登录    |    注册

您好,欢迎来到中国测试科技资讯平台!

首页> 《中国测试》期刊 >本期导读>级联H桥逆变器的多特征融合CNN故障诊断

级联H桥逆变器的多特征融合CNN故障诊断

180    2020-07-22

¥0.50

全文售价

作者:杨俊杰1,2, 谢维成1, 曹倩3

作者单位:1. 西华大学电气与电子信息学院,四川 成都 610039;
2. 四川中测辐射科技有限公司,四川 成都 610021;
3. 重庆大学自动化学院,重庆 400044


关键词:级联H桥七电平逆变器;故障诊断;多尺度主元分析;双流CNN;多特征融合


摘要:

针对级联H桥七电平逆变器不同故障表现相似程度高以及浅层分类器难以应对高维特征输入而制约故障诊断准确性的问题,该文提出一种基于多特征融合CNN的级联H桥七电平逆变器故障诊断策略。首先,采集原始三相电流信号,并结合参考电流信号求取电流偏差信号;其次,多尺度主元分析(multi-scale principal component analysis,MSPCA)算法通过将变分模态分解与主元分析相结合筛选故障信息存在的尺度分量,并将得到的各尺度分量直接重构作为高维时域特征输入,对得到的各尺度分量进行希尔伯特黄(HHT)变换,提取边际谱作为高维时频域特征输入;最后,将上述两种特征作为双通道CNN模型的输入进行训练,建立最终的多特征融合CNN故障诊断模型。结果表明:所提方法的故障诊断准确率达到95%,相较于单一特征与浅层分类器相结合的故障诊断策略,具有更高的识别率和更强的适应性,可为基于电信号的高相似度故障的分类识别提供一定参考。


Multi-feature fusion CNN fault diagnosis of cascaded H-bridge inverter
YANG Junjie1,2, XIE Weicheng1, CAO qian3
1. School of Electrical and Electronic Information, Xihua University, Chengdu 610039, China;
2. Sichuan Zhongce Radiation Technology Co., Ltd., Chengdu 610021, China;
3. School of Automation, Chongqing University, Chongqing 400044, China
Abstract: Aiming at the problems of high similarity in different fault performance of cascaded H-bridge seven-level inverter and the difficulty of shallow classifiers to cope with high-dimensional feature inputs, which restricts the accuracy of fault diagnosis, this paper proposes a fault diagnosis strategy for cascaded H-bridge seven-level inverter based on multi-feature fusion CNN. Firstly, the original three-phase current signal is collected, and the current deviation signal is obtained by combining the reference current signal. Secondly, the multi-scale principal component analysis (MSPCA) algorithm, which combines variational mode decomposition and principal component analysis, is used to select the several component from original signal. On the basis of above, the Hilbert-Huang transform (HHT) marginal spectrum was used to extract the high-dimensional fault features from the selected component as time-frequency features, and the high-dimensional fault features reconstructed from selected component at various scales were used as time-domain features. Finally, The above two features are used as the input of the two-stream CNN model to establish the final multi-feature fusion CNN fault diagnosis model.The results show that the fault diagnosis accuracy of the proposed method is 95%, which has higher recognition rate and stronger adaptability than the fault diagnosis strategy combined with single feature and shallow classifier. The research in this paper can provide a reference for fault diagnosis of the cascaded H-bridge seven-level inverter.
Keywords: cascaded H-bridge seven-level inverter;fault diagnosis;multi-scale principal component analysis;two-stream CNN;multi-feature fusion
2020, 46(7):8-17  收稿日期: 2020-05-19;收到修改稿日期: 2020-06-14
基金项目: 国家自然科学基金(61174401);教育部“春晖计划”(Z2018087);四川省科技计划资助项目(2019ZYZF0145)
作者简介: 杨俊杰(1993-),男,四川宜宾市人,硕士研究生,专业方向为智能控制与智能信号处理
参考文献
[1] 孙玉巍, 刘教民, 李永刚, 等. 单相级联H桥整流电路非线性控制策略[J]. 电工技术学报, 2017, 32(11): 180-188
[2] 彭丽维, 张彼德, 孔令瑜. 级联H桥七电平逆变器故障的SKSNN-LPP特征提取方法[J]. 电子测量与仪器学报, 2019(2): 110-116
[3] LU B, SSANTOSH K S. A literature review of IGBT fault diagnostic and protection methods for power inverters[J]. IEEE Transactions on Industry Application, 2009, 45(5): 1770-1777
[4] KO Y, LEE K B, KIN J M. Fault diagnosis of three parallel voltage-source converter for a high-power wind turbine[J]. IET Power Electron, 2012, 5(7): 1058-1067
[5] SHUAI S, ALAN J, JON C C. Robustness analysis and experimental validation of a fault detection and isolation method for the modular multilevel converter[J]. IEEE Transactions on Power Electronics, 2016, 31(5): 3794-3805
[6] 尹桥宣, 段斌. 模块化五电平逆变器子模块开路故障的智能诊断方法[J]. 电力系统自动化, 2018, 42(12): 127-147
[7] 陈勇, 刘志龙, 陈章勇. 基于电流矢量特征分析的逆变器开路故障快速诊断与定位方法[J]. 电工技术学报, 2018, 33(4): 883-891
[8] TIANZHEN W, QI J, XU H, et al. Fault diagnosis method based on FFT-RPCA-SVM for cascaded multilevel inverter[J]. ISA Transactions, 2016, 60: 156-163
[9] 姜媛媛, 王友仁. 基于小波包能量谱和ELM的光伏逆变器多故障在线诊断[J]. 仪器仪表学报, 2015, 36(9): 2143-2152
[10] 余运俊, 裴石磊, 万晓凤, 等. NPC三电平光伏逆变器开路故障诊断[J]. 电子测量与仪器学报, 2018(5): 41-49
[11] CHENG L, GAO J W, ZHANG B, et al. Fault diagnosis of subway auxiliary inverter based on EEMD and GABP[C]//26th Chinese Control and Decision Conference, 2014.
[12] 姜媛媛, 程浩, 崔江, 等. VMD小波能量的光伏逆变器软故障诊断[J]. 电力系统及其自动化学报, 2018, 30(11): 19-25
[13] 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(6): 120-126
[14] 胡超. 光伏逆变器故障诊断方法研究[D]. 淮南: 安徽理工大学, 2015.
[15] IAN G, YOSHUA B, AARON C. Deep learning[M]. Cambridge: MIT Press, 2016: 70-74.
[16] 杨晓冬, 王崇林. H桥逆变器IGBT开路故障诊断方法研究[J]. 电机与控制学报, 2014, 18(5): 112-118
[17] BAKSHI R B. Multiscale PCA with application to multivariate statistical process monitoring[J]. AIChE Journal, 1998, 44(7): 1596-1610
[18] HUANG N E. The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proc. R. Soc. Lond. A, 1998, 454: 903-995.
[19] SIMONYAN K, ZISSERMAN A. Two-stream convolutional network for action recognition in videos[C]//Advances in Neural Information Processing System, 2014.
[20] 易超人, 邓燕妮. 多通道卷积神经网络图像识别方法[J]. 河南科技大学学报, 2017, 38(3): 41-44