基于ANN和ES相结合的变电站报警信息处理系统
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
变电站发生故障后,会涌现大量的报警信息,
    特别是其中可能含有错误报警。在这样的情况下,
    要求运行人员作出正确的判断是非常困难的,因
    此,开发变电站的报警处理系统来辅助运行人员做
    出判断是十分有必要和有意义的。本论文所做的工
    作正是在此背景下进行的,在分析单独采用神经网
    络及专家系统存在各自的缺陷的基础上,开发了基
    于神经网络和专家系统相结合的变电站报警处理系
    统。
     论文首先对神经网络做了简介以及研究了前馈
    神经网络的容错性,提出了一种提高神经网络容错
    能力的实用学习算法。然后针对南昌500KV综合
    自动化变电站,开发该变电站的报警处理系统。该
    系统以母线、线路、变压器为核心元件,构造按元
    件类型来分类的网络诊断模块,以开关动作信息、
    保护动作信息作为其输入。在此基础上,建立了变
    电站的网络诊断模型,以有容错性的神经网络为其
    诊断核心,同时结合专家系统,利用其推理判断能
    力,对变电站运行方式进行识别,并对神经网络的
    某些输出结果进行必要的修正。
Many alarming messages will occur when there are some fault arising
     in substation, but in these messages some are unreliable. It is very
     difficult for the operator to decide where the fault happened under this
     condition. For these sakes it is a significant and essential task that
     substation alarm message dealing system is developed to assist operators.
     On the background, this paper studies the fault diagnosis using Expert
     System (ES) and Artificial Neural Network(ANN) because using ES or
     ANN separately has flaw.
    
     Firstly, the paper gives an brief account of ANN and researches the
     fault-tolerance performance of BP NN, it also puts forward a practical
     calculation which can improve the fault-tolerance performance. Secondly
     the paper develops the alarming dealing system directed at NanChang
     5 00KV automation substation. The kernel components of this system are
     bus ,electrical line and transformer. It constructs some network-diagnosis
     model classified by the kind of the components whose input messages are
     the information of protection alarm and tripped breakers, then the paper
     builds up a network-diagnosis model of substation on this basis. The
     diagnosis kernel of this model is ANN with the fault-tolerance
     performance and it combines the ES. With the inference an judgment
     ability of ES the model can judge the operating way and modify some
     output of ANN.
引文
[1] T. Sakaguchi, K.Matsumoto. Development of a Knowledge Based Expert System for Power System Restoration. IEEE Trans. on PAS, No.2, 1983
    [2] T. Minalawa,M.Kunugi.Development and Implementation of a Power System Fault Diagnosis Expert System. IEEE Transaction on Power System, 1995,10(2)
    [3]朱永利等.电力系统故障判断专家系统.华北电力学院学报,1992,NO.1
    [4]段振国.电力系统解列策略、故障诊断及其恢复策略研究.华北电力大学博士论文,1997
    [5]陈竟成.基于面向对象方法的电力系统在线警报处理、故障诊断与恢复控制专家系统.电力科学研究院博士学位论文,1994
    [6]刘青松等.基于正反向推理的电力系统故障诊断专家系统.电网技术,Vol.29,No.9
    [7]孙雅明等.超高压变电所在线故障诊断专家系统,中国电机工程学报,Vol.11,No.3
    [8]秦红霞等.基于面向对象技术的变电站故障诊断及恢复处理专家系统:(一)总体设计与建模.电力系统自动化,1996,20(9)
    [9]秦红霞等.基于面向对象技术的变电站故障诊断及恢复处理专家系统:(二)故障诊断及恢复处理.电力系统自动化,1996,21(2)
    [10]张东英等,解释型变电站故障诊断专家系统.华北电力大学学报,Vol.25,No.1
    [11]侯小梅等.神经网络在汽轮发电机组故障诊断中的应用.华南理工大学学报(自然科学版),1999,8
    [12]丁晓群等.基于BP网络的故障诊断方法的改进.电网技术,1998,11
    [13] Perez .L .G, Flechisg .A .j .Letal .Training an Artificial Neural to Discriminate Between Magnetizing Inrush and Internal Faults.IEEE POWER, 1994,9(1)
    
    
    [14]刘应梅等.人工神经网络在变电站故障诊断中的应用.99全国高校电力系统及其自动化专业学术论文集
    [15] Kwang-Ho Kim,Jong-Keun Park. Application of Hierarchical Neural Networks to Fault Diagnosis of Power Systems.Electrical Power&Energy Systems, Vol 15, No 2, 1993
    [16]顾雪平等.人工神经网络和专家系统结合运用的电力系统故障诊断方法.华北电力学院学报,1994,21(2)
    [17] Yang H T, Chang W Y, Huang C L.A New Neural Network Approach to On-Line Fault Section Estimation Using Protective Relays and Ciruit Breaker. IEEE PWRD, 1994, 9(1)
    [18]周国忠等.基于分层分布式人工神经网络的大规模电力系统的故障诊断.91全国高校电力系统及其自动化专业学术论文集
    [19]顾雪平等.电力系统故障诊断神经网络专家系统的一种实现方式.电力系统自动化,1995,19(9)
    [20]姜惠兰.联想记忆神经网络的容错性研究及其在输电线路故障识别中的实现.天津大学博士论文
    [21]焦李成.神经网络系统理论.西安:西安电子科技大学出版社,1991
    [22]全国电力工人技术教育供电委员会.变电运行岗位技能培训教材(500KV、200KV).中国电力出版社,1997
    [23]国家电力调度通信中心.电力系统继电保护规定汇编.中国电力出版社,1997

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700