| 电网技术 2007, 31(1) 37-43 DOI: ISSN: 1000-3673 CN: 11-2410/TM | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 本期目录 | 下期目录 | 过刊浏览 | 高级检索 [打印本页] [关闭] | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 论文 |
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 基于粗糙集理论和朴素贝叶斯网络的电网故障诊断方法 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 张耀天1,何正友1,赵 静1,张 鹏2,李 明3,桂建廷3 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|
1.西南交通大学 电气工程学院,四川省 成都市 610031;2.电力系统保护与动态 安全监控教育部重点实验室(华北电力大学),北京市 昌平区 102206; 3.河南省电力公司 南阳供电公司,河南省 南阳市 473001 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 摘要:
电网发生故障后,当故障信息存在不完整或不确定性,甚至关键信息丢失时,会导致故障诊断难以得出正确结论。针对此问题,文章提出了一种粗糙集理论和朴素贝叶斯网络相结合的电网故障诊断方法。首先以保护、断路器作为条件属性,故障区域作为决策属性,考察各种故障情况并建立决策表,然后利用基于可辨识矩阵和信息熵的属性约简方法提取最佳属性约简组合,最后以最佳属性约简组合形成的约简决策表建立朴素贝叶斯网络模型,并对节点概率进行训练。运用VC++编写了基于该方法的故障诊断软件,算例结果表明,该方法正确、有效,能提高系统在丢失核属性情况下的容错性,具有较好的实用价值。 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 关键词: 故障诊断 粗糙集 贝叶斯网络 约简 信息熵 容错性 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| A Power Network Fault Diagnosis MethodBased on Rough Set Theory and Naive Bayesian Networks | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ZHANG Yao-tian1,HE Zheng-you1,ZHAO Jing1,ZHANG Peng2,LI Ming3,GUI Jian-ting3 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|
1.School of Electrical Engineering,Southwest Jiaotong University,Chengdu 610031,Sichuan Province,China; 2.Key Laboratory of Power System Protection and Dynamic Security Monitoring and Control(North China Electric Power University),Ministry of Education,Changping District,Beijing 102206,China;3.Nanyang Power Supply Company of Henan Provincial Electric Power Company,Nanyang 473001,Henan Province,China | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Abstract:
When power network is in fault, if the fault information is imperfect and indeterminate or even the key information is lost, it may result in the condition that correct conclusion could not be given by fault diagnosis. To settle this problem the authors propose a new method to diagnose faults in power network in which the rough set theory is integrated with naive Bayesian networks. At first, the protections and circuit breakers are taken as conditional attributes and faulty region as decision-making attribute, various faults are investigated and decision table is established; then by use of attribute reducing method based on cognizable matrix and information entropy the optimal attribute reduction combination is extracted; finally, by means of the reduction decision table formed by optimal attribute reduction combination, the naive Bayesian networks model is built and the nodal probability is trained. The fault diagnosis software is programmed by VC++ programming language. Results of calculation examples show that the proposed method is correct and effective, and can improve the fault tolerance capability of the fault diagnosis system while the kernel attribute is lost, so this method is available. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Keywords: fault diagnosis rough set Bayesian networks reduction information entropy fault-tolerance capability | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 收稿日期 1900-01-01 修回日期 1900-01-01 网络版发布日期 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| DOI: | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 基金项目: | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 通讯作者: | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 作者简介: | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 作者Email: | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|
