[1]刘仲民,呼彦喆,张 鑫.电网故障智能诊断技术研究综述[J].南京师范大学学报(自然科学版),2019,42(03):138-144.[doi:10.3969/j.issn.1001-4616.2019.03.018]
　Liu Zhongmin,Hu Yanzhe,Zhang Xin.Research Review on Intelligent Fault Diagnosis Technology of Power Grid[J].Journal of Nanjing Normal University(Natural Science Edition),2019,42(03):138-144.[doi:10.3969/j.issn.1001-4616.2019.03.018]
点击复制

电网故障智能诊断技术研究综述()
分享到：

《南京师范大学学报》（自然科学版）[ISSN:1001-4616/CN:32-1239/N]

卷:
第42卷
期数:
2019年03期
页码:
138-144
栏目:
·全国机器学习会议论文专栏·
出版日期:
2019-09-30

文章信息/Info

Title:
Research Review on Intelligent Fault Diagnosis Technology of Power Grid
文章编号:
1001-4616(2019)03-0138-07
作者:
刘仲民1; 呼彦喆2; 张 鑫3
(1.兰州理工大学电气工程与信息工程学院,甘肃 兰州 730050)(2.兰州理工大学电气工程与信息工程学院,甘肃 兰州 730050)(3.国网甘肃省电力公司检修公司,甘肃 兰州 730050)
Author(s):
Liu Zhongmin1; Hu Yanzhe2; Zhang Xin3
(1.Lanzhou University of Technology,Lanzhou University of Technology,Gansu 730050,China)(2.Electrical Engineering & Information Engineering School,Gansu 730050,China)(3.State Grid GANSU Maintenance Company,Gansu 730050,China)
关键词:
电网; 故障诊断; 智能技术; 发展趋势
Keywords:
power grid; fault diagnosis; intelligent technology; the development trend
分类号:
TP277
DOI:
10.3969/j.issn.1001-4616.2019.03.018
文献标志码:
A
摘要:
电网故障诊断技术在国内外应用已十分广泛,随着人工智能的快速发展,基于智能方法的电网故障诊断得到前所未有的发展. 本文对结合专家系统、贝叶斯网络、Petri网、多源信息融合技术、人工神经网络的电网故障诊断原理及框架进行了综述. 根据实际工程的应用情况,对各种智能诊断方法的长处和不足以及各自未来的发展方向进行了详细阐释. 最后以智能电网建设为背景,大数据为依托,利用智能电网故障诊断技术解决所面临的实际问题,并对电网故障诊断技术的未来发展趋势进行了展望.
Abstract:
At present,the fault diagnosis technology of power grid has been widely used at home and abroad. At the same time,power grid fault diagnosis based on intelligent methods has realized unprecedented development with the rapid development of artificial intelligence. In this paper,it makes the summary of the principle and framework of power grid fault diagnosis through the combination of expert system,Bayesian network,Petri network,multi-source information integration technology and artificial neural network. According to the application of practical engineering,it makes the explanation of the advantages and disadvantages of various intelligent diagnosis methods and their future development directions in detail. Finally,it uses the smart grid fault diagnosis technology to solve practical problems under the background of smart grid construction and on the basis of large data,which also looks forward to the prospect of the future development trend of power grid fault diagnosis technology.

参考文献/References:

