针对光伏逆变器的绝缘栅双极型晶体管(insulated gate bipolar transistor, IGBT)接线故障不易发现且易被忽略,现有方法诊断速度慢、识别率低的问题,提出了一种基于电压均值的特征提取策略,并利用改进狮群算法(improved loin swarm optimization, ILSO)优化核极限学习机(kernel extreme learning machine, KELM),实现对IGBT的故障诊断.首先,分析逆变器各状态下三相电压Concordia变换后的效果,获得表征故障特征的二维向量,通过二维散点图验证接线故障的可分性;其次,通过Sine混沌映射改进的狮群算法(loin swarm optimization, LSO)对KELM进行参数寻优,建立诊断模型;最后,以Z源逆变器为例进行验证.结果表明:对于逆变器的IGBT接线故障,所提方法能提取包含丰富故障信息的二维故障特征,极大地简化了特征提取的过程,且诊断方法适用于单个和2个器件的故障类型,与其他方法相比速度更快,故障识别率更高.
To solve the problem that insulated gate bipolar transistor wiring fault of photovoltaic inverters are difficult to be found and are easily to be ignored, and the existing diagnostic methods are slow and have low recognition rate, a feature extraction strategy based on voltage mean is proposed, and the kernel extreme learning machine(KELM)is optimized using improved loin swarm optimization(ILSO)to achieve fault diagnosis of IGBTs. Firstly, the effect of the Concordia transformation of the three-phase voltage in each state of the inverter is analyzed to obtain a two-dimensional vector that clearly characterizes the fault, and the separability of the wiring fault is verified by a two-dimensional scatter plot. Secondly, the parameters of KELM are optimized by the LSO of Sine chaotic mapping to establish the diagnostic model. Finally, the Z-source inverter is taken as an example for verification. The results show that the proposed method can extract two-dimensional fault features containing rich fault information for IGBT wiring faults of inverters, which greatly simplifies the process of feature extraction. Moreover, the proposed method is suitable for single and double device fault types. Compared with other methods, the proposed method is faster and has higher fault recognition rate.
[1] 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. DOI: 10.19595/j.cnki.1000-6753.tces.L70547.
[2] BANDYOPADHYAY I, PURKAIT P, KOLEY C. A SVM based classifier for identification of spurious resistance rault involving IGBTs in VSI based Induction Motor Drive[C] //2018 IEEE Applied Signal Processing Conference(ASPCON). December 7-9, 2018, Kolkata, India. IEEE, 2019: 9-13. DOI: 10.1109/ASPCON.2018.8748606.
[3] KESWANI R A, SURYAWANSHI H M, BALLAL M S. Multi-resolution analysis for converter switch faults identification[J]. IET Power Electron, 2015, 8(5): 783-792. DOI: 10.1049/iet-pel.2014.0450.
[4] 胡亮灯,孙驰,陈玉林,等.大功率IGBT的短路故障检测[J].电工技术学报, 2018, 33(11):2592-2603. DOI: 10.19595/j.cnki.1000-6753.tces.170360.
[5] 陈超波,王霞霞,高嵩,等.基于区间滑模观测器的逆变器开路故障诊断方法[J].中国电机工程学报, 2020, 40(14): 4569-4579. DOI: 10.13334/j.0258-8013.pcsee.190886.
[6] 周晨阳,沈艳霞.基于小波分析的二重三相电压型逆变器开路故障诊断[J].电机与控制学报, 2020, 24(9):65-75. DOI: 10.15938/j.emc.2020.09.008.
[7] GUZMAN H, BARRERO F, DURAN M J. IGBT-gating failure effect on a fault-tolerant predictive current-controlled five-phase induction motor drive[J]. IEEE Trans Ind Electron, 2015,62(1): 15-20. DOI: 10.1109/TIE.2014.2331019.
[8] BANDYOPADHYAY I, PURKAIT P, KOLEY C. A combined image processing and Nearest Neighbor Algorithm tool for classification of incipient faults in induction motor drives[J]. Comput Electr Eng, 2016, 54: 296-312. DOI: 10.1016/j.compeleceng.2016.01.014.
