Open-circuit fault diagnosis method for switching tube of mine NPC three-level inverter
-
摘要: 矿井提升机、带式输送机中电动机驱动系统的变频器大多采用中点钳位式（NPC）三电平逆变器，该逆变器开关管数量多、运行频率高，在短时间内高频率切换开关工作状态和在复杂工作环境下容易出现开关管开路故障，且故障信号具有非平稳特性。现有NPC三电平逆变器开关管故障诊断方法存在故障特征提取困难、计算量大、故障准确率较低等问题。针对上述问题，提出了一种基于概率神经网络(PNN)的矿用NPC三电平逆变器开关管开路故障诊断方法。首先利用示波器采集逆变器三相相电压信号，并对相电压信号进行去噪、归一化等处理。然后利用Clark与Park变换将三相相电压转换为两相旋转（d−q）坐标系电压，利用经验模态分解（EMD）将d轴电压分解为多个本征模态分量（IMF），对于不同的开路故障，计算各IMF的方差贡献率，得出第2、第3、第8个IMF的方差贡献率相差较大，以这3个IMF代表不同的开路故障，并计算出它们的均值、均方差和方差，作为逆变器开关管开路故障特征向量。最后将特征向量输入PNN中进行训练与分类，实现NPC三电平逆变器开关管开路故障诊断。实验结果表明，与基于卷积神经网络（CNN）和支持向量机（SVM）的故障诊断方法相比，基于PNN的矿用NPC三电平逆变器开关管故障诊断方法具有更高的故障诊断准确率，平均故障诊断准确率达97.75%。Abstract: The inverter of the motor drive system in the mine hoist and belt conveyor mostly adopts neutral point clamped (NPC) three-level inverter. This inverter has a large number of switching tubes and high running frequency. Switching the working state of the switching tubes at high frequency in a short time and in complex working environment are prone to open-circuit fault. The fault signal has non-stationary characteristics. The existing fault diagnosis method for switching tube of NPC three-level inverter has the problems of difficult fault feature extraction, large calculation amount, and low fault accuracy. In order to solve the above problems, an open-circuit fault diagnosis method for switching tube of mine NPC three-level inverter based on probabilistic neural network (PNN) is proposed. Firstly, the phase voltage signals of three-phase of inverter are collected by oscilloscope. The phase voltage signals are processed by denoising and normalization. Secondly, the three-phase voltage is converted into two-phase rotating (d-q) coordinate system voltage by Clark transform and Park transform. The d-axis voltage is decomposed into multiple intrinsic mode function (IMF) using empirical mode decomposition (EMD). For different open-circuit faults, the variance contribution rate of each IMF is calculated. The variance contribution rates of the second, third and eighth IMF differ greatly. The three IMF represent different open-circuit faults. The mean, mean square and variance of the second, third and eighth IMF are calculated as the open-circuit fault feature vector of the inverter switching tube. Finally, the feature vector is input into the PNN for training and classification. The open-circuit fault diagnosis of the NPC three-level invert switching tube is realized. The experimental results show that the fault diagnosis method based on PNN has higher fault diagnosis accuracy than the fault diagnosis method based on CNN and SVM, and the average fault diagnosis accuracy reaches 97.75%.
-
图 8 加噪前后的
$ {{\rm{Q}}_{{\rm{a}}3}} $ $ {{\rm{Q}}_{{\rm{c}}1}} $ 故障波形Figure 8.
