基于粗糙集理论和Petri网的电力变压器故障诊断
|
摘要
电力变压器是电力系统中最重要的电气设备之一,也是导致电力系统事故最多的电气设备之一,其运行状态直接影响系统的安全性水平。及早发现变压器的潜伏性故障,保证变压器的安全运行,从而提高供电的可靠性,是电力部门关注的一个重要问题。因此,研究变压器故障诊断技术,提高变压器的运行维护水平,具有重要的现实意义。
本文主要对电力变压器故障性质的诊断和故障部位的诊断方法进行研究。
首先,针对变压器故障气体与故障类型的关系,建立结构为5-12-6型的变压器故障诊断人工神经网络模型。采用6种改进BP(Back-Propagation)算法及原最速梯度下降法对已建立的网络模型进行训练,使用训练好的网络模型对变压器样本进行故障性质的诊断。通过仿真比较了6种改进BP算法在变压器故障诊断中的性能优劣。
其次,利用粗糙集理论对不完备的变压器故障信息决策表进行属性约简和规则的提取,得到决策表中隐藏的规则(即“if...then...”规则),利用此规则构建Petri网络模型,并利用Petri网进行故障诊断。将粗糙集理论与Petri网结合起来一同进行变压器故障部位的诊断。
最后,通过故障实例验证了,基于人工神经网络对变压器故障性质的诊断和基于粗糙集理论和Petri网对变压器故障部位的诊断都能准确的、快速的得到诊断结果,达到预期效果。
Power transformer is one of the most important electrical equipments in the electric system, and is also one of the electrical equipments resulting in most electric system accidents. Its operating state affects system’s security level directly. It is an important issue for electrical department to find the potential faults of the transformer, to keep it operating safely, and to improve the reliability or power supply. Therefore, it is of great realistic significance to study the fault diagnosis technology of transformer and to increase the operating and maintaining level of transformer.
This paper applies the power transformer fault quality diagnosis and fault location diagnosis synchronously.
Firstly, research of the relationship between fault types and dissolved gas, a type of 5-12-6 artificial neural network model for transformer fault diagnosis is established. Using of six improved back-propagation network algorithms and fast gradient drop algorithm to train the established artificial neural network, using of transformer data samples to the trained network model and processing fault quality diagnosis. Through the practical fault examples compare the fault diagnosis performance of six improved BP algorithms.
Secondly, through rough set theory reduce the attribute of incomplete information table and extract rules, gain the potential and diagnostic rules (if…then…rules), and then based on these rules, the optimum petri nets are built, and through the petri nets calculate fault diagnosis. Rough set theory and petri nets are integrated for fault location diagnosis of transformer.
Finally, the correctness and speediness of fault quality diagnosis of transformer based on artificial neural network and fault location diagnosis of transformer based on rough set theory and petri nets are validated by the practical fault examples. Meanwhile, fault diagnosis results can achieve the prospective effects.
本文主要对电力变压器故障性质的诊断和故障部位的诊断方法进行研究。
首先,针对变压器故障气体与故障类型的关系,建立结构为5-12-6型的变压器故障诊断人工神经网络模型。采用6种改进BP(Back-Propagation)算法及原最速梯度下降法对已建立的网络模型进行训练,使用训练好的网络模型对变压器样本进行故障性质的诊断。通过仿真比较了6种改进BP算法在变压器故障诊断中的性能优劣。
其次,利用粗糙集理论对不完备的变压器故障信息决策表进行属性约简和规则的提取,得到决策表中隐藏的规则(即“if...then...”规则),利用此规则构建Petri网络模型,并利用Petri网进行故障诊断。将粗糙集理论与Petri网结合起来一同进行变压器故障部位的诊断。
最后,通过故障实例验证了,基于人工神经网络对变压器故障性质的诊断和基于粗糙集理论和Petri网对变压器故障部位的诊断都能准确的、快速的得到诊断结果,达到预期效果。
Power transformer is one of the most important electrical equipments in the electric system, and is also one of the electrical equipments resulting in most electric system accidents. Its operating state affects system’s security level directly. It is an important issue for electrical department to find the potential faults of the transformer, to keep it operating safely, and to improve the reliability or power supply. Therefore, it is of great realistic significance to study the fault diagnosis technology of transformer and to increase the operating and maintaining level of transformer.
This paper applies the power transformer fault quality diagnosis and fault location diagnosis synchronously.