| |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 参考文献: | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| [1] 史述红,杨宛辉,王克文.城市110 kV电网故障元件的快速识别[J].电网技术,2001,25(6):37-40. Shi Shuhong,Yang Wanhui,Wang Kewen.Identification of faulty components in 110 kV urban power networks[J].Power System Technology,2001,25(6):37-40(in Chinese). [2] 文福拴,韩祯祥,田磊,等.基于遗传算法的电力系统故障诊断的解析模型与方法,第一部分:模型与方法[J].电力系统及其自动化学报,1998,10(3):1-7. Wen Fushuan,Han Zhenxiang,Tian Lei,et al.An analytic model and genetic algorithm based methods for fault diagnosis in power systems,part 1:the model and method[J].Proceeding of the EPSA,1998,10(3):1-7(in Chinese). [3] 杜一,张沛超,郁惟镛.基于事例和规则混合推理的变电站故障诊断系统[J].电网技术,2004,28(1):34-37. Du Yi,Zhang Peichao,Yu Weiyong.A substation fault diagnosis system based on case-based reasoning and rule-based reasoning [J].Power System Technology,2004,28(1):34-37(in Chinese). [4] 周明,任建文,李庚银,等.基于模糊推理的分布式电力系统故障诊断专家系统[J].电力系统自动化,2001,25(24):33-36. Zhou Ming,Ren Jianwen,Li Gengyin,et al.Distributed power system fault diagnosis expert system based on fuzzy inference [J].Automation of Electric Power Systems,2001,25(24):33-36(in Chinese). [5] 毕天姝,严正,文福拴,等.基于径向基函数神经网络的在线分布式故障诊断系统[J].电网技术,2001,25(11):27-32,37. Bi Tianshu,Yan Zheng,Wen Fushuan,et al.On-line fault section estimation in power systems with radial basis function neural network[J].Power System Technology,2001,25(11):27-32,37(in Chinese). [6] 毕天姝,倪以信,吴复立,等.基于径向基函数神经网络和模糊控制系统的电网故障诊断新方法[J].中国电机工程学报,2005,25(14):12-18. Bi Tianshu,Ni Yixin,Wu Fuli,et al.Hybrid fault section estimation system with radial basis function neural network and fuzzy system [J].Proceedings of the CSEE,2005,25(14):12-18(in Chinese). [7] 任惠,赵洪山,米增强,等.基于编码Petri 网的电网故障诊断[J].电网技术,2004,28(5):64-68. Ren Hui,Zhao Hongshan,Mi Zengqiang,et al.Power system fault diagnosis by use of encoded Petri net models[J].Power System Technology,2004,28(5):64-68(in Chinese). [8] 任惠,米增强,赵洪山.基于编码Petri网的电力系统故障诊断模型研究[J].中国电机工程学报,2005,25(20):44-49. Ren Hui,Mi Zengqiang,Zhao Hongshan.Power system fault diagnosis modeling techniques based on encoded Petri nets [J].Proceedings of the CSEE,2005,25(20):44-49(in Chinese). [9] 孙静,秦世引,宋永华.模糊Petri 网在电力系统故障诊断中的应用[J].中国电机工程学报,2004,24(9):74-79. Sun Jing,Qin Shiyin,Song Yonghua.Fuzzy Petri nets and its application in the fault diagnosis of electric power systems [J].Proceedings of the CSEE,2004,24(9):74-79(in Chinese). [10] 孙静,秦世引,宋永华.一种基于Petri 网和概率信息的电力系统故障诊断方法[J].电力系统自动化,2003,27(13):10-15. Sun Jing,Qin Shiyin,Song Yonghua.A fault diagnosis method for power systems based on Petri nets and probability information [J].Automation of Electric Power Systems,2003,27(13):10-15(in Chinese). [11] 毕天姝,杨春发,黄少锋,等.基于改进Petri网模型的电网故障诊断方法[J].电网技术,2005,29(21):52-56. Bi Tianshu,Yang Chunfa,Huang Shaofeng,et al.Improved Petri net models based fault diagnosis approach for power networks [J].Power System Technology,2005,29(21):52-56(in Chinese). [12] 文福拴,韩祯祥.基于遗传算法和模拟退火算法的电力系统故障诊断[J].中国电机工程学报,1994,14(3):29-35. Wen Fushuan,Han Zhenxiang.Fault section estimation in power systems using genetic algorithm and simulated annealing [J].Proceedings of the CSEE,1994,14(3):29-35(in Chinese). [13] 文福拴,韩祯祥.基于覆盖集理论和Tabu搜索方法的电力系统警报处理[J].电力系统自动化,1997,21(2):18-24. Wen Fushuan,Han Zhenxiang.A new approach to alarm processing in power systems based upon the set covering theory and Tabu search method[J].Automation of Electric Power Systems,1997,21(2):18-24(in Chinese). [14] 孙伟,李林川,卢庆聪,等.基于停电区域的电力系统故障诊断的一种新模型[J].电网技术,2004,28(5):30-34. Sun Wei,Li Linchuan,Lu Qingcong,et al.A new method for power system fault diagnosis based on power supply interrupted region [J].Power System Technology,2004,28(5):30-34(in Chinese). [15] 汤磊,孙宏斌,张伯明,等.基于信息理论的电力系统在线故障诊断[J].中国电机工程学报,2003,23(7):5-11. Tang Lei,Sun Hongbin,Zhang Boming,et al.Online fault diagnosis for power system based on information theory[J].Proceedings of the CSEE,2003,23(7):5-11(in Chinese). [16] 束洪春,孙向飞,司大军,等.基于粗糙集理论的配电网故障诊断研究[J].中国电机工程学报,2001,21(10):73-82. Shu Hongchun,Sun Xiangfei,Si Dajun,et al.A study of fault diagnosis in distribution line based on rough set theory [J].Proceedings of the CSEE,2001,21(10):73-82(in Chinese). [17] 束洪春,孙向飞,司大军.基于故障投诉电话信息的配电网故障定位粗糙集方法[J].