基于贝叶斯网络和粗糙集约简的变压器故障诊断

doi:10.11930/j.issn.1004-9649.2013.9.75.4

摘要/Abstract

摘要： 贝叶斯网络处理不确定性问题的能力可以很好地解决变压器故障诊断中因数据不完整而难以得到可靠结论的问题。为此,将贝叶斯网络分类器和粗糙集约简理论相结合,基于专家知识及统计数据建立贝叶斯网络分类模型,并综合运用色谱数据及电气试验数据作为变压器故障诊断的属性集输入,实现概率推理及对可能故障类型的排序,提高诊断结论的可靠性。此外,利用粗糙集约简理论对贝叶斯网络分类模型进行最小约简,降低网络结构的复杂性,减小模型所依赖的输入量,以更切合实际诊断情况。实验证明,该方法具有处理信息缺失的能力及容错特性,准确率较高,是一种变压器故障诊断的有效方法。

关键词: 变压器, 故障诊断, 决策表, 贝叶斯网络, 粗糙集, 知识约简

Abstract: The ability of Bayesian network to deal with uncertain problems can be a solution to transformer fault diagnosis when data is incomplete and reliable conclusions are difficult to be reached. By combining the Bayesian network classifier and rough set reduction theory, this paper set up a Bayesian network classification model based on expert knowledge and statistical data. The integral use of DGA and electrical test data as the input set of diagnosis realized the probabilistic reasoning and sequencing of the possible failure types, and as a result, improved the reliability of the diagnosis. Meanwhile the rough set reduction theory was used to make the minimization reduction of Bayesian network classification model, effectively reduced the complexity of network structure and the input of the model. Experiments proved that this method is an effective transformer fault-diagnosis method and has the ability to deal with the absence of information, the fault-tolerant features and high accuracy.

Key words: transformer, failure diagnosis, decision table, Bayesian network, rough sets, information reduction

中图分类号:

TM407

吕启深, 曾辉雄, 姚森敬, 黄荣辉, 张海龙. 基于贝叶斯网络和粗糙集约简的变压器故障诊断[J]. 中国电力, 2013, 46(9): 75-79.

LU Qi-shen, ZENG Hui-xiong, YAO Sen-jing, HUANG Rong-hui, ZHANG Hai-long. Transformer Fault Diagnosis Method Based on Bayesian Network and Rough Set Reduction Theory[J]. Electric Power, 2013, 46(9): 75-79.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.2013.9.75.4

