基于多分辨率小波网络-BP神经网络-D-S证据理论信息融合模型的直流系统故障诊断方法DC SYSTEM GROUNDING FAULT DIAGNOSIS METHOD BASED ON DATA FUSION MODEL OF MRNN-BPN-DS
李冬辉,周巍巍
摘要(Abstract):
直流系统接地故障检测中常用的低频信号注入法容易受到大电容接地、环网以及电流互感器故障和饱和等因素的影响。针对这种情况,引入多传感器信息融合的思想,提出了基于“多分辨率小波网络—BP神经网络—D-S证据理论”信息融合模型的故障诊断方法,以综合多个信息源对直流系统的接地故障进行诊断。对具有3条支路的直流供电系统进行的仿真分析表明,在上述情况下利用该方法可以有效诊断出直流系统的故障支路,具有较好的诊断效果。
关键词(KeyWords): 直流系统;接地故障;信息融合;多分辨率小波网络(MRNN);D-S证据理论
基金项目(Foundation):
作者(Author): 李冬辉,周巍巍
Email:
DOI: 10.13335/j.1000-3673.pst.2004.24.004
参考文献(References):
- [1] 贾秀芳,陈恺,施慧.直流系统一点接地问题及简易查找法[J].电力情报,1999,(2):16-19.
- Jia Xiufang, Chen Ka(?), Shi Hui. The problem of DC system one-point grounding and a simple measuring approach[J]. Information on Electric Power, 1999, (2): 16-19.
- [2] 杨建华.直流系统绝缘监察装置的改进和接地点检测[J].华北电力技术,1993,(12):20-22.
- Yang Jianhua. Improvement of insulation monitoring device for DC system and the grounding point detection[J]. North China Electric Power, 1993, (12): 20-22.
- [3] 李冬辉,蔡旭,邹宝兰.微机直流系统绝缘监视装置及测量方法的研究[J].电子测量与仪器学报,2000,14(3):37-39.
- Li Donghui, Cai Xu, Zou Baolan. Research on insulation monitoring device and measuring method for DC system based on microcomputer [J]. Journal of Electronic Measurement and Instrument, 2000, 14(3): 37-39.
- [4] 薛永瑞.一种探测电站直流系统接地点的新方法及相关仪器的研制[D].西安:西安交通大学,1996.
- [5] 李立伟,邹积岩.直流系统接地电阻检测仪的研究与实现[J].测控技术,2002,21(10):27-29.
- Li Liwei, Zou Jiyan. Research and realization of the measuring device for DC system grounding resistance value[J]. Measurement & Control Technology, 2002, 21(10): 27-29.
- [6] 费万民,张艳莉,吴兆麟.电力系统中直流接地故障电阻检测的
- ??新原理[J].电力系统自动化,2001,25(6):54-56.
- Fei Wanmin, Zhang Yanli, Wu Zhaolin. New measuring princtple of DC system grounding resistance value in electric power system [J]. Automation of Electric Power Systems, 2001, 25(6): 54-56.
- [7] Marrero J A. Understand ground fault detection and isolation in DC systems[A]. IEEE Power Engineering Society Summer Meeting [C]. Seattle, WA, USA, 2000, 3: 1707-1711.
- [8] 陈坚红,李蔚,盛德仁,等.一种火电机组在线性能训算中的数据融合方法[J].中国电机工程学报,2002.22(5):152-156.
- Chen Jianhong, Li Wei, Sheng Deren et al. A data fusion method for on-line performance calculation of turbogenerator[J]. Proceedings of the CSEE, 2002, 22(5): 152-156.
- [9] Yang Z, Sagara S, Tsyji T. System impulse response identification using a multiresolution neural networklJ]. Automatica, 1997, 33(7): 1345-1350.
- [10] Ingrad Daubechies. Ten lectures on wavelets[M]. Philadelphia: Society for Industrial and Applied Mathematics, 1992.
- [11] 李贵存,刘万顺,宫德锋,等.用于磁化曲线拟合的高精度混合型径向基函数神经网络[J].电网技术,2001,25(12):18-21,25.
- Li Guicun, Liu Wanshun, Gong Defeng et al. Networks in simulation of ferromagnetic elements' major hysteresis curve [J]. Power System Technology, 2001, 25(12): 18-21, 25.
- [12] Martin T H, Howard B D. Neural network design[M]. Beijing: China Machine Press, 2002.
- [13] 袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,1999.
- [14] 谢开贵,李春燕,周家启.基于神经网络的负荷组合预测模型研究[J].中国电机工程学报,2002,22(7):85-89.
- Xie Kaigui, Li Chunyan, Zhou Jiaqi. Research of the combination forecasting model for load based on artificial neural network [J]. Proceedings of the CSEE, 2002, 22(7): 85-89.
- [15] 朱大奇,于盛林.基于D-S证据理论的数据融合算法及其在电路故障诊断中的应用[J].电子学报,2002,30(2):221-223.
- Zhu Daqi, Yu Shenglin. The data fusion algorithm based on D-S evidence theory and its application to the diagnosis of circuit faults [J]. Chinese Journal of Electronics, 2002, 30(2): 221-223.
- [16] 胡晓光,于文斌.电流互感器的暂态仿真及其铁芯饱和的小波分析[J].电网技术,2001,25(11):58-61.
- Hu Xiaoguang, Yu Wenbin. Transient simulation of current sensor and the wavelet analysis of its iron core saturation[J]. Power System Technology, 2001, 25(11): 58-61.
- [17] 徐军华,刘天琪.基于小波分解和人工神经网络的短期负荷预测[J].电网技术,2004,28(8):30-33.
- Xu Junhua, Liu Tianqi. An approach to short-term load forecasting based on wavelet transform and artificial neural network[JI. Power System Technology, 2004, 28(8): 30-33.
- [18] 王成,王鑫全.被动式多雷达系统的多目标数据融合[J].电子学报,2001,29(11):F003-F006.
- Wang Cheng, Wang Xinquan. Multiobjective data fusion of passive multiradar system[J]. Chinese Journal of Electronics, 2001, 29(11): F003-F006.
- [19] 胡寿松.基于小波神经网络的组合故障模式识别[J].自动化学报,2002,28(4):540-543.
- Hu Shousong. Pattern recognition of combined fault based on WNN[J]. Acta Automatica Sinica, 2002, 28(4): 540-543.