电力变压器故障在线监测与诊断系统

【作者】 夏向阳；

【导师】 罗安；

【作者基本信息】 中南大学 ， 控制理论与控制工程， 2004， 硕士

【摘要】 本文研究课题是湖南超高压输变电公司和中南大学共同合作攻关科研项目，其目的是开发变压器故障的在线监测诊断系统。本文通过建立一种变压器故障综合诊断的多级决策融合模型，将油中溶解气体分析与常规电气试验的结论结合起来，并充分借鉴现场的运行、诊断和维修经验，具有较强的知识表示及不确定性处理能力。本文首先简要介绍了变压器智能在线诊断的意义、国内外发展现况及故障诊断方法；然后系统地阐述了电力变压器故障诊断模型和多种诊断理论的基础和方法；接着结合电力变压器故障诊断的具体情况，较为深入地分析了诊断理论用于电力系统变压器在线故障诊断时的具体实现方法，即在信息融合思想的指导下，采用一个基于层次分类的变压器故障诊断模型，分析利用各种诊断方法的诊断结果；最后对诊断软件的实现进行了较详尽的论述，包括软件开发平台的确定、功能的实现以及用到的关键技术和开发过程中碰到的一些问题与解决方法。 整个系统可分为三个大模块：信息采集模块、数据管理模块和故障诊断模块。其中诊断模块是以集成诊断形式出现，利用决策融合网络将基于不同诊断机理与方法的诊断子模块进行融合，提高了诊断确诊率。本系统可提高电网运行的可靠性，并切实提升用户对电气设备进行状态诊断的自动化及智能化水平。更多还原

【Abstract】 The dissertation is about the study of transformer fault online diagnosis system, sponsored by Hunan EHV Power Transmission Company. A type of multi-level comprehensive fault decision model is built. Based on the diagnostic model, the dissolved gas-in-oil analysis and the results of conventional electrical tests of power transformers are combined tightly. The on-site experiences in operation, diagnosis and maintenance are highly utilized in the model. It has shown that the model possesses satisfactory capacity of knowledge representation and strong solving ability to deal with uncertain facts. At first, the importance of transformer faults online diagnosis technology and its development actuality are given briefly, the structure of the whole system and its work mechanism are introduced detailedly; Then the diagnostic theory and the model are discussed systematically? Combined with the reality of power transformer faults online diagnosis, the realization of methods of transformer faults diagnosis are presented in detail. In accordance with the basic principles of information fusion, all these methods are analysed and compared through simulation experiments and a new integrated diagnostic model is presented based on these methods; At last, the realization of the software is discussed which includes its structure, functions and key techniques.The system comprises three main sub-module which includes information collection module, data management module, fault diagnosis module. In fault diagnosis module, integrated diagnosis module is presented. The diagnostic precision is improved by the decision-making fusion network in which all diagnostic sub-modules based on different theories and mechanisms are fused. The system will contribute to the security of electric power network, the automatic and intelligent level of power equipment insulation condition diagnosis is enhanced greatly.更多还原