基于多神经网络的三电平逆变器器件开路故障诊断方法

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (714 KB)
输出: BibTeX | EndNote (RIS)

摘要研究了三电平逆变器功率器件故障的诊断问题,以实现单个器件开路和多个器件同时开路的多故障模式的诊断。采用三电平逆变器的上、中、下桥臂电压作为测量信号,以分离不同的故障模式。利用频谱分析提取桥臂电压的谐波幅值和相位作为故障特征信息。提出了多神经网络结构和算法,实现了多模式故障的诊断。仿真和实验结果表明,该方法能够区分多种故障模式,并精确定位到故障器件,且诊断结果精度高,抗干扰能力强。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	陈丹江
	叶银忠

关键词 ：三电平, 故障诊断, 频谱分析, 多神经网络, 桥臂电压

Abstract：In order to diagnose different fault patterns of single device open circuit and several devices open circuit at the same time,a fault diagnosis method for a kind of three level inverters was discussed in this paper. Due to the reason of some fault patterns can not be isolated easily,the upper,middle and down bridge voltages were used as test signals. Then the fault features including harmonic amplitude and phase were extracted from these signals use the method of spectrum analysis. At last,a novel multi neural network was proposed to diagnose all these open circuit faults. The simulation and experiment result show that the method can isolate fault patterns exactly. This method has the advantages of high classification performance and high reliability.

Key words： Three level fault diagnosis spectrum analysis multi neural network bridge voltage

收稿日期: 2011-11-29 出版日期: 2013-12-11

PACS:

TM464

基金资助:上海市教育委员会科研创新重点项目（12zz191）,宁波市自然科学基金（2012A610007）和上海海事大学研究生创新基金（YC2011061）资助项目。

引用本文:

陈丹江，叶银忠. 基于多神经网络的三电平逆变器器件开路故障诊断方法[J]. 电工技术学报, 2013, 28(7): 120-126. Chen Danjiang,Ye Yinzhong. Fault Diagnosis of Three Level Inverter Based on Multi Neural Network. Transactions of China Electrotechnical Society, 2013, 28(7): 120-126.

链接本文:

http://dgjsxb.ces-transaction.com/CN/Y2013/V28/I7/120

[1] Hochgraf C, Lasseter R, Divan D, et al. Comparison of multilevel inverters for static Var compensation[C]. IEEE Conference on Industrial Applications, 1994: 921-928.
[2] Menzies R W, Steimer P, Steinke J K. Five level GTO inverters for large induction motor drives[C]. IEEE Institute for Advanced Studies Annual Meeting, 1993: 593-601.
[3] Stemmler H.Power electronics in electric traction applications[C]. IEEE Annual Conference of the Industrial Electronics Society, 1993: 707-713.
[4] Steimel A. Electric railway traction in europe[J]. IEEE Transactions on Industry Applications, 1996, 2: 7-17.
[5] Jih Sheng Lai, Fang Zheng Peng. Multilevel converters-a New breed of power converters[J]. IEEE Transactions on Industry Applications, 1996, 32: 509-517.
[6] Ceballos S, Pou J, Robles E, et al. Three-leg fault-tolerant neutral-point-clamped converter[C]. IEEE International Symposium on Industrial Electronics, 2007: 3180-3185.
[7] 汤清泉, 颜世超, 卢松升, 等. 三电平逆变器的功率管开路故障诊断[J]. 中国电机工程学报, 2008, 28(21): 26-32.
level inverter[J]. Proceedings of the CSEE, 2008, 28(21): 26-32.
[8] 周京华, 刘辉臣, 姚亚兰, 等. 三电平大功率变频器故障特征及诊断方法研究[J]. 电力电子技术, 2009, 43(6): 1-3.
[9] Ho In Son, Tae Jin Kim, Dae Wook Kang, et al. Fault diagnosis and neutral point voltage control when the 3-level inverter faults occur[C]. Power Electronics Specialists Conference, 2004: 4558-4563.
[10] Jae Chul Lee, Tae Jin Kim, Dae Wook Kang, et al. A control method for improvement of reliability in fault tolerant NPC inverter system[C]. 37th IEEE Power Electronics Specialists Conference, 2006: 1-5.
[11] 胡广书. 数字信号处理#x02014;#x02014;理论、算法与实现[M]. 北京: 清华大学出版社, 2003.
[12] 苏鹏声, 王志强, 姜建国. 用人工神经网络诊断电力电子电路主回路故障[J]. 清华大学学报(自然科学版), 1999, 39(3): 19-22.
[13] 龙伯华, 谭阳红, 许慧. 基于量子神经网络的电力电子电路故障诊断[J]. 电工技术学报, 2009, 24(10): 170-175.
[14] 马成才, 顾晓东. 基于神经网络组与故障分级的故障诊断[J]. 系统工程与电子技术, 2009, 31(1): 225-228.
[15] 蔡金锭, 付中云. 粒子群_神经网络混合算法在三相整流电路故障诊断中的应用[J]. 电工电能新技术, 2006, 25(4): 23-26.
[16] 乔维德. 基于改进粒子群算法神经网络的电力电子电路故障诊断[J]. 电气传动自动化, 2008, 30(5): 29-31.
[17] 王云亮, 孟庆学. 基于小波包能量法及神经网络的电力电子装置故障诊断[J]. 电气自动化, 2009, 31(2): 25-27, 45.
[18] 林渭勋. 现代电力电子技术[M]. 北京: 机械工业出版社, 2006.
[19] 闻新. Matlab神经网络仿真与应用[M]. 北京: 科学出版社, 2003.
[20] 周东华, 叶银忠. 现代故障诊断与容错控制[M]. 北京: 清华大学出版社, 2000.