优选小波包和AdaBoost-SVM的柔性直流输电变流器故障诊断
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Fault Diagnosis of Flexible HVDC Converter Based on Preferred Wavelet Packet and AdaBoost-SVM
  • 作者:郑小霞 ; 彭鹏
  • 英文作者:ZHENG Xiaoxia;PENG Peng;School of Automation Engineering,Shanghai University of Electric Power;
  • 关键词:变流器 ; 小波包变换 ; 支持向量机 ; AdaBoost算法 ; 故障诊断
  • 英文关键词:converter;;wavelet packet transform;;support vector machine(SVM);;AdaBoost algorithm;;fault diagnosis
  • 中文刊名:DLZD
  • 英文刊名:Proceedings of the CSU-EPSA
  • 机构:上海电力学院自动化工程学院;
  • 出版日期:2018-05-10 11:55
  • 出版单位:电力系统及其自动化学报
  • 年:2019
  • 期:v.31;No.182
  • 基金:国家自然科学基金资助项目(51507098);; 上海市电站自动化技术重点实验室项目(13DZ2273800)
  • 语种:中文;
  • 页:DLZD201903007
  • 页数:8
  • CN:03
  • ISSN:12-1251/TM
  • 分类号:46-53
摘要
变流器作为输电系统中的核心部件极易发生故障。为了提高其故障诊断精度,提出一种优选小波包的故障特征提取和鸟群算法优化的AdaBoost-SVM相结合的故障诊断方法。首先,采用正常特征和故障特征之间的夹角余弦来选择小波基;再利用Parseval恒等式计算小波包变换后各频带的能量,以突出故障信号在尺度上复杂的细节特征;最后采用鸟群算法优化AdaBoost-SVM来实现变流器的故障诊断。仿真结果显示,该方法可对变流器开路故障进行有效诊断;相比于传统的SVM算法,该方法噪声鲁棒性强而且在不同比例训练样本下的诊断精度都要高。
        As the core component of a transmission system,the converter is prone to failure. To improve its fault diagnosis accuracy,a fault diagnosis method,which is combined with preferred wavelet packet with fault feature extraction and AdaBoost-SVM optimized by Bird Swarm Algorithm(BSA),is proposed in this paper. Firstly,the cosine of the angle between the normal and fault features is used to select wavelet bases. Secondly,the Parseval Identical Equation is used to calculate the energy of each frequency band after wavelet packet transform to highlight more complex detailed features of the fault signal on the scale. Finally,the AdaBoost-SVM optimized by BSA is used to realize fault diagnosis of the converter. Simulation results show that this method can effectively diagnose the open circuit fault of the converter;compared with the traditional SVM algorithm,it is more robust to noises and has higher diagnostic accuracies with training samples of different proportions.
引文
[1]李珊珊,李丽兰,朱云霞,等(Li Shanshan,Li Lilan,Zhu Yunxia,et al).基于双闭环控制的柔性直流输电变流器仿真研究(Simulation study of VSC-HVDC converter based on double closed-loop control)[J].电气传动(Elec?tric Drive),2017,47(9):19-23.
    [2]陈高华,成庶,向超群(Chen Gaohua,Cheng Shu,Xiang Chaoqun).非侵入式逆变器功率管开路故障诊断方法(A non-intrusive diagnostic technique for open-circuited faults of inverters)[J].中国电机工程学报(Proceedings of the CSEE),2017,37(13):3854-3862.
    [3]崔江,王强,龚春英(Cui Jiang,Wang Qiang,Gong Chuny?ing).结合小波与Concordia变换的逆变器功率管故障诊断技术研究(Inverter power switch fault diagnosis tech?nique research based on wavelet and Concordia transform)[J].中国电机工程学报(Proceedings of the CSEE),2015,35(12):3110-3116.
    [4]沈艳霞,周文晶,纪志成,等(Shen Yanxia,Zhou Wen?jing,Ji Zhicheng,et al).基于小波包分析的风力发电系统中变流器的故障识别(Fault identification of convert?er used in wind power generation based on wavelet packet analysis)[J].电网技术(Power System Technology),2013,37(7):2011-2017.
    [5]杭俊,张建忠,程明,等(Hang Jun,Zhang Jianzhong,Cheng Ming,et al).基于线电压误差的永磁直驱风电系统变流器的开路故障诊断(Fault diagnosis of open-cir?cuit faults in converters of direct-driven permanent mag?net wind power generation systems based on line voltage errors)[J].中国电机工程学报(Proceedings of the CSEE),2017,37(10):2933-2943.
    [6]张米露(Zhang Milu).基于分形神经网络的电力电子电路故障诊断(Fault diagnosis of power electronic circuits based on fractal and neural network)[J].电气传动自动化(Electric Drive Automation),2013,35(2):41-44.
