基于改进关联规则挖掘算法的变压器故障诊断
CSTR:
作者:
作者单位:

1.国网四川省电力公司天府新区供电公司;2.长沙理工大学电气与信息工程学院;3.国网河南省电力公司;4.国网长沙供电公司

中图分类号:

TM407??????????

基金项目:

国家自然科学基金项目(面上项目,重点项目,重大项目)


Diagnosis of the power transformer fault events based on the enhanced association rule mining algorithm
Author:
Affiliation:

1.State Grid Tianfu New Area Electric Power Supply Company;2.School of Electrical &3.Information Engineering, Changsha University of Science &4.Technology;5.State Grid Henan Electric Power Company;6.State Grid Changsha Power Supply Company

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [21]
  • | |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    关联规则挖掘算法常被应用在基于油中溶解气体分析的变压器故障诊断中。为进一步提升诊断效果,文章提出一种基于改进关联规则挖掘算法的变压器故障诊断方法。首先构建了可调整的状态重要度评估标准计算方式,能够适应不同输入特征并将其中的罕见高危数据纳入分析,从而有效应对现实中可能出现的所有极端情况;其次直接基于输入特征量导致故障的风险而非特征量的数据占比求解相应故障风险权重,从而能够更加准确地衡量各个特征量所带来的影响;最后应用Relim算法进行关联规则挖掘,从而有力改善挖掘效率。实验结果表明,所提出的方法相较采用固定重要度评估标准计算方式、传统风险权重求解方法以及Apriori关联规则挖掘算法的故障诊断方法,具有更好的诊断准确率、实际可行性以及运算效率。

    Abstract:

    Association rule mining methods are commonly utilized to analyze the dissolved gas which is applied to diagnose the power transmission fault events. For the purpose of improving the performance, this paper proposes a diagnosis method for power transformer fault events based on the enhanced association rule mining algorithm. Firstly, the conditional significance measurements which can be adapted for different input features are established. Thus the rarely distributed but risky data can be incorporated in analysis, and all the potential circumstances in reality can be considered. Next, the risk weights of input data are generated through their likelihood of causing a fault rather than their statistical distribution. Therefore, the impact of each input will be measured more precisely. Finally, Relim algorithm is applied to raise the efficiency of mining. The empirical study shows that the proposed method is more pinpoint, realizable and efficient compared with the methods with the fixed significance measurements, the conventional technique to calculate the risk weight, and Apriori algorithm.