$ {{\rm{Q}}_{{\rm{a}}3}} $ $ {{\rm{Q}}_{{\rm{c}}1}} $ faults waveforms before and after noise adding
图 10 基于PNN的矿用三电平逆变器开路故障诊断流程
Figure 10. Diagnosis flow of open-circuit fault of mine NPC type three-level inverter
表 1 故障类型及标签
Table 1. Fault types and labels
故障类型 标签 故障类型 标签 故障类型 标签 故障类型 标签 ${{\rm{Q}}_{{\rm{a}}1}}$ 1 ${{\rm{Q}}_{{\rm{b}}4}} {{\rm{Q}}_{{\rm{c}}3}}$ 19 ${{\rm{Q}}_{{\rm{a}}3}} {{\rm{Q}}_{{\rm{c}}1}}$ 37 ${ {\rm{Q} }_{ {\rm{a} }4} } { {\rm{Q} }_{ {\rm{b} }2} }$ 55 ${{\rm{Q}}_{{\rm{a}}2}}$ 2 ${{\rm{Q}}_{{\rm{b}}1}} {{\rm{Q}}_{{\rm{b}}3}}$ 20 ${{\rm{Q}}_{{\rm{a}}3}} {{\rm{Q}}_{{\rm{c}}2}}$ 38 ${ {\rm{Q} }_{ {\rm{a} }4} } { {\rm{Q} }_{ {\rm{b} }3} }$ 56 ${{\rm{Q}}_{{\rm{a}}3}}$ 3 ${{\rm{Q}}_{{\rm{b}}1}} {{\rm{Q}}_{{\rm{b}}4}}$ 21 ${{\rm{Q}}_{{\rm{a}}4}} {{\rm{Q}}_{{\rm{b}}1}}$ 39 ${ {\rm{Q} }_{ {\rm{a} }4} } { {\rm{Q} }_{ {\rm{b} }4} }$ 57 ${{\rm{Q}}_{{\rm{a}}4}}$ 4 ${{\rm{Q}}_{{\rm{b}}2}} {{\rm{Q}}_{{\rm{b}}3}}$ 22 ${{\rm{Q}}_{{\rm{b}}1}} {{\rm{Q}}_{{\rm{c}}1}}$ 40 ${ {\rm{Q} }_{ {\rm{a} }4} } { {\rm{Q} }_{ {\rm{c} }1} }$ 58 ${{\rm{Q}}_{{\rm{b}}1}}$ 5 ${{\rm{Q}}_{{\rm{b}}2}} {{\rm{Q}}_{{\rm{b}}4}}$ 23 ${{\rm{Q}}_{{\rm{b}}1}} {{\rm{Q}}_{{\rm{c}}2}}$ 41 ${ {\rm{Q} }_{ {\rm{a} }4} } { {\rm{Q} }_{ {\rm{c} }2} }$ 59 ${{\rm{Q}}_{{\rm{b}}2}}$ 6 ${ {\rm{Q} }_{ {\rm{b} }4} } { {\rm{Q} }_{ {\rm{c} }2} }$ 24 ${ {\rm{Q} }_{ {\rm{a} }2} } { {\rm{Q} }_{ {\rm{b} }1} }$ 42 ${ {\rm{Q} }_{ {\rm{a} }4} } { {\rm{Q} }_{ {\rm{c} }3} }$ 60 ${{\rm{Q}}_{{\rm{b}}3}}$ 7 ${{\rm{Q}}_{{\rm{b}}3}} {{\rm{Q}}_{{\rm{c}}4}}$ 25 ${{\rm{Q}}_{{\rm{a}}2}} {{\rm{Q}}_{{\rm{b}}2}}$ 43 ${ {\rm{Q} }_{ {\rm{a} }4} } { {\rm{Q} }_{ {\rm{c} }4} }$ 61 ${{\rm{Q}}_{{\rm{b}}4}}$ 8 ${{\rm{Q}}_{{\rm{c}}1}} {{\rm{Q}}_{{\rm{c}}3}}$ 26 ${{\rm{Q}}_{{\rm{a}}2}} {{\rm{Q}}_{{\rm{b}}3}}$ 44 ${ {\rm{Q} }_{ {\rm{b} }1} } { {\rm{Q} }_{ {\rm{c} }4} }$ 62 ${{\rm{Q}}_{{\rm{c}}1}}$ 9 ${{\rm{Q}}_{{\rm{c}}1}} {{\rm{Q}}_{{\rm{c}}4}}$ 27 ${{\rm{Q}}_{{\rm{a}}2}} {{\rm{Q}}_{{\rm{b}}4}}$ 45 ${ {\rm{Q} }_{ {\rm{b} }2} } { {\rm{Q} }_{ {\rm{c} }1} }$ 63 ${{\rm{Q}}_{{\rm{c}}2}}$ 10 ${{\rm{Q}}_{{\rm{c}}2}} {{\rm{Q}}_{{\rm{c}}3}}$ 28 ${{\rm{Q}}_{{\rm{a}}2}} {{\rm{Q}}_{{\rm{c}}1}}$ 46 ${ {\rm{Q} }_{ {\rm{b} }2} } { {\rm{Q} }_{ {\rm{c} }2} }$ 64 ${{\rm{Q}}_{{\rm{c}}3}}$ 11 ${{\rm{Q}}_{{\rm{c}}2}} {{\rm{Q}}_{{\rm{c}}4}}$ 29 ${ {\rm{Q} }_{ {\rm{a} }2} } { {\rm{Q} }_{ {\rm{c} }2} }$ 47 ${ {\rm{Q} }_{ {\rm{b} }2} } { {\rm{Q} }_{ {\rm{c} }3} }$ 65 ${{\rm{Q}}_{{\rm{c}}4}}$ 12 ${{\rm{Q}}_{{\rm{b}}3}} {{\rm{Q}}_{{\rm{c}}2}}$ 30 ${ {\rm{Q} }_{ {\rm{a} }2} } { {\rm{Q} }_{ {\rm{c} }3} }$ 48 ${ {\rm{Q} }_{ {\rm{b} }2} } { {\rm{Q} }_{ {\rm{c} }4} }$ 66 ${{\rm{Q}}_{{\rm{b}}4}} {{\rm{Q}}_{{\rm{c}}4}}$ 13 ${{\rm{Q}}_{{\rm{a}}1}} {{\rm{Q}}_{{\rm{b}}1}}$ 31 ${ {\rm{Q} }_{ {\rm{a} }2} } { {\rm{Q} }_{ {\rm{c} }4} }$ 49 ${ {\rm{Q} }_{ {\rm{b} }3} } { {\rm{Q} }_{ {\rm{c} }1} }$ 67 ${{\rm{Q}}_{{\rm{a}}1}} {{\rm{Q}}_{{\rm{a}}3}}$ 14 ${{\rm{Q}}_{{\rm{a}}1}} {{\rm{Q}}_{{\rm{b}}2}}$ 32 ${ {\rm{Q} }_{ {\rm{b} }1} } { {\rm{Q} }_{ {\rm{c} }3} }$ 50 ${ {\rm{Q} }_{ {\rm{a} }4} } { {\rm{Q} }_{ {\rm{b} }1} }$ 68 ${{\rm{Q}}_{{\rm{a}}1}} {{\rm{Q}}_{{\rm{a}}4}}$ 15 ${{\rm{Q}}_{{\rm{a}}1}} {{\rm{Q}}_{{\rm{b}}3}}$ 33 ${ {\rm{Q} }_{ {\rm{a} }3} } { {\rm{Q} }_{ {\rm{b} }1} }$ 51 ${ {\rm{Q} }_{ {\rm{a} }1} } { {\rm{Q} }_{ {\rm{c} }3} }$ 69 ${{\rm{Q}}_{{\rm{b}}4}} {{\rm{Q}}_{{\rm{c}}1}}$ 16 ${{\rm{Q}}_{{\rm{a}}1}} {{\rm{Q}}_{{\rm{b}}4}}$ 34 ${ {\rm{Q} }_{ {\rm{a} }3} } { {\rm{Q} }_{ {\rm{b} }2} }$ 52 ${ {\rm{Q} }_{ {\rm{a} }3} } { {\rm{Q} }_{ {\rm{c} }3} }$ 70 ${{\rm{Q}}_{{\rm{a}}2}} {{\rm{Q}}_{{\rm{a}}3}}$ 17 ${{\rm{Q}}_{{\rm{a}}1}} {{\rm{Q}}_{{\rm{c}}1}}$ 35 ${ {\rm{Q} }_{ {\rm{a} }3} } { {\rm{Q} }_{ {\rm{b} }3} }$ 53 ${ {\rm{Q} }_{ {\rm{b} }3} } { {\rm{Q} }_{ {\rm{c} }3} }$ 71 ${{\rm{Q}}_{{\rm{a}}2}} {{\rm{Q}}_{{\rm{a}}4}}$ 18 ${{\rm{Q}}_{{\rm{a}}1}} {{\rm{Q}}_{{\rm{c}}2}}$ 36 ${ {\rm{Q} }_{ {\rm{a} }3} } { {\rm{Q} }_{ {\rm{b} }4} }$ 54 ${ {\rm{Q} }_{ {\rm{a} }1} } { {\rm{Q} }_{ {\rm{c} }4} }$ 72 
下载: 导出CSV
-
[1] 王谦,曹娜. 矿用远距离供电高压变频器输出滤波装置设计[J]. 工矿自动化,2019,45(12):97-100,105. doi: 10.13272/j.issn.1671-251x.17487WANG Qian,CAO Na. Design of output filter of mine-used high-voltage inverter for long-distance power supply[J]. Industry and Mine Automation,2019,45(12):97-100,105. doi: 10.13272/j.issn.1671-251x.17487 [2] 李娜,许燕萍,何凤有. 矿山高压多电平ANPC变频调速系统损耗分析[J]. 工矿自动化,2014,40(11):61-65. doi: 10.13272/j.issn.1671-251x.2014.11.015LI Na,XU Yanping,HE Fengyou. Loss analysis of frequency-conversion speed-regulation system of mine high-voltage multilevel ANPC[J]. Industry and Mine Automation,2014,40(11):61-65. doi: 10.13272/j.issn.1671-251x.2014.11.015 [3] 马铭遥,凌峰,孙雅蓉,等. 三相电压型逆变器智能化故障诊断方法综述[J]. 中国电机工程学报,2020,40(23):7683-7699. doi: 10.13334/J.0258-8013.PCSEE.201235MA Mingyao,LING Feng,SUN Yarong,et al. Review of intelligent fault diagnosis methods for three-phase voltage-mode inverters[J]. Proceedings of the CSEE,2020,40(23):7683-7699. doi: 10.13334/J.0258-8013.PCSEE.201235 [4] LI Haoyang,GUO Yuanbo,XIA Jinhui,et al. Open-circuit fault diagnosis for a fault-tolerant three-level neutral-point-clamped STATCOM[J]. IET Power Electronics,2019,12(4):810-816. doi: 10.1049/iet-pel.2018.5802 [5] 任晓红,万红,俞啸,等. 基于Park变换的三电平逆变器开路故障诊断[J]. 工矿自动化,2020,46(5):82-86,93. doi: 10.13272/j.issn.1671-251x.17523REN Xiaohong,WAN Hong,YU Xiao,et al. Open-circuit fault diagnosis of three-level inverter based on Park transformation[J]. Industry and Mine Automation,2020,46(5):82-86,93. doi: 10.13272/j.issn.1671-251x.17523 [6] 万红,任晓红,范晋瑜,等. 