Firstly, research of the relationship between fault types and dissolved gas, a type of 5-12-6 artificial neural network model for transformer fault diagnosis is established. Using of six improved back-propagation network algorithms and fast gradient drop algorithm to train the established artificial neural network, using of transformer data samples to the trained network model and processing fault quality diagnosis. Through the practical fault examples compare the fault diagnosis performance of six improved BP algorithms.
Secondly, through rough set theory reduce the attribute of incomplete information table and extract rules, gain the potential and diagnostic rules (if…then…rules), and then based on these rules, the optimum petri nets are built, and through the petri nets calculate fault diagnosis. Rough set theory and petri nets are integrated for fault location diagnosis of transformer.
Finally, the correctness and speediness of fault quality diagnosis of transformer based on artificial neural network and fault location diagnosis of transformer based on rough set theory and petri nets are validated by the practical fault examples. Meanwhile, fault diagnosis results can achieve the prospective effects.
引文
1王晓莺.变压器故障与监测.北京:机械工业出版社, 2004: 1-5
2钱之银,陆志浩,楼其民等.变压器油中溶解气体判断方法综述.高压电器, 2002, 38(6): 34-37
3李俭.大型电力变压器以油中溶解气体为特征量的内部故障诊断模型研究. [重庆大学工学博士论文]. 2001: 26-28
4 Mohamed. E. A, Abdelaziz. A. Y, Mostafa A. S, et. al. A Neural Network-based Scheme for Dault Diagnosis of Power Transformers. Electric Power Systems Research, 2005, 75(1): 29-39
5 Chen Weigen, Pan Chong, Yun Yuxin. Wavelet Networks in Power Transformers Diagnosis using Dissolved Gas Analysis. IEEE Transactions on Power Delivery, 2009, 24(1): 187-194
6胡汉梅,鲍亮亮,赵海军.神经网络在变压器故障诊断中典型算法研究.高压电器, 2008, 44(3): 217-220
7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理论方法.中国电机工程学报, 2002, 22(2): 31-35
8 Lautre Nitin. K, Manna Alakesh. A Study on Fault Diagnosis and Maintenance of CNC-WEDM based on Binary Relational Analysis and Expert System. International Journal of Advanced Manufacturing Technology, 2006, 29(5): 490-498
9孙才新,郭俊峰,郑海平等.基于行为的变压器油色谱分析模糊诊断专家系统.电工技术学报, 2001, 16(3): 49-52
10 Su. Q, Mi. C, Lai. L. A Fuzzy Dissolved Gas Analysis Method for the Diagnosis of Multiple Faults in a Transformer. IEEE Transactions on Power System, 2006, 15(2): 593-598
11 Islam. S. M, Wu. T, Ledwich. G. A Novel Fuzzy Logic Approach to Transformer Fault Diagnosis. IEEE Transactions on Dielectrics and Electrical Insulation, 2006, 7(2): 177-186
12符杨,江玉蓉,崔椿洪.基于模糊数学和概率论的变压器故障诊断.高电压技术, 2008, 34(5): 1040-1044
13 Dong Lixin, Xiao Dengming, Liu Yilu, et. al. Insulation Fault Diagnosis Based on Group Grey Relational Grade Analysis Method for Power Transformers. Journal of Southeast University(English Edition), 2005, 21(2): 175-179
14 Lin Chaihung, Huang Pingzan, Wu Chen, et. al. Grey Clustering Analysis for Incipient Fault Diagnosis in Oil-immersed Transformers. Expert Systems with Applications, 2009, 36(2): 1371-1379
15 Zhang Zheng, Xiao Dengming, Liu Yilu. Insulation Fault Diagnosis of Power Transformers by Genetic Programming based Polynomial Networks Model. WSEAS Transactions on Circuits and Systems, 2006, 5(1): 79-84
