles. But because the transformer circulates over a long period of time, the break down and the trouble can not be avoided completely, and the cause to break down to proceed from many various reason with trouble again. Implement of state on-line monitoring and fault diagnosis of the power equipment is the precondition of predicting maintenance, is the key element of reliable run, and is the important supplement and updated development to the traditional off-line preventive maintenance.According to the type and content of gas dissolved in transformer oil, it is easy to conclude the internal insulation faulty of transformer. The paper analyses the influence on the analysis of transformer oil chromatogram induced by different sampling oil spot when conventional analysis of transformer oil chromatogram or on-line analysis of transformer oil chromatogram. The paper introduces particularly the relation between the character of gases dissolved in transformer oil, content of gases, and the type of faults, the degree of the faults.T DGA is one of the mainly methods on insulation monitoring of transformer, but the accuracy is low because it is difficult to distinguish between failures when overheating and PD coexist. By analyzing all types of faults, a method is raised. The DGA of transformer by neural network based on particle swarm optimization (PSO) with neighborhood operator. Based on correlation analysis and pretreatment, the key gases are selected as the inputs of neural network, furthermore, fault diagnosis is accomplished by the neural network based on PSO with neighborhood operator. By discussing the experiment results, the method of this paper has very good classification results, and figure out the problem that is difficult to distinguish between failures when overheating and PD coexist, meanwhile, the effectiveness and usefulness is proved.更多还原