[1] RUSSELL J C,MASIELLO R D,BOSE A. Power System Control Center Concepts[C]//Power Industry Computer Applications Conference. Minneapolis,Minnesota,USA:IEEE,2002.
[2]FUKUI C,KAWAKAMI J. An expert system for fault section estimation using information from protective relays and circuit breakers[J]. Power delivery IEEE transactions on,1986,1(4):83-90.
[3]DOBAKHSHARI A S,RANJBAR A M. A circuit approach to fault diagnosis in power systems by wide area measurement system[J]. European transactions on electrical power,2013,23(8):1272-1288.
[4]LEE H J,PARK D Y,AHN B S,et al. A fuzzy expert system for the integrated fault diagnosis[J]. IEEE transactions on power delivery,2000,15(2):833-838.
[5]RESHMILA S,DEVANATHAN R. Di-agnosis of power system failures using observer based discrete event system[C]//IEEE International Conference on Control,Measurement and Instrumentation. Kolkata,India,2016.
[6]赵伟,白晓民,丁剑,等. 基于协同式专家系统及多智能体技术的电网故障诊断方法[J]. 中国电机工程学报,2006(20):1-8.
[7]邓武,杨鑫华,赵慧敏,等. 粗糙集、神经网络和专家系统模型用于电力系统故障诊断[J]. 高电压技术,2009,35(7):1624-1628.
[8]李再华,白晓民,周子冠,等. 基于特征挖掘的电网故障诊断方法[J]. 中国电机工程学报,2010,30(10):16-22.
[9]凌子俊,胡超,唐军胜. 基于贝叶斯网络和粗糙集的电网故障诊断方法[J]. 科技视界,2014(31):79,109.
[10]宋功益,王晓茹,周曙. 基于贝叶斯网的电网多区域复杂故障诊断研究[J]. 电力系统保护与控制,2011,39(7):20-25,31.
[11]孙明蔚,童晓阳,刘新宇,等. 运用时序贝叶斯知识库的电网故障诊断方法[J]. 电网技术,2014,38(3):715-722.
[12]罗孝辉,童晓阳. 计及可信度的变结构贝叶斯网络电网故障诊断[J]. 电网技术,2015,39(9):2658-2664.
[13]韩迎春,童晓阳. 基于动态推理链的电网故障诊断方法[J]. 电网技术,2017,41(4):1315-1324.
[14]童晓阳,谢红涛,孙明蔚. 计及时序信息检查的分层模糊Petri网电网故障诊断模型[J]. 电力系统自动化,2013,37(6):63-68.
[15]BINH P T T,TUYEN N D. Fault diagnosis of power system using neural Petri net and fuzzy neural Petri net[C]//Power India Conference. IEEE,New Delhi,India,2006.
[16]谢敏,吴亚雄,黄庶,等. 基于有色自控Petri网的电网故障区域识别[J]. 电力系统保护与控制,2016,44(2):56-64.
[17]谢红涛,童晓阳. 基于分层模糊Petri网的电网故障综合诊断方法[J]. 电网技术,2012,36(1):246-252.
[18]刘同明,夏祖勋,解洪成. 信息融合技术及其应用[M]. 北京:国防工业出版社,1998:12-13.
[19]BEDWORTH M,O’BRIEN J. The Omnibus model:a new model of data fusion?[J]. Aerospace & electronic systems magazine IEEE,2009,15(4):30-36.
[20]韩迎春,童晓阳.利用时空电气量基于灰色关联度的电网故障诊断[J]. 电网技术,2017,41(2):581-588.
[21]JOTA P R S,ISLAM S M,WU T,et al. A class of hybrid intelligent system for fault diagnosis in electric power systems[J]. Neurocomputing,1998,23(1-3):207-224.
[22]刘晓琴,王大志,张翠玲,等. 基于模型预测和溯因推理网络的电网故障诊断方法[J]. 东北大学学报(自然科学版),2016,37(4):472-476,480.
[23]林霞,李瑶,李强,等. 基于多Agent的分层扩展电网故障信息融合处理系统[J]. 电力系统保护与控制,2016,44(21):129-137.
[24]陈哲,江晓燕,岑炳成,等. 基于多种算法融合的区域电网在线故障诊断[J/OL]. 电力系统及其自动化学报:1-7[2019-06-12].
[25]NOVELO A F,CUCARELLA E Q,MORENO E G,et al. Fault diagnosis of electric transmission lines using modular neural networks[J]. IEEE Latin America transactions,2016,14(8):3663-3668.
[26]THUKARAM D,KHINCHA H P,VIJAYNARA S H P. Artificial neural network and support vector Machine approach for locating faults in radial distribution systems[J]. IEEE transactions on power delivery,2005,20(2):710-721.
[27]WU Q L,ZHANG H J. A novel expertise-guided machine learning model for internal fault state diagnosis of power transformers[J].
[28]XIONG G J,SHI D Y,CHEN J F,et al. Divisional fault diagnosis of large-scale power systems based on radial basis function neural network and fuzzy integral[J]. Electric power systems research,2013,105:9-19.
[29]张应军,江永全,杨燕,等. 基于深度卷积神经网络的未知复合故障诊断[J]. 中国科技论文,2019(2):204-209.
[30]孙波,黄建波,陆洁,等. 基于小波SOM神经网络和多Agent系统的微电网故障诊断方法[J]. 舰船电子工程,2018,38(8):151-155,186.
[31]杨彦杰,毛亚峰,唐圣学,等. 基于RTDS和神经网络的光储微电网线路故障诊断[J]. 可再生能源,2018,36(7):1010-1016.
[32]KHOMFOI S,TOLBERT L M. Fault diagnosis system for a multilevel inverter using a neural network[C]//Conference of IEEE Industrial Electronics Society. Paris,France,2006.

备注/Memo

备注/Memo:
收稿日期:2019-04-16. 通讯联系人:呼彦喆,硕士研究生,研究方向:故障诊断. E-mail:zxcv_418175812@qq.com
更新日期/Last Update: 2019-09-30