16孙秋野,张化光,刘鑫蕊.基于粗糙集和遗传算法的变压器故障诊断方法,仪器仪表学报, 2008, 29(10): 2034-2040
17 Pawlak. Z. Rough sets. International Journal of Computer and Information Sciences, 1982, 11(3): 341-356
18 Li Xiaoou, Yu Wen, Lara. Rosano. F. Dynamic Knowledge Inference and Learning under Adaptive Fuzzy Petri net Framework. IEEE Transactions on Power Systems, 2000, 30(4): 442-449
19彭宁云.基于DGA技术的变压器故障智能诊断系统研究. [武汉大学工学博士论文]. 2001: 6-9
20中华人民共和国电力工业部. DL/T596-1996《电气设备预防性试验规程》.北京:中国电力出版社, 2000, 10-15
21徐安定.大型变压器状态监测与故障诊断技术. [浙江大学工学硕士论文]. 2005: 15-16
22何志强,文习山,陈旭.基于粗糙集理论的变压器故障的诊断.高电压技术. 2006, 32(6): 27-30
23 Duval, Michel. Calculation of DGA Limit Values and Sampling Intervals in Transformers in Service. IEEE Electrical Insulation Magazine, 2008, 24(5): 7-13
24包中福.电力变压器内部故障诊断的特征气体法及其应用研究. [重庆大学工程硕士论文]. 2004: 46-51
25 Sun Yanjing, Li Jingmeng, Miao Changxin. Improved BP Neural Network for Transformer Fault Diagnosis. Journal of China University of Mining and Technology, 2007, 17(1): 138-142
26 Liang Liuming, Chen Weigen, Yue YanFeng. Study on Power Transformers Fault Diagnosis based on Wavelet Neural Network and D-S Evidence Theory. High Voltage Engineering, 2008, 34(12): 2694-2700
27 Cang S, Yu H. Novel Probability Neural Network. IEE Proceedings: Vision, Image and Signal Processing, 2005, 152(5): 535-544
28闻新,周露,李翔等. MATLAB神经网络仿真与应用.北京:科学出版社, 2003: 264-274
29 Sun Yanjing, Zhang Shenmiao, Chang xin. Improved BP Neural Network for Transformer Fault Diagnosis. Journal of China University of Mining and Technology, 2007, 17(1): 138-142
30哈根.神经网络设计.北京:机械工业出版社, 2002, 143-145
31周开利,康耀红.神经网络模型及其MATLAB仿真程序设计.北京:清华大学出版社, 2005: 74-86
32 Wu Jianda, Liu Chiuhong. Investigation of Engine Fault Diagnosis using Discrete Wavelet Transform and Neural Network. Expert Systems with Applications, 2008, 35(3): 1200-1213
33王国胤. Rough集理论与知识获取.西安:西安交通大学出版社, 2001: 14-20
34 Zhang Weizheng, Li Yanming, Yang Lanjun. The Fault Diagnosis of Power Transformer based on Rough Set Theory. WSEAS Transactions on Circuits and Systems, 2005, 4(8): 912-916
35王庆东,陈建.不完备信息系统的粗糙集分解方法.计算机工程, 2007, 33(24): 41-43
36王国胤. Rough集理论在不完备信息系统中的扩充.计算机研究与发展, 2002, 39(10): 1238-1243
37黄文涛,王伟杰,赵学增等.从不完备数据中获取诊断规则的粗糙集方法.电力系统自动化, 2005, 29(14): 49-54
38张腾飞,王锡淮,肖健梅.不完备信息系统的一种属性相对约简算法.计算机工程, 2007, 33(9): 184-186
39黄兵,周献中.不完备信息系统分配约简与规则提取的矩阵算法.计算机工程, 2005, 31(17): 20-22
40谭天乐,宋执环,李平.信息系统数据清洗、规则提取的矩阵算法.信息与控制, 2003, 32(4): 289-294
41 Dey. D, Chatterjee. B. Rough-granular Approach for Impulse Fault Classification of Transformers Using Cross-wavelet Transform. IEEE Transactions on Dielectrics and Electrical Insulation, 2008, 15(5): 1297-1304
42宋轶博.基于Petri Net和遗传算法结合的配电变电站智能故障恢复研究. [天津大学工学硕士论文]. 2004: 12-15
43 Ting Y, Lu W, Chen C. A Fuzzy Reasoning Design for Fault Detection and Diagnosis of a Computer-controlled System. Engineering Applications of Artificial Intelligence, 2008, 21(2): 157-160
44 Georqilakis. P. S. A Systematic Stochastic Petri net based Methodology for Transformer Fault Diagnosis and Repair Actions. Journal of Intelligent and Robotic Systems: Theory and Applications, 2006, 45(2): 181-185