电网技术,2004,28(1):64-66,70. Shu Hongchun,Sun Xiangfei,Si Dajun.A study of fault diagnosis in distribution line based on rough set theory[J].Power System Technology,2004,28(1):64-66,70(in Chinese). [18] 赵冬梅,韩月,高曙.电网故障诊断的决策表约简新算法[J].电力系统自动化,2004,28(4):63-66. Zhao Dongmei,Han Yue,Gao Shu.New reduct algorithm of decision table for electric power grid fault diagnosis[J].Automation of Electric Power Systems,2004,28(4):63-66(in Chinese). [19] 栗然,黎静华,李和明.基于加权平均粗糙度的配电网故障诊断分层模型[J].电网技术,2006,30(2):61-66. Li Ran,Li Jinghua,Li Heming.Fault diagnosis layer model of distribution network based on weighted mean roughness[J].Power System Technology,2006,30(2):61-66(in Chinese). [20] 束洪春,孙向飞,于继来.粗糙集理论在电力系统中的应用[J].电力系统自动化,2004,28(3):90-95. Shu Hongchun,Sun Xiangfei,Yu Jilai.A survey on the application of rough set theory in power systems[J].Automation of Electric Power Systems,2004,28(3):90-95(in Chinese). [21] 霍利民,朱永利,贾兰英,等.基于贝叶斯网络的电网故障诊断方法[J].华北电力学院学报,2004,31(3):30-34. Huo Limin,Zhu Yongli,Jia Lanying,et al.Bayesian networks based novel method for fault section estimation of power[J].Journal of North China Electric Power University,2004,31(3):30-34(in Chinese). [22] 吴欣,郭创新,曹一家.基于贝叶斯网络及信息时序属性的电力系统故障诊断方法[J].中国电机工程学报,2005,25(13):14-18. Wu Xin,Guo Chuangxin,Cao Yijia.A new fault diagnosis approach of power system based on Bayesian network and temporal order information[J].Proceedings of the CSEE,2005,25(13):14-18(in Chinese). [23] 朱永利,吴立增,李雪玉.贝叶斯分类器与粗糙集相结合的变压器综合故障诊断[J].中国电机工程学报,2005,25(10):159-165. Zhu Yongli,Wu Lizeng,Li Xueyu.Synthesized diagnosis on transformer faults based on Bayesian classifier and rough set [J].Proceedings of the CSEE,2005,25(10):159-165(in Chinese). [24] 李波,赵志彦,王秀峰.基于互信息和凝义度相结合的知识约简方法[J].天津大学学报,2003,36(4):503-506. Li Bo,Zhao Zhiyan,Wang Xiufeng.A method of knowledge reduction based on combination of mutual information and doubtful measure[J].Journal of Tianjin University,2003,36(4):503-506(in Chinese). | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 本刊中的类似文章 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 1.王永强 律方成.基于贝叶斯网络的电容型设备故障诊断[J]. 电网技术, 2009,33(17): 222-225 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 2.刘超 何正友 杨建维 .基于量子神经网络的电网故障诊断算法[J]. 电网技术, 2008,32(9): 56-59 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 3.梅 念|石东源|杨雄平|段献忠.基于开关变位信息的电网可疑故障元件集识别方法[J]. 电网技术, 2007,31(15): 80-84 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 4.张 强|张建民|薛丽华.基于快速通信机制的馈线自动化系统[J]. 电网技术, 2007,31(Supp): 141-144 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 5.钱 奇|刘 军|钱建军.电气设备绝缘监督管理系统的设计与实现[J]. 电网技术, 2007,31(Supp2): 14-17 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 6.熊 浩|李卫国|黄彦浩|张海峰|畅广辉.基于模糊粗糙集理论的综合数据挖掘方法在空间负荷预测中的应用[J]. 电网技术, 2007,31(14): 36-40 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 7.殷志鹏.远程控制航模巡线的可行性分析和展望[J]. 电网技术, 2007,31(Supp): 221-223 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 8.周爱华 张彼德 方春恩 李伟 .基于模糊免疫识别方法的电力变压器故障诊断[J]. 电网技术, 2009,33(3): 99-102 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 9.张国华|张建华|杨志栋|彭谦|杨京燕 .电力系统N-K故障的风险评估方法[J]. 电网技术, 2009,33(5): 17-21 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 10.张彦.基于多目标优化随机权系数加权和的机组负荷分配[J]. 电网技术, 2008,32(26): 64-67 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 11.王锡淮,张腾飞,肖健梅 .基于粗糙径向基函数网络的船舶发电机励磁控制[J]. 电网技术, 2007,31(24): 66-71 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 12.耿艳 韩学山 韩力 .基于最小二乘支持向量机的短期负荷预测[J]. 电网技术, 2008,32(18): 72-76 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 13.罗国敏 何正友 林圣 .利用小波相对熵值的差异识别输电线路暂态信号的探讨[J]. 电网技术, 2008,32(15): 46-51 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 14.窦东阳 赵英凯 .基于C语言集成产生式系统的火电厂实时故障诊断系统[J]. 电网技术, 2008,32(9): 89-92 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 15.潘 超|岳建平|刘 冰|于景龙 .基于适应型Petri网的电网故障诊断方法[J]. 电网技术, 2008,32(1): 46-50 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Copyright by 电网技术 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||