粗糙集及神经网络在配电网故障诊断中的应用研究
|
摘要
随着我国电网联网工程的顺利完成，电网规模不断扩大和加强，当电网发生故障时，要判定故障区域将是一件比较困难的事情。为此，本文尝试借助粗糙集理论所具有分析约简能力，提出了基于可辨识矩阵与布尔代数相结合的属性约简算法以及改进的值约简算法，并将其应用于由断路器和保护为条件属性，考虑各种故障情况所组成的诊断决策表的约简过程中，形成了故障诊断总体规则知识库模型，从算例结果看基本达到了实际应用设计要求，但也存在一个缺陷，即粗糙集的容错能力还不够理想，当核属性受噪声污染时有可能会出现误判的情况。因此为了提高粗糙集的容错能力，将粗糙集理论与神经网络相结合，构建粗糙集和神经网络智能混合系统，充分利用粗糙集理论对知识的约简能力和神经网络的容错学习能力。首先利用粗糙集方法对原始数据进行约简，形成精简的规则集，然后神经网络通过调用最简规则集进行学习训练，这样既减少了神经网络的学习训练时间，又提高了诊断的准确度。最后对21个测试样本数据进行测试仿真，仿真结果表明该算法具有高容错性和高诊断正确率(100％)，很好的满足了配电网故障诊断的要求。
Along with the completion of the networking project of electrical network of our country, the scale of electrical network enlarges and strengthens constantly. When electrical network breaks down, it will be difficult to judge fault areas. So, this paper attempts with the aid of the Rough Set theory, presenting a new attribute reduction arithmetic as well as an improved value reduction arithmetic based on the combination of the Rough Set theory and the Boolean calculation, and using it to handle the reduction progress of the decision table including all kinds of fault cases which is established by considering the signals of protection relays and circuit breakers, and last forming a model of fault diagnosis overall regular knowledge base. Since looked from the example results, it has basically met the practical application design requirements, but it still has a flaw, which is that the fault-tolerance ability of the Rough Set theory is also insufficient ideal. When core attributes are polluted by noise, it may arouse error judgment. Therefore in order to enhance the fault-tolerance ability of Rough Set theory, unify Rough Set theory and Neural Network, construct an intelligent mixture system of Rough Set theory and neural Network, which fully develops the reduction ability of Rough Set theory and the classification ability of Neural Network. First, use Rough Set theory to form a simple rule collection from the reduction of original data, and then neural network carries on the study training through using the simple rule collection. Like this it can both reduce the neural network training time, and enhance the diagnosis accuracy. Finally, carry on the test simulation to 21 test sample data, the simulation results indicate that this algorithm has high fault-tolerance ability and high diagnosis correct rate (100%), which has satisfied the requirement of distribution network fault diagnosis very well.
Along with the completion of the networking project of electrical network of our country, the scale of electrical network enlarges and strengthens constantly. When electrical network breaks down, it will be difficult to judge fault areas. So, this paper attempts with the aid of the Rough Set theory, presenting a new attribute reduction arithmetic as well as an improved value reduction arithmetic based on the combination of the Rough Set theory and the Boolean calculation, and using it to handle the reduction progress of the decision table including all kinds of fault cases which is established by considering the signals of protection relays and circuit breakers, and last forming a model of fault diagnosis overall regular knowledge base. Since looked from the example results, it has basically met the practical application design requirements, but it still has a flaw, which is that the fault-tolerance ability of the Rough Set theory is also insufficient ideal. When core attributes are polluted by noise, it may arouse error judgment. Therefore in order to enhance the fault-tolerance ability of Rough Set theory, unify Rough Set theory and Neural Network, construct an intelligent mixture system of Rough Set theory and neural Network, which fully develops the reduction ability of Rough Set theory and the classification ability of Neural Network. First, use Rough Set theory to form a simple rule collection from the reduction of original data, and then neural network carries on the study training through using the simple rule collection. Like this it can both reduce the neural network training time, and enhance the diagnosis accuracy. Finally, carry on the test simulation to 21 test sample data, the simulation results indicate that this algorithm has high fault-tolerance ability and high diagnosis correct rate (100%), which has satisfied the requirement of distribution network fault diagnosis very well.