45王楠,律方成,刘云鹏等.基于决策表约简的变压器故障诊断Petri网络模型及其应用研究.电工技术学报, 2003, 18(6): 88-92
46王建元,纪严超. Petri网络在变压器故障诊断中的应用.电网技术, 2002, 26(8): 21-24
47徐欢,李孝忠.一种基于模糊Petri网的并行推理方法.系统仿真学报, 2007, 19(1): 108-110
48 Petrosino. A, Salvi. G. Rough Fuzzy Set based Scale Space Transforms and Their use in Image Analysis. International Journal of Approximate Reasoning, 2006, 41(2): 212-216
49 Zhang Jianhua, Yue Hong. Fault Diagnosis and Fault Tolerant Control in Power Plants and Power Systems. Measurement and Control, 2006, 39(6): 171-177
50莫娟,王雪,董明等.基于粗糙集理论的电力变压器故障诊断方法.中国电机工程学报, 2004, 24(7): 162-167
51杨启平,薛五德,蓝之达.变压器故障诊断技术的研究.变压器, 2002, 39(10): 38-42
2钱之银,陆志浩,楼其民等.变压器油中溶解气体判断方法综述.高压电器, 2002, 38(6): 34-37
3李俭.大型电力变压器以油中溶解气体为特征量的内部故障诊断模型研究. [重庆大学工学博士论文]. 2001: 26-28
4 Mohamed. E. A, Abdelaziz. A. Y, Mostafa A. S, et. al. A Neural Network-based Scheme for Dault Diagnosis of Power Transformers. Electric Power Systems Research, 2005, 75(1): 29-39
5 Chen Weigen, Pan Chong, Yun Yuxin. Wavelet Networks in Power Transformers Diagnosis using Dissolved Gas Analysis. IEEE Transactions on Power Delivery, 2009, 24(1): 187-194
6胡汉梅,鲍亮亮,赵海军.神经网络在变压器故障诊断中典型算法研究.高压电器, 2008, 44(3): 217-220
7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理论方法.中国电机工程学报, 2002, 22(2): 31-35
8 Lautre Nitin. K, Manna Alakesh. A Study on Fault Diagnosis and Maintenance of CNC-WEDM based on Binary Relational Analysis and Expert System. International Journal of Advanced Manufacturing Technology, 2006, 29(5): 490-498
9孙才新,郭俊峰,郑海平等.基于行为的变压器油色谱分析模糊诊断专家系统.电工技术学报, 2001, 16(3): 49-52
10 Su. Q, Mi. C, Lai. L. A Fuzzy Dissolved Gas Analysis Method for the Diagnosis of Multiple Faults in a Transformer. IEEE Transactions on Power System, 2006, 15(2): 593-598
11 Islam. S. M, Wu. T, Ledwich. G. A Novel Fuzzy Logic Approach to Transformer Fault Diagnosis. IEEE Transactions on Dielectrics and Electrical Insulation, 2006, 7(2): 177-186
12符杨,江玉蓉,崔椿洪.基于模糊数学和概率论的变压器故障诊断.高电压技术, 2008, 34(5): 1040-1044
13 Dong Lixin, Xiao Dengming, Liu Yilu, et. al. Insulation Fault Diagnosis Based on Group Grey Relational Grade Analysis Method for Power Transformers. Journal of Southeast University(English Edition), 2005, 21(2): 175-179
14 Lin Chaihung, Huang Pingzan, Wu Chen, et. al. Grey Clustering Analysis for Incipient Fault Diagnosis in Oil-immersed Transformers. Expert Systems with Applications, 2009, 36(2): 1371-1379
15 Zhang Zheng, Xiao Dengming, Liu Yilu. Insulation Fault Diagnosis of Power Transformers by Genetic Programming based Polynomial Networks Model. WSEAS Transactions on Circuits and Systems, 2006, 5(1): 79-84
16孙秋野,张化光,刘鑫蕊.基于粗糙集和遗传算法的变压器故障诊断方法,仪器仪表学报, 2008, 29(10): 2034-2040
17 Pawlak. Z. Rough sets. International Journal of Computer and Information Sciences, 1982, 11(3): 341-356
18 Li Xiaoou, Yu Wen, Lara. Rosano. F. Dynamic Knowledge Inference and Learning under Adaptive Fuzzy Petri net Framework. IEEE Transactions on Power Systems, 2000, 30(4): 442-449
19彭宁云.基于DGA技术的变压器故障智能诊断系统研究. [武汉大学工学博士论文]. 2001: 6-9
20中华人民共和国电力工业部. DL/T596-1996《电气设备预防性试验规程》.北京:中国电力出版社, 2000, 10-15
21徐安定.大型变压器状态监测与故障诊断技术. [浙江大学工学硕士论文]. 2005: 15-16
22何志强,文习山,陈旭.基于粗糙集理论的变压器故障的诊断.高电压技术. 2006, 32(6): 27-30