    [7]马立新,范丽君(Ma Lixin,Fan Lijun).基于小波包神经网络的整流电路晶闸管故障识别(Thyristor fault identi?fication of rectifier circuit based on wavelet packet and neural network)[J].能源研究和信息(Energy Research and Information),2016,32(1):45-50.
    [8]沈艳霞,周文晶,纪志成,等(Shen Yanxia,Zhou Wen?jing,Ji Zhicheng,et al).基于小波包与SVM的风电变流器故障诊断(Fault diagnosis of converter used in wind power generation based on wavelet packet analysis and SVM)[J].太阳能学报(Acta Energiae Solaris Sinica),2015,36(4):785-790.
    [9]李爽,王志新,王国强(Li Shuang,Wang Zhixin,Wang Guoqiang).海上风电柔性直流输电变流器P-DPC控制研究(Predictive direct power control strategy for offshore wind power VSC-HVDC converter)[J].电工技术学报(Transactions of China Electrotechnical Society),2013,28(2):264-270.
    [10] Schettler F,Huang H,Christl N. HVDC transmission sys?tems using voltage source converters design and applica?tions[C]//IEEE Power Engineering Society Summer Meeting. Seattle,USA,2000:715-720.
    [11]刘畅,魏建忠(Liu Chang,Wei Jianzhong).基于正交紧支复小波的动车组变流器功率器件故障诊断(Fault di?agnosis for power devices in EMU converter based on or?thogonal compact support complex wavelet)[J].电力系统及其自动化学报(Proceedings of the CSU-EPSA),2017,29(9):143-150.
    [12]朱艳,王渝红,丁志林,等(Zhu Yan,Wang Yuhong,Ding Zhilin,et al).小波能量偏度神经网络的HVDC换相失败故障诊断(Fault diagnosis of commutation failures in HVDC system based on neural network of wavelet energy skewness)[J].电力系统及其自动化学报(Proceedings of the CSU-EPSA),2017,29(2):39-44.
    [13]黄云辉,翟雪冰,刘栋,等(Huang Yunhui,Zhai Xuebing,Liu Dong,et al).弱电网下风力发电机组并网变流器直流电压稳定性机理分析(Stability analysis on DC-link voltage of wind turbine grid-connected converter as inte?grated to weak grid)[J].高电压技术(High Voltage Engi?neering),2017,43(9):3127-3136.
    [14] Freund Y,Schapire R E. A decision-theoretic generaliza?tion of on-line learning and an application to boosting[J].Journal of Computer and System Science,1997,55(1):119-139.
    [15]吴俊利,张步涵,王魁(Wu Junli,Zhang Buhan,Wang Kui).基于Adaboost的BP神经网络改进算法在短期风速预测中的应用(Application of Adaboost-based BP neu?ral network for short-term wind speed forecast)[J].电网技术(Power System Technology),2012,36(9):221-225.
    [16]张震,汪斌强,梁宁宁,等(Zhang Zhen,Wang Binqiang,Liang Ningning,et al).一种基于AdaBoost-SVM的流量分类方法(Internet traffic classification based on Ada?Boost-SVM)[J].计算机应用研究(Application Research of Computers),2013,30(5):1481-1485.
    [17] Rifkin Ryan,Klautau Aldebaro. In defense of one-vs-all classification[J]. Journal of Machine Learning Research,2004,5:101-141.
    [18]周松林,峁美琴,苏建徽(Zhou Songlin,Mao Meiqin,Su Jianhui).基于小波分析与支持向量机的风速预测(Wind speed forecasting based on wavelet analysis and support vector machine)[J].太阳能学报(Acta Energiae Solaris Sinica),2012,33(3):452-456.
    [19]刘霄涵,王渝红,胡松伶,等(Liu Xiaohan,Wang Yuhong,Hu Songling,et al).基于SVD-SVM的HVDC换流器故障诊断(Fault diagnosis for HVDC converters based on SVD-SVM)[J].高压电器(High Voltage Appara?tus),2016,52(10):86-91.
    [20]刘晓龙,宁芊,赵成萍,等(Liu Xiaolong,Ning Qian,Zhao Chengping,et al).基于莱维飞行的鸟群优化算法(Bird swarm algorithm based on Levy flight)[J].计算机测量与控制(Computer Measurements&Control),2016,24(12):194-197.
    [21]曾嶒,彭春华,王奎,等(Zeng Ceng,Peng Chunhua,Wang Kui,et al).基于鸟群算法的微电网多目标运行优化(Multi-objective operation optimization of micro grid based on bird swarm algorithm)[J].电力系统保护与控制(Power System Protection and Control),2016,44(13):117-122.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700