三电平逆变器开路故障诊断研究[J]. 工矿自动化,2020,46(4):66-74. doi: 10.13272/j.issn.1671-251x.2019070045WAN Hong,REN Xiaohong,FAN Jinyu. Research on open-circuit fault diagnosis of three-level inverter[J]. Industry and Mine Automation,2020,46(4):66-74. doi: 10.13272/j.issn.1671-251x.2019070045 [7] 吴传龙,陈伟,刘晓文,等. 基于特征融合的提升机逆变器故障诊断[J]. 工矿自动化,2021,47(5):46-51. doi: 10.13272/j.issn.1671-251x.17772WU Chuanlong,CHEN Wei,LIU Xiaowen,et al. Feature fusion based fault diagnosis of hoist inverter[J]. Industry and Mine Automation,2021,47(5):46-51. doi: 10.13272/j.issn.1671-251x.17772 [8] SZCZESNY R, KURZYNSKI P, PIQUEB H, et al. Knowledge-based system approach to power electronic systems fault diagnosis[C]. Proceedings of the IEEE International Symposium on Industrial Electronics, 1996: 1005-1010. [9] 付娟娟. 基于神经网络的有源中点箝位型三电平逆变器故障诊断系统研究[D]. 徐州: 中国矿业大学, 2016.FU Juanjuan. Study on the fault diagnosis system of active neutral point clamped three level inverter based on neural network[D]. Xuzhou: China University of Mining and Technology, 2016. [10] 姜媛媛,王友仁,吴祎,等. 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):2145-2152. doi: 10.3969/j.issn.0254-3087.2015.09.029JIANG Yuanyuan,WANG Youren,WU Yi,et al. Online multiple fault diagnosis for PV inverter based on wavelet packet energy spectrum and extreme learning machine[J]. Chinese Journal of Scientific Instrument,2015,36(9):2145-2152. doi: 10.3969/j.issn.0254-3087.2015.09.029 [11] 张程. 三电平逆变器故障诊断技术与容错控制策略研究[D]. 徐州: 中国矿业大学, 2019.ZHANG Cheng. Research on fault diagnosis technology and fault tolerant control strategy of the three-level inverter[D]. Xuzhou: China University of Mining and Technology, 2019. [12] 阳瑞霖,何葵东,胡蝶,等. 基于振动信号EMD分解与支持向量机的有载分接开关机械故障诊断[J]. 变压器,2022,59(7):29-33. doi: 10.19487/j.cnki.1001-8425.2022.07.007YANG Ruilin,HE Kuidong,HU Die,et al. Mechanical fault diagnosis of on-load tap-changer based on EMD decomposition of vibration signal and support vector machine[J]. Transformer,2022,59(7):29-33. doi: 10.19487/j.cnki.1001-8425.2022.07.007 [13] 何婷,乔俊强,包建勤,等. 基于EMD和SVM的电力系统故障分类识别[J]. 仪表技术,2022(4):64-69. doi: 10.19432/j.cnki.issn1006-2394.2022.04.001HE Ting,QIAO Junqiang,BAO Jianqin,et al. Fault classification in power system using EMD and SVM[J]. Instrumentation Technology,2022(4):64-69. doi: 10.19432/j.cnki.issn1006-2394.2022.04.001 [14] 李克海. 基于PNN的电力变压器故障诊断方法[J]. 工业仪表与自动化,2014(4):66-69.LI Kehai. Method of power transformer fault diagnosis based on PNN[J]. Industrial Instrumentation & Automation,2014(4):66-69. [15] 安源,张智恒. 基于PNN的电力变压器故障诊断[J]. 电气应用,2020,39(11):12-17.AN Yuan,ZHANG Zhiheng. Fault diagnosis of power transformer based on PNN[J]. Electrotechnical Application,2020,39(11):12-17. -
点击查看大图
图(13) / 表(1)
计量
- 文章访问数: 94
- HTML全文浏览量: 31
- PDF下载量: 15
- 被引次数: 0