[9] BANDYOPADHYAY I, PURKAIT P, KOLEY C. Performance of a classifier based on time-domain features for incipient fault detection in inverter drives[J]. IEEE Trans Ind Inform, 2019, 15(1): 3-14. DOI: 10.1109/TII.2018.2854885.
[10] ORAON B, DAS S, DAS S, et al. Spurious resistance identification in SPWM inverter circuit feeding power to induction motor[C] //2017 3rd International Conference on Condition Assessment Techniques in Electrical Systems(CATCON). November 16-18, 2017, Rupnagar, India. IEEE, 2018: 216-221. DOI: 10.1109/CATCON.2017.8280215.
[11] RAJ N, MATHEW J, JAGADANAND G, et al. Open-transistor fault detection and diagnosis based on current trajectory in a two-level voltage source inverter[J]. Procedia Technol, 2016, 25: 669-675. DOI: 10.1016/j.protcy.2016.08.159.
[12] 谢东,葛兴来.基于残差变化率的单相级联H桥整流器IGBT开路故障诊断[J].电工技术学报, 2018, 33(16):3822-3834. DOI: 10.19595/j.cnki.1000-6753.tces.180484.
[13] 崔江,王强,龚春英.结合小波与Concordia变换的逆变器功率管故障诊断技术研究[J].中国电机工程学报, 2015, 35(12): 3110-3116.. DOI: 10.13334/j.0258-8013.pcsee.2015.12.023.
[14] 唐圣学,王维威,马强,等.三电平逆变器IGBT器件接线故障在线诊断方法研究[J].仪器仪表学报, 2020, 41(11): 19-30. DOI: 10.19650/j.cnki.cjsi.J2006888.
[15] 崔博文,任章.基于傅里叶变换和神经网络的逆变器故障检测与诊断[J].电工技术学报, 2006, 21(7)37-43. DOI: 10.3321/j.issn: 1000-6753.2006.07.008.
[16] 耿乙文,李伟,王凯.一种三相光伏并网逆变器故障诊断方法[J].电工技术学报, 2014, 29(Supp 1): 203-209.
[17] CHENG S, CHEN Y T, YU T J, et al. A novel diagnostic technique for open-circuited faults of inverters based on output line-to-line voltage model[J]. IEEE Trans Ind Electron, 2016, 63(7): 4412-4421. DOI: 10.1109/TIE.2016.2535960.
[18] CASEIRO L M A, MENDES A M S. Real-time multiple IGBT open-circuit fault diagnosis in three-level neutral-point-clamped converters with no additional sensors[C] //IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society. November 9-12, 2015, Yokohama, Japan. IEEE, 2016: 3181-3186. DOI: 10.1109/IECON.2015.7392590.
[19] 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.0254-3087.2015.09.029.
[20] 吴滨源,李建文,李永刚,等.基于知识和数据联合驱动的并网逆变器多工况阻抗获取方法[J].电力系统自动化, 2022, 46(6): 83-91. DOI: 10.7500/AEPS20210605001.
[21] 李兵,崔介兵,何怡刚,等.基于能量谱熵及小波神经网络的 有源中性点钳位三电平逆变器故障诊断[J].电工技术学报, 2020, 35(10): 2216-2225. DOI: 10.19595/j.cnki.1000-6753.tces.190429.
[22] 李彦苍,巩翔宇.基于信息熵的改进狮群算法及其在组合优化中的应用[J].电子学报, 2021, 49(8):1577-1585. DOI: 10.12263/DZXB.20200143.
[23] 吕鑫,慕晓冬,张钧,等.混沌麻雀搜索优化算法[J].北京航空航天大学学报, 2021, 47(8):1712-1720. DOI: 10.13700/j.bh.1001-5965.2020.0298.
[24] 肖成龙,孙颖,林邦姜,等.基于神经网络与复合离散混沌系统的双重加密方法[J].电子与信息学报, 2020, 42(3):687-694. DOI: 10.11999/JEIT190213. (