引文
1 Xu Kali, Zhou Ming, Ren Jianwen. An Object-Oriented Power System Fault Diagnosis Expert System. ImInternational Conference on Electrical Engineering 1999(ICEE99). Hung Kong: 1999
2 朱永利．电力系统故障判断专家系统[J]．华北电力学院学报，1992，NO．1：1～7
3 文福栓．只利用断路器信息诊断电力系统故障的高级遗传算法[J]．电工技术学报，1996 11(2)：58～64
4 Young Moon Park, Gwang-Won Kim, Jin-Man Sohn. A Logic Base Expert System (LBES) for Fault Diagnosis of Power System. IEEE Transactions on Power Systems, 1997, 12(1): 363～369
5 刘青松．基于正反向推理的电力系统故障诊断专家系统[J]．电网技术，1998，9
6 文福栓．利用保护和断路器信息的电力系统故障诊断与不可观测的保护的状态识别的模型Tabu搜索方法[J]．电工技术学报，1998，13(5)：1～8
7 顾雪平，张文朝，基丁Tabu搜索技术的暂态稳定分类神经网络的输入特征选择[J]．中国电机工程学报，2002，22(7)：66～70
8 Ernesto Vazquez M, Oscar L, Chacon M, et al. An On-Line Expert System for Fault Section Diagnosis in Power Systems. IEEE Transactions on Power Systems, 1997, 12(1): 357～362
9 Juhwan Jung, Chen-Ching Liu, Mingguo Hung. Multiple Hypotheses and Their Credibility in On-Line Fault Diagnosis. IEEE Transactions on Power Delivery 2001, 16(2): 225～230
10 C Yang, HO kamoto, etal. Expert System for Fault Section Estimation of Power System Using Time Sequence Information. In Proceeding of 3rd Symposium on Expert System Application to Power Systems. April 1991, Tokyo-Kobo, Japan: 587～594
11 Liu Chenching Sforna M, Miao Hanjin. On-Line Fault Diagnosis UsingSequence-of-Events Recorder Information. In: Proceedings of 1996 International Conference on Intelligent System Applications to Power Systems(ISAP' 96). Orlando(USA): 1996:339～344
12 文福栓．计及警报信息时间特性的故障诊断模型[J]．电力系统自动化，1999，23(17)：6～9
13 T Minakawa, M Kunugi, K Shimada. Development and Implementation of a Power System Fault Diagnosis Expert System. IEEE Transactions on Power Systems, 1995, Vol10, No.2:932～939
14 骆敬年．华东500kV电网故障录波器联网系统[J]．华东电力，2000，1：4～6
15 孙晓凌，郑群．微机型故障录波器联网系统的设计与实现[J]．电力系统通信 1999，4：23～25
16 Yang H T, Chang W YHuang C L. Power System Distributed On-Line Fault Section Estimation Using Decision Tree Based Neural Nets Approach. IEEE Transactions on Power Delivery, 1995, 10(1): 540～546
17 Aygen Z E, Seker S, Bagriyanik M, et at. Fault Section Estimation in Electrical Power Systems Using Artificial Neural Network Approach. In: IEEE Transmission and Distribution Conference. New Orleans(LA): 1999
18 刘应梅．人工神经网络在变电站故障诊断中的应用[J]．99全国高校电力系统及其自动化专业 学术论文集