23 Duval, Michel. Calculation of DGA Limit Values and Sampling Intervals in Transformers in Service. IEEE Electrical Insulation Magazine, 2008, 24(5): 7-13
24包中福.电力变压器内部故障诊断的特征气体法及其应用研究. [重庆大学工程硕士论文]. 2004: 46-51
25 Sun Yanjing, Li Jingmeng, Miao Changxin. Improved BP Neural Network for Transformer Fault Diagnosis. Journal of China University of Mining and Technology, 2007, 17(1): 138-142
26 Liang Liuming, Chen Weigen, Yue YanFeng. Study on Power Transformers Fault Diagnosis based on Wavelet Neural Network and D-S Evidence Theory. High Voltage Engineering, 2008, 34(12): 2694-2700
27 Cang S, Yu H. Novel Probability Neural Network. IEE Proceedings: Vision, Image and Signal Processing, 2005, 152(5): 535-544
28闻新,周露,李翔等. MATLAB神经网络仿真与应用.北京:科学出版社, 2003: 264-274
29 Sun Yanjing, Zhang Shenmiao, Chang xin. Improved BP Neural Network for Transformer Fault Diagnosis. Journal of China University of Mining and Technology, 2007, 17(1): 138-142
30哈根.神经网络设计.北京:机械工业出版社, 2002, 143-145
31周开利,康耀红.神经网络模型及其MATLAB仿真程序设计.北京:清华大学出版社, 2005: 74-86
32 Wu Jianda, Liu Chiuhong. Investigation of Engine Fault Diagnosis using Discrete Wavelet Transform and Neural Network. Expert Systems with Applications, 2008, 35(3): 1200-1213
33王国胤. Rough集理论与知识获取.西安:西安交通大学出版社, 2001: 14-20
34 Zhang Weizheng, Li Yanming, Yang Lanjun. The Fault Diagnosis of Power Transformer based on Rough Set Theory. WSEAS Transactions on Circuits and Systems, 2005, 4(8): 912-916
35王庆东,陈建.不完备信息系统的粗糙集分解方法.计算机工程, 2007, 33(24): 41-43
36王国胤. Rough集理论在不完备信息系统中的扩充.计算机研究与发展, 2002, 39(10): 1238-1243
37黄文涛,王伟杰,赵学增等.从不完备数据中获取诊断规则的粗糙集方法.电力系统自动化, 2005, 29(14): 49-54
38张腾飞,王锡淮,肖健梅.不完备信息系统的一种属性相对约简算法.计算机工程, 2007, 33(9): 184-186
39黄兵,周献中.不完备信息系统分配约简与规则提取的矩阵算法.计算机工程, 2005, 31(17): 20-22
40谭天乐,宋执环,李平.信息系统数据清洗、规则提取的矩阵算法.信息与控制, 2003, 32(4): 289-294
41 Dey. D, Chatterjee. B. Rough-granular Approach for Impulse Fault Classification of Transformers Using Cross-wavelet Transform. IEEE Transactions on Dielectrics and Electrical Insulation, 2008, 15(5): 1297-1304
42宋轶博.基于Petri Net和遗传算法结合的配电变电站智能故障恢复研究. [天津大学工学硕士论文]. 2004: 12-15
43 Ting Y, Lu W, Chen C. A Fuzzy Reasoning Design for Fault Detection and Diagnosis of a Computer-controlled System. Engineering Applications of Artificial Intelligence, 2008, 21(2): 157-160
44 Georqilakis. P. S. A Systematic Stochastic Petri net based Methodology for Transformer Fault Diagnosis and Repair Actions. Journal of Intelligent and Robotic Systems: Theory and Applications, 2006, 45(2): 181-185
45王楠,律方成,刘云鹏等.基于决策表约简的变压器故障诊断Petri网络模型及其应用研究.电工技术学报, 2003, 18(6): 88-92
46王建元,纪严超. Petri网络在变压器故障诊断中的应用.电网技术, 2002, 26(8): 21-24
47徐欢,李孝忠.一种基于模糊Petri网的并行推理方法.系统仿真学报, 2007, 19(1): 108-110
48 Petrosino. A, Salvi. G. Rough Fuzzy Set based Scale Space Transforms and Their use in Image Analysis. International Journal of Approximate Reasoning, 2006, 41(2): 212-216
49 Zhang Jianhua, Yue Hong. Fault Diagnosis and Fault Tolerant Control in Power Plants and Power Systems. Measurement and Control, 2006, 39(6): 171-177
50莫娟,王雪,董明等.基于粗糙集理论的电力变压器故障诊断方法.中国电机工程学报, 2004, 24(7): 162-167
51杨启平,薛五德,蓝之达.变压器故障诊断技术的研究.变压器, 2002, 39(10): 38-42