基于随机森林特征优选与MAEPSO-ELM算法的变压器DGA故障诊断
CSTR:
作者:
中图分类号:

TM411

基金项目:

广东电网有限责任公司科技项目(GDKJXM20173051)


Transformer DGA fault diagnosis based on the random forest feature optimization and MAEPSO-ELM algorithm
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [12]
  • | | | |
  • 文章评论
    摘要:

    针对变压器故障智能诊断方法中输入特征不同影响诊断结果以及粒子群算法优化极限学习机准确率低的问题,提出基于随机森林特征优选与多尺度协同变异粒子群极限学习机的变压器DGA故障诊断方法。首先,基于故障样本DGA数据建立候选特征集,采用随机森林算法计算各特征重要性评分并降序排列,通过序列前向选择法筛选最优输入特征;其次,针对极限学习机参数选择困难的问题,引入多尺度协同变异粒子群算法进行优化;最后,将之与 IEC 三比值法以及不同组合极限学习机诊断性能进行比较。实例表明所提方法诊断精度更高。

    Abstract:

    A transformer DGA fault diagnosis method is proposed based on the random forest feature optimization and multi-scale cooperative mutation particle swarm limit learning machine for the problems that different input characteristics effects the diagnosis results and the low accuracy of particle swarm algorithm optimization limit learning machine. Firstly, the candidate feature set is established on the basis of the DGA data in the fault sample. The random forest algorithm is utilized to calculate the feature importance scores and rank them in a descending order. The optimal input features are then selected by the sequence forward selection method. Next, aiming at the problem of difficult parameter selection of extreme learning machine, a multi-scale cooperative mutation particle swarm optimization algorithm is introduced for optimization. Finally, the method is compared for the diagnostic performance with the IEC three-ratio method and different combinations of extreme learning machines. An example shows that the proposed method has higher diagnostic accuracy.

    参考文献
    [1] 李亮,范瑾,闫林,等.基于混合采样和支持向量机的变压器故障诊断[J].中国电力,2021,54(12):150-155.LI Liang,FAN Jin,YAN Lin,et al.Transformer fault diagnosis based on hybrid sampling and support vector machines[J].Electric Power,2021,54(12):150-155.
    [2] 谢国民,倪乐水.基于IABC优化SVM的变压器故障诊断[J].电力系统保护与控制,2020,48(15):156-163.XIE Guomin,XIE Guomin.Transformer fault diagnosis based on an artificial bee colony-support vector machine optimization algorithm[J].Power System Protection and Control,2020,48(15):156-163.
    [3] 王阳,乐健,周谦,等.基于小波包分析与神经网络的变压器区内外故障判断方法[J].电测与仪表,2020,57(7):1-7.WANG Yang,LE Jian,ZHOU Qian,et al.Inner and outer zone fault diagnosis method of transformer based on wavelet packet analysis and neural network[J].Electrical Measurement & Instrumentation,2020,57(7):1-7.
    [4] 张丞鸣,谢菊芳,胡东,等.基于QPSO-SVM与DGA五边形解释工具的变压器故障诊断方法[J].高压电器,2021,57(12):117-124.ZHANG Chengming,XIE Jufang,HU Dong,et al.Fault diagnosis method of transformer based on QPSO-SVM and DGA pentagonal interpretation tool[J].High Voltage Apparatus,2021,57(12):117-124.
    [5] 魏金萧,周步祥,唐浩,等.综合RapidMiner与改进粒子群极限学习机算法的变压器故障诊断[J].电力系统及其自动化学报,2019,31(3):133-138.WEI Jinxiao,ZHOU Buxiang,TANG Hao,et al.Transformer fault diagnosis with the combination of RapidMiner-modified particle swarm optimization-extreme learning machine algorithm[J].Proceedings of the CSU-EPSA,2019,31(3):133-138.
    [6] 周光宇,马松龄.基于机器学习与DGA的变压器故障诊断及定位研究[J].高压电器,2020,56(6):262-268.ZHOU Guangyu,MA Songling.Study of transformer fault diagnosis and location based on machine learning and DGA[J].High Voltage Apparatus,2020,56(6):262-268.
    [7] 汪可,李金忠,张书琦,等.变压器故障诊断用油中溶解气体新特征参量[J].中国电机工程学报,2016,36(23):6570-6578.WANG Ke,LI Jinzhong,ZHANG Shuqi,et al.New features derived from dissolved gas analysis for fault diagnosis of power transformers[J].Proceedings of the CSEE,2016,36(23):6570-6578.
    [8] 王干军,李锦舒,吴毅江,等.基于随机森林的高压电缆局部放电特征寻优[J].电网技术,2019,43(4):1329-1336.WANG Ganjun,LI Jinshu,WU Yijiang,et al.Random forest based feature selection for partial discharge recognition of HV cables[J].Power System Technology,2019,43(4):1329-1336.
    [9] 易淑智,刘云凯,杨帆,等.基于改进门控循环单元分位数回归的短期负荷概率预测[J].智慧电力,2021,49(8):84-90.YI Shuzhi,LIU Yunkai,YANG Fan,et al.Short-term load probability forecasting based on improved quantile regression of gated recurrent unit[J].Smart Power,2021,49(8):84-90.
    [10] 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(3):108-113.DANG 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(3):108-113.
    [11] 班国邦,徐玉韬,蔡欢,等.基于改进量子粒子群算法的直流配电中心削峰填谷策略研究[J].电网与清洁能源,2021,37(12):86-95.BAN Guobang,XU Yutao,CAI Huan.A study on peak load shaving strategies for DC distribution center based on improved QPSO algorithm[J].Power System and Clean Energy,2021,37(12):86-95.
    [12] KIM S W,KIM S J,SEO H D,et al.New methods of DGA diagnosis using IEC TC 10 and related databases part 1:application of gas-ratio combinations[J].IEEE Transactions on Dielectrics and Electrical In-sulation,2013,20(2):685-690.
    相似文献
    引证文献
引用本文

丁学辉,许海林,罗颖婷,等.基于随机森林特征优选与MAEPSO-ELM算法的变压器DGA故障诊断[J].电力科学与技术学报,2022,37(2):181-187.
DING Xuehui, XU Hailin, LUO Yingting, et al. Transformer DGA fault diagnosis based on the random forest feature optimization and MAEPSO-ELM algorithm[J]. Journal of Electric Power Science and Technology,2022,37(2):181-187.

复制
分享
文章指标
  • 点击次数:196
  • 下载次数: 847
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2022-05-26
文章二维码