19 Park D YAhn BS, Kim SH, et al. Dealing Uncertainties in the Fault Diagnosis System. In: ISAP' 99. Rio de Janeiro(Brazil): 1999
20 Hyun Joon Cho, Jong Keun Park. An Expert System for Fault Section Diagnosis of Power Systems using Fuzzy Relations. IEEE Transactions on Power Systems, 1996, Vol12, No.1: 342～347
21 文福拴，邱家驹，韩祯祥．只利用断路器信息诊断电力系统故障的高级遗传算法[J]．电工技术学报，1996．4，11(2)
22 文福拴，韩祯祥．基于遗传算法的电力系统故障诊断的解析模型与方法(一)[J]．电力系统及其自动化学报，1998，10(9)：1～7
23 文福拴，韩祯祥．基于遗传算法的电力系统故障诊断的解析模型与方法(二)[J]．电力系统及其自动化学报，1998，10(9)：8～13
24 文福拴，韩祯祥．基于遗传算法的电力系统故障诊断的解析模型与方法(三)[J]．电力系统及其自动化学报，1999，11(3)：8～13
25 Wen F S, Chang C S.Probabilistic-Diagnosis Theory for Fault-Section Estimation and State Identification of Unobserved Protective Relays Using Tabu-Search Method.IEE Proceedings Generation, Transmission and Distribution, 1998, 145(6): 722～730
26 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)
27 文福拴，韩祯祥．基于Tabu搜索方法的输电系统最优规划[J]．电网技术，1997，21(5)：2～7
28 文福拴，钱源平．利用保护和断路器信息的电力系统故障诊断与不可观测的保护的状态识别的模型与Tabu搜索方法[J]．电工技术学报，1998，13(5)
29 王凌．智能优化算法及其应用[M]．清华大学出版社，2001，10
30 文福拴，韩祯祥．基于遗传算法和模拟退火算法的电力系统的故障诊断[J]．中国电机工程学报，1994，14 (3)
31 Lo K L, Ng H S, Trecat J. Power Systems Fault Diagnosis Using Petri Nets. IEE Proceedings Generations, Transmissions and Distributions, 1997, 144(3): 231～236
32 Roh M GHong SE Oh Y T. Modeling of Protection System and Fault Diagnosis Using Petri Nets for Power Systems.In International Conference on Electrical Engineering 1999(ICEE' 99).Hong Kong, 1999: 243～246
33 李日隆，李雄刚，利用Petri网对电力系统进行故障诊断[J]．华中电力，2000，13(1)：1～4
34 赵洪山，米增强，杨奇逊．基于冗余嵌入Petri网技术的变电站故障诊断[J]．电力系统自动化，2002，13(4)：32～35
35 Gu X P, Yang Y H, Zhang W Qet al.Integration of Artificial Neural Networks and Expert Systems for Power System Fault Diagnosis.Proc of IPEC' 95, Singapore: 1995, 2
36 何定，唐国庆，陈晰．神经元网络、专家系统及其结合的研究[J]．全国高校电自专业第九届学术年会论文集，南京：东南大学，1992，10
37 顾雪平，盛四清，张文勤．电力系统故障诊断神经网络专家系统的一种实现方式[J]．电力系统自动化，1995，19(9)
38 Pawlak Z.Rough Set.International Journal of Computer and Information Sciences. 1982, 11: 341～356
39 Pawlak Z.Rough Set. Theoretical Aspects of Reasoning About Data.Dorrecht (Netherland): Kluwer Academic Publishers, 1991
40 Pawlak Z. Grzymala-Buses J, Slowinski R, et al. Rough Sets. Communication of ACM, 1995, 38(11): 89～95
41 胡可云，陆玉昌，石纯一．粗糙集理论及其应用进展[J]．清华大学学报(目然科学版)，2001，41(1)：64～68
42 韩祯祥．张琦，文福拴．粗糙集理论及其应用综述[J]，控制理论与应用，1999，16(2)：153～157