https://www.electricpower.com.cn/CN/Y2013/V46/I9/75

参考文献

[1] 廖瑞金. 变压器绝缘故障诊断黑板型专家系统和基于遗传算法的故障预测研究[D]. 重庆：重庆大学,2003.
[2] 熊浩,杨俊. 多种类证据体的变压器故障综合诊断方法[J]. 中国电机工程学报,2008,28（28）：24-30.
XIONG Hao, YANG Jun. Application of evidence theory to transformer faults synthesized diagnosis[J]. Proceedings of the CSEE, 2008, 28(28): 24-30.
[3] LI Hong-lei, XIAO Deng-ming, CHEN Ya-zhu. Wavelet ANN based on transformer fault diagnosis using gas-in-oil analysis[C]//IEEE: Proceedings of the 6th International Conference on Properties and Applications of Dielectric Materials. Piscataway NJ, USA, 2000.
[4] 林士敏,田凤占,陆玉昌. 贝叶斯网络的建造及其在数据采掘中的应用[J]. 清华大学学报：自然科学版,2001,41（1）：49-52.
LIN Shi-min, TIAN Feng-zhan, LU Yu-chang. Construction and applications in data mining of Bayesian networks[J]. Journal of Tsinghua University: Sci & Tech, 2001, 41(1): 49-52.
[5] JIN Huang, LU Jing-jing, LING C X. Comparing Naive Bayes,decision trees, and SVM with AUC and accuracy[C]// Proceeding of the 3rd IEEE International Conference on Data Mining. Melboume, Flofida, USA, 2003: 553-556.
[6] 赵文清,朱永利,姜波,等. 基于贝叶斯网络的电力变压器状态评估[J]. 高电压技术,2008,34（5）：1032-1039.
ZHAO Wen-qing, ZHU Yong-li, JIANG Bo, et al . Condition assessment for power transformers by Bayes networks [J]. High Voltage Engineering, 2008, 34(5): 1032-1039.
[7] 毕文杰. 基于粗糙集与贝叶斯理论的群决策方法研究[M]. 长沙：中南大学出版社,2009.
[8] 吴立增,朱永利,苑津莎. 基于贝叶斯网络分类器的变压器综合故障诊断方法[J]. 电工技术学报,2005,20（4）：45-51.
WU Li-zeng, ZHU Yong-li, YUAN Jin-sha. Novel method for transformer faults integrated diagnosis based on Bayesian network classifier [J]. Transactions of China Electrotechnical Society, 2005, 20(4): 45-51.
[9] 杨莉,尚勇,周跃峰,等. 基于概率推理和模糊数学的变压器综合故障诊断模型[J]. 中国电机工程学报,2000,20（7）：19-23.
YANG Li, SHANG Yong, ZHOU Yue-feng, et al . Probability reasoning and fuzzy technique applied for identifying power transformer malfunction[J]. Proceedings of the CSEE, 2000, 20(7): 19-23.
[10] 王永强,律方成,李和明. 基于贝叶斯网络和DGA的变压器故障诊断[J]. 高电压技术,2004,30（5）：12-14.
WANG Yong-qiang, LU Fang-cheng, LI He-ming. Intelligent fault diagnosis for power transformer based on Bayesian network and DGA [J]. High Voltage Engineering, 2004, 30(5): 12-14.
[11] 吴欣,郭创新. 基于贝叶斯网络的电力系统故障诊断方法[J]. 电力系统及其自动化学报,2005,17（4）：11-15.
WU Xin, GUO Chuang-xin. Power system fault diagnosis approach based on Bayesian network [J]. Proceeding of the EPSA, 2005, 17(4): 11-15.
[12] 荣亚君,葛葆华,赵杰,等. 用粗糙集理论和贝叶斯网络诊断SF 6 断路器故障[J]. 高电压技术,2009,35（12）：2995-2999.
RONG Ya-jun, GE Bao-hua, ZHAO Jie, et al . Fault diagnosis of SF 6 circuit breaker using rough set theory and bayesian network[J]. High Voltage Engineering, 2009, 35(12): 2995-2999.
[13] 刘育明,周湶,唐捷,等. 粗糙集理论提取配电网故障诊断规则的方法[J]. 高电压技术,2006,32（8）：97-99,104.
LIU Yu-ming, ZHOU Quan, TANG Jie, et al . Fault diagnosis rule extraction for distribution system based on rough set theory[J]. High Voltage Engineering, 2006, 32(8): 97-99, 104.
[14] 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[J]. 中国电机工程学报,2004,24（7）：162-167.
MO Juan, WANG Xue, DONG Ming, et al . Diagnosis model of insulation faults in power equipment based on rough set theory[J]. Proceedings of the CSEE, 2004, 24(7): 162-167.
[15] 王国胤. Rough集理论与知识获取[M]. 西安：西安交通大学出版社,2001.
[16] 王楠,律方成,刘云鹏. 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[J].电工技术学报,2003,18（6）：88-92.
WANG Nan, LU Fang-cheng, LIU Yun-peng. Study on application of Petri net model of transformer fault diagnosis based on decision table reduction [J]. Transactions of China Electrotechnical Society, 2003, 18(6): 88-92.
[17] 黄文涛,赵学增,王伟杰,等. 基于粗糙集理论的故障诊断决策规则提取方法[J]. 中国电机工程学报,2003,23（11）：150-154.
HUANG Wen-tao, ZHAO Xue-zeng, WANG Wei-jie, et al . Decision rule extraction method for fault diagnosis based on Rough set theory[J]. Proceedings of the CSEE, 2003, 23(11): 150-154.
[18] 张文修,吴伟志,梁吉业,等. 粗糙集理论与方法[M]. 西安：西安交通大学出版社,2001.
[19] 赵文清,朱永利,王晓辉. 基于组合贝叶斯网络的电力变压器故障诊断[J]. 电力自动化设备,2009,29（11）：6-9.
ZHAO Wen-qing, ZHU Yong-li, WANG Xiao-hui. Combinatorial Bayesian network in fault diagnosis of power transformer[J].Electric Power Automation Equipment, 2009, 29(11): 6-9.