    参考文献
    [1] 孟安波,卢海明,郭壮志.纵横交叉算法与模糊聚类相结合的变压器故障诊断[J].电测与仪表,2016,53(13):25-29.eng Anbo, Lu Haiming, Guo Zhuangzhi. Fault diagnosis method of transformer based on crisscross optimization algorithm and fuzzy clustering[J]. Electrical Measurement Instrumentation, 2016, 53(13): 25-29.
    [2] 党东升,张树永,葛鹏江,等.基于改进量子粒子群优化支持向量机的变压器故障诊断方法[J].电力科学与技术学报,2019,34(03):108-113.ANG Dongsheng, ZHANG Shuyong, GE Pengjiang, et al. Transformer fault diagnosis method based on support vector machine optimized by improved quantum-behaved particle swarm optimization [J]. Journal of Electric Power Science and Technology, 2019,34(03):108-113.
    [3] 张育杰,冯健,李典阳,等.基于油色谱数据的变压器故障征兆新优选策略[J/OL].电网技术:1-9[2021-03-22].https://doi.org/10.13335/j.1000-3673.pst.2020.1282.HANG Yujie, FENG Jian LI Dianyang WANG Shanyuan, et al. New Feature Selection Method for Transformer Fault Diagnosis Based on DGA Data [J/OL]. Power System Technology, 2021. https: //doi.org/10.13335/ j. 1000-3673.pst.2020.1282.
    [4] 王晶,许素安,洪凯星,等.基于DGA特征量优选与GA-SVM的变压器故障诊断模型[J].变压器,2020,57(12):36-40+46.ANG Jing, XU Su-an, HONG Kai-xing, et al. Transformer Based on DGA Feature Quantity Optimization and GA-SVM Fault Diagnosis Model [J]. Transformer, 2020,57(12):36-40+46.
    [5] ?夏玉剑,李敏,向天堂,等.基于SOM的变压器绕组和铁芯故障诊断[J].电力科学与技术学报,2018,33(02):129-134.IA Yujian, LI Min, XIANG Tiantang, et al. Fault diagnosis of transformer winding and core based on SOM [J]. Journal of Electric Power Science and Technology,2018,33(02):129-134.
    [6] 荣智海,齐波,李成榕,等.面向变压器油中溶解气体分析的组合DBN诊断方法[J].电网技术,2019,43(10):3800-3808.ONG Zhihai, QI Bo, LI Chengrong, et al. Combined DBN Diagnosis Method for Dissolved Gas Analysis of Power Transformer Oil[J]. Power System Technology, 2019,43(10):3800-3808.
    [7] 贾京龙,余涛,吴子杰,等.基于卷积神经网络的变压器故障诊断方法[J].电测与仪表,2017,54(13):62-67.ia Jinglong, Yu Tao, Wu Zijie, et al. Fault diagnosis method of transformer based on convolutional neural network[J]. Electrical Measurement Instrumentation, 2017,54(13):62-67.
    [8] G. Rigatos, P. Siano. Power transformers’ condition monitoring using neural modeling and the local statistical approach to fault diagnosis[J]. International Journal of Electrical Power and Energy Systems, 2016, 80(1):150-159.
    [9] 王保义,杨韵洁,张少敏.改进BP神经网络的SVM变压器故障诊断[J].电测与仪表,2019,56(19):53-58.ang Baoyi, Yang Yunjie, Zhang Shaomin. Fault diagnosis of support vector machine transformer based on improved BP neural network[J]. Electrical Measurement Instrumentation, 2019,56(19):53-58.
    [10] 刘君,赵立进,黄良,等.基于Adaboost.MK和SM-SVDD的变压器故障诊断方法[J].电力科学与技术学报,2017,32(03):139-144+152.IU Jun, ZHAO Lijin, HUANG Liang, et al. Fault diagnosis method for power transformer based on Adaboost.MK and SM-SVDD [J]. Journal of Electric Power Science and Technology, 2017,32(03):139-144+152.
    [11] K. Bacha, S. Souahlia, M. Gossa. Power transformer fault diagnosis based on dissolved gas analysis by support vector machine[J]. Electric Power Systems Research, 2012, 83(1): 73-79.
    [12] 谭贵生,曹生现,赵波,等.基于关联规则与变权重系数的变压器状态综合评估方法[J].电力系统保护与控制,2020,48(01):88-95.AN Guisheng, CAO Shengxian, ZHAO Bo, et al. An assessment of power transformers based on association rules and variable weight coefficients [J]. Power System Protection and Control, 2020,48(01):88-95.
    [13] L. Li, C. Yong, X. Jun, et al. An Integrated Method of Set Pair Analysis and Association Rule for Fault Diagnosis of Power Transformers[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2015, 22(04):2368-2378.
    [14] G. Sheng, H. Hou, X. Jiang, et al. A Novel Association Rule Mining Method of Big Data for Power Transformers State Parameters Based on Probabilistic Graph Model[J]. IEEE Transactions on Smart Grid, 2018, 9(02): 695-702.
    [15] R Agrawal, T Imieliński, A Swami. Mining association rules between sets of items in large databases[J]. Acm Sigmod Record, 1993, 22(2): 207-216.
    [16] Hipp J. Algorithms for association rule mining-a general survey and comparison [J]. ACM, 2000, 2(1):58-64.
    [17] DL/T 722-2014, 变压器油中溶解气体分析和判断导则[S].
    [18] Birnbaum Z W. On the importance of different components in a multicomponent system [J]. Multivariate Analysis II, 1968:581-592.
    [19] Borgelt C. Keeping Things Simple: Finding Frequent Item Sets by Recursive Elimination[C]// International Workshop on Open Source Data Mining: Frequent Pattern Mining Implementations. ACM, 2005.
    [20] Swets J A. Signal detection theory and ROC analysis in psychology and diagnostics: collected papers[M]. USA: Lawrence Erlbaum Associates, 2016.
    [21] Davis J, Goadrich M. The relationship between precision-recall and roc curves[C]// Proceedings of the 23rd international conference on machine learning. ACM; 2006.2
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:38
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2021-03-31
  • 最后修改日期:2021-06-09
  • 录用日期:2021-07-26
文章二维码