43 王开，苗夺谦，周育健．关于Rough Set理论与应用的综述模式识别与人工智能[J]，1996，9(4)：337～344
44 梁吉业，曲开社，徐宗本．信息系统的属性约简[J]．系统工程理论与实践，2001，21(12)：76～80．
45 曾黄麟．粗糙集理论及其应用(修订版)[M]．重庆大学出版社，1998
46 刘同明．数据挖掘技术及其应用[M]．国防工业出版社，北京 2001
47 Germano Lambert-Torres Application of Rough Sets in Power Control Center Data Mining.IEEE 0-7803-7322-7/02:627～631
48 Zhang Qi, Han Zhenxiang, Wen Fushuan. A New Approach for Fault Diagnosis in Power Systems Based on Rough Set Theory. In: Proceedings of 4th International Conference on Advances in Power System Control, Operation &Management. Hong Kong, 1997:597～602
49 束洪春，孙向飞，司大军．电力变压器故障诊断专家系统知识库建立和维护的粗糙集方法[J]．电机工程学报，2002，22(2)：31～35
50 张琦，韩祯祥，文福拴．一种基于粗糙集理论的电力系统故障诊断和警报处理新方法[J]．中国电力，1998，31(4)：32～38
51 贺家李，宋从矩．电力系统继电保护原理[M]．中国电力出版社，1994
52 增乐，黄馥林．离散数学[M]．华东师范大学出版社，1984
53 傅彦，顾小丰．离散数学及其应用[M]．电子工业出版，1997
54 贾永红．计算机图像处理与分析[M]．武汉：武汉大学出版社，2001．
55 郝丽娜，徐心和．粗糙集神经网络系统在故障诊断中的应用[J]．控制理论与应用，2001，5
56 毕天妹，严正，文福栓．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)：27～3
57 孙增圻．智能控制理论与技术[M]．清华大学出版社，广西科学技术出版社，1997
58 吴今培，肖健华．智能故障诊断与专家系统[M]．北京：科学出版社，1997
59 贵忠华，刘振凯．智能混合系统研究综述[J]．信息与控制，2000，29(1)：59～64
60 陈遵德．Rough Set神经网络智能系统及其应用[J]．模式识别与人工智能，1999，12(1)
61 刘璨，陈统坚，彭永红．基于粗糙集理论的模糊神经网络建模方法研究[J]．中国机械工程，2001，12(11)：1256～1259
2 朱永利．电力系统故障判断专家系统[J]．华北电力学院学报，1992，NO．1：1～7
3 文福栓．只利用断路器信息诊断电力系统故障的高级遗传算法[J]．电工技术学报，1996 11(2)：58～64
4 Young Moon Park, Gwang-Won Kim, Jin-Man Sohn. A Logic Base Expert System (LBES) for Fault Diagnosis of Power System. IEEE Transactions on Power Systems, 1997, 12(1): 363～369
5 刘青松．基于正反向推理的电力系统故障诊断专家系统[J]．电网技术，1998，9
6 文福栓．利用保护和断路器信息的电力系统故障诊断与不可观测的保护的状态识别的模型Tabu搜索方法[J]．电工技术学报，1998，13(5)：1～8
7 顾雪平，张文朝，基丁Tabu搜索技术的暂态稳定分类神经网络的输入特征选择[J]．中国电机工程学报，2002，22(7)：66～70
8 Ernesto Vazquez M, Oscar L, Chacon M, et al. An On-Line Expert System for Fault Section Diagnosis in Power Systems. IEEE Transactions on Power Systems, 1997, 12(1): 357～362
9 Juhwan Jung, Chen-Ching Liu, Mingguo Hung. Multiple Hypotheses and Their Credibility in On-Line Fault Diagnosis. IEEE Transactions on Power Delivery 2001, 16(2): 225～230
10 C Yang, HO kamoto, etal. Expert System for Fault Section Estimation of Power System Using Time Sequence Information. In Proceeding of 3rd Symposium on Expert System Application to Power Systems. April 1991, Tokyo-Kobo, Japan: 587～594
11 Liu Chenching Sforna M, Miao Hanjin. On-Line Fault Diagnosis UsingSequence-of-Events Recorder Information. In: Proceedings of 1996 International Conference on Intelligent System Applications to Power Systems(ISAP' 96). Orlando(USA): 1996:339～344
12 文福栓．计及警报信息时间特性的故障诊断模型[J]．电力系统自动化，1999，23(17)：6～9
13 T Minakawa, M Kunugi, K Shimada. Development and Implementation of a Power System Fault Diagnosis Expert System. IEEE Transactions on Power Systems, 1995, Vol10, No.2:932～939
14 骆敬年．华东500kV电网故障录波器联网系统[J]．华东电力，2000，1：4～6
15 孙晓凌，郑群．微机型故障录波器联网系统的设计与实现[J]．电力系统通信 1999，4：23～25
16 Yang H T, Chang W YHuang C L. Power System Distributed On-Line Fault Section Estimation Using Decision Tree Based Neural Nets Approach. IEEE Transactions on Power Delivery, 1995, 10(1): 540～546
17 Aygen Z E, Seker S, Bagriyanik M, et at. Fault Section Estimation in Electrical Power Systems Using Artificial Neural Network Approach. In: IEEE Transmission and Distribution Conference. New Orleans(LA): 1999
18 刘应梅．人工神经网络在变电站故障诊断中的应用[J]．99全国高校电力系统及其自动化专业 学术论文集
19 Park D YAhn BS, Kim SH, et al. Dealing Uncertainties in the Fault Diagnosis System. In: ISAP' 99. Rio de Janeiro(Brazil): 1999
20 Hyun Joon Cho, Jong Keun Park. An Expert System for Fault Section Diagnosis of Power Systems using Fuzzy Relations. IEEE Transactions on Power Systems, 1996, Vol12, No.1: 342～347
21 文福拴，邱家驹，韩祯祥．只利用断路器信息诊断电力系统故障的高级遗传算法[J]．电工技术学报，1996．4，11(2)
22 文福拴，韩祯祥．基于遗传算法的电力系统故障诊断的解析模型与方法(一)[J]．电力系统及其自动化学报，1998，10(9)：1～7
23 文福拴，韩祯祥．基于遗传算法的电力系统故障诊断的解析模型与方法(二)[J]．电力系统及其自动化学报，1998，10(9)：8～13
24 文福拴，韩祯祥．基于遗传算法的电力系统故障诊断的解析模型与方法(三)[J]．电力系统及其自动化学报，1999，11(3)：8～13
25 Wen F S, Chang C S.Probabilistic-Diagnosis Theory for Fault-Section Estimation and State Identification of Unobserved Protective Relays Using Tabu-Search Method.IEE Proceedings Generation, Transmission and Distribution, 1998, 145(6): 722～730
26 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)
27 文福拴，韩祯祥．基于Tabu搜索方法的输电系统最优规划[J]．电网技术，1997，21(5)：2～7
28 文福拴，钱源平．利用保护和断路器信息的电力系统故障诊断与不可观测的保护的状态识别的模型与Tabu搜索方法[J]．电工技术学报，1998，13(5)
29 王凌．智能优化算法及其应用[M]．清华大学出版社，2001，10
30 文福拴，韩祯祥．基于遗传算法和模拟退火算法的电力系统的故障诊断[J]．中国电机工程学报，1994，14 (3)
31 Lo K L, Ng H S, Trecat J. Power Systems Fault Diagnosis Using Petri Nets. IEE Proceedings Generations, Transmissions and Distributions, 1997, 144(3): 231～236
32 Roh M GHong SE Oh Y T. Modeling of Protection System and Fault Diagnosis Using Petri Nets for Power Systems.In International Conference on Electrical Engineering 1999(ICEE' 99).Hong Kong, 1999: 243～246
33 李日隆，李雄刚，利用Petri网对电力系统进行故障诊断[J]．华中电力，2000，13(1)：1～4
34 赵洪山，米增强，杨奇逊．基于冗余嵌入Petri网技术的变电站故障诊断[J]．电力系统自动化，2002，13(4)：32～35
35 Gu X P, Yang Y H, Zhang W Qet al.Integration of Artificial Neural Networks and Expert Systems for Power System Fault Diagnosis.Proc of IPEC' 95, Singapore: 1995, 2
36 何定，唐国庆，陈晰．神经元网络、专家系统及其结合的研究[J]．全国高校电自专业第九届学术年会论文集，南京：东南大学，1992，10
37 顾雪平，盛四清，张文勤．电力系统故障诊断神经网络专家系统的一种实现方式[J]．电力系统自动化，1995，19(9)
38 Pawlak Z.Rough Set.International Journal of Computer and Information Sciences. 1982, 11: 341～356
39 Pawlak Z.Rough Set. Theoretical Aspects of Reasoning About Data.Dorrecht (Netherland): Kluwer Academic Publishers, 1991
40 Pawlak Z. Grzymala-Buses J, Slowinski R, et al. Rough Sets. Communication of ACM, 1995, 38(11): 89～95
41 胡可云，陆玉昌，石纯一．粗糙集理论及其应用进展[J]．清华大学学报(目然科学版)，2001，41(1)：64～68
42 韩祯祥．张琦，文福拴．粗糙集理论及其应用综述[J]，控制理论与应用，1999，16(2)：153～157
43 王开，苗夺谦，周育健．关于Rough Set理论与应用的综述模式识别与人工智能[J]，1996，9(4)：337～344
44 梁吉业，曲开社，徐宗本．信息系统的属性约简[J]．系统工程理论与实践，2001，21(12)：76～80．
45 曾黄麟．粗糙集理论及其应用(修订版)[M]．重庆大学出版社，1998
46 刘同明．数据挖掘技术及其应用[M]．国防工业出版社，北京 2001
47 Germano Lambert-Torres Application of Rough Sets in Power Control Center Data Mining.IEEE 0-7803-7322-7/02:627～631
48 Zhang Qi, Han Zhenxiang, Wen Fushuan. A New Approach for Fault Diagnosis in Power Systems Based on Rough Set Theory. In: Proceedings of 4th International Conference on Advances in Power System Control, Operation &Management. Hong Kong, 1997:597～602
49 束洪春，孙向飞，司大军．电力变压器故障诊断专家系统知识库建立和维护的粗糙集方法[J]．电机工程学报，2002，22(2)：31～35
50 张琦，韩祯祥，文福拴．一种基于粗糙集理论的电力系统故障诊断和警报处理新方法[J]．中国电力，1998，31(4)：32～38
51 贺家李，宋从矩．电力系统继电保护原理[M]．中国电力出版社，1994
52 增乐，黄馥林．离散数学[M]．华东师范大学出版社，1984
53 傅彦，顾小丰．离散数学及其应用[M]．电子工业出版，1997
54 贾永红．计算机图像处理与分析[M]．武汉：武汉大学出版社，2001．
55 郝丽娜，徐心和．粗糙集神经网络系统在故障诊断中的应用[J]．控制理论与应用，2001，5
56 毕天妹，严正，文福栓．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)：27～3
57 孙增圻．智能控制理论与技术[M]．清华大学出版社，广西科学技术出版社，1997
58 吴今培，肖健华．智能故障诊断与专家系统[M]．北京：科学出版社，1997
59 贵忠华，刘振凯．智能混合系统研究综述[J]．信息与控制，2000，29(1)：59～64
60 陈遵德．Rough Set神经网络智能系统及其应用[J]．模式识别与人工智能，1999，12(1)
61 刘璨，陈统坚，彭永红．基于粗糙集理论的模糊神经网络建模方法研究[J]．中国机械工程，2001，12(11)：1256～1259