基于CEEMD与改进的ELM旋转整流器故障诊断

朱佩荣; 刘勇智; 刘棕成; 陈俊柏; 聂恺

doi:10.13700/j.bh.1001-5965.2021.0376

基于CEEMD与改进的ELM旋转整流器故障诊断

doi: 10.13700/j.bh.1001-5965.2021.0376

1.
空军工程大学研究生院，西安 710038
2.
空军工程大学航空工程学院，西安 710038

基金项目: 西安市青年人才托举计划项目(095920201309)

详细信息

通讯作者:
E-mail：liuyz_kj@163.com

中图分类号: V242.44
计量
- 文章访问数: 236
- HTML全文浏览量: 55
- PDF下载量: 37
- 被引次数: 0
出版历程
- 收稿日期: 2021-07-06
- 录用日期: 2021-11-14
- 网络出版日期: 2022-01-04
- 整期出版日期: 2023-05-31

Fault diagnosis of synchronous generator rotating rectifier based on CEEMD and improved ELM

1.
School of Graduate，Air Force Engineering University，Xi’an 710038，China
2.
School of Aviation Engineering，Air Force Engineering University，Xi’an 710038，China

Funds: Xi’an Youth Talent Lift Project (095920201309)

More Information

Corresponding author: E-mail：liuyz_kj@163.com

摘要

摘要:
针对目前应用于航空发电机旋转整流器故障诊断中的人工智能算法存在诊断速度慢、参数选取困难等问题，提出一种基于互补式集合经验模态分解（CEEMD）与樽海鞘优化的极限学习机（SSA-ELM）故障诊断方法。在有限元软件Maxwell与Simplorer中搭建三级式电机模型，采集励磁电流信号，利用CEEMD将励磁电流信号分解为一系列模态分量，构建故障特征参量，再通过樽海鞘群算法（SSA）优化极限学习机的训练参数$ \omega $和$ b $，并对故障进行诊断，最后通过实验平台验证所提方法。结果证明了三级式同步电机有限元模型的有效性，所提方法相校于现有方法，具有更高的故障诊断准确率与分类速度。
- 互补式集合经验模态分解 /
- 极限学习机 /
- 旋转整流器 /
- 故障诊断 /
- 有限元 /
- 樽海鞘群算法
Abstract:
Aiming at the problems of slow diagnostic speed and difficulty in pardmeter selection in artifical intelligence algorithms currently used in fault diagnosis of aviation generator rotating rectifiers, an extreme learning machine (SSA-ELM) and complementary ensemble empirical mode decomposition (CEEMD) based fault diagnosis approach is investigated. In the finite element software Maxwell and Simplorer, the three-stage motor model is built, the excitation current signal is collected, the excitation current signal is decomposed into a series of modal components by CEEMD, and the fault characteristic parameters are constructed. Then the training parameters and parameters of the extreme learning machine are optimized by the SSA algorithm, and the fault is diagnosed. Finally, it is verified by the experimental platform. The results show the effectiveness of the three-stage synchronous motor finite element model.Compared with the existing methods, the rotating rectifier diode fault diagnosis method based on CEEMD and SSA-ELM has higher fault diagnosis accuracy and classification speed.
- complementary ensemble empirical mode decomposition /
- extreme learning machine /
- rotating rectifier /
- fault diagnosis /
- finite element method /
- salps group algorithm

HTML全文

图 1 主发电机有限元2D模型

Figure 1. 2D finite element model of main generator

下载: 全尺寸图片幻灯片

图 2 三级式同步电机整体模型

Figure 2. Integral model of three stage synchronous motor

下载: 全尺寸图片幻灯片

图 3 调压器模型

Figure 3. Voltage regulator model

下载: 全尺寸图片幻灯片

图 4 主发电机三相输出电压波形

Figure 4. Three phase output voltage waveform of main generator

下载: 全尺寸图片幻灯片

图 5 CEEMD信号分解流程

Figure 5. Signal decomposition flow chart of CEEMD

下载: 全尺寸图片幻灯片

图 6 SSA-ELM算法流程

Figure 6. Flow chart of SSA-ELM algorithm

下载: 全尺寸图片幻灯片

图 7 5类故障状态下的励磁电流信号

Figure 7. Excitation current signals under five fault states

下载: 全尺寸图片幻灯片

图 8 D1二极管开路时励磁电流IMF分量的时域图

Figure 8. Time domain diagram of IMF component of excitation current in D1 diode open circuit

下载: 全尺寸图片幻灯片

图 9 D1二极管开路时IMF分量能量熵

Figure 9. Energy entropy of IMF component in D1 diode open circuit

下载: 全尺寸图片幻灯片

图 10 不同故障状态下的能量熵

Figure 10. Energy entropy under different fault states

下载: 全尺寸图片幻灯片

图 11 本文方法的故障诊断结果

Figure 11. Fault diagnosis results based on proposed method

下载: 全尺寸图片幻灯片

图 12 三级式同步发电机实验台

Figure 12. Three stage synchronous generator experiment bed

下载: 全尺寸图片幻灯片

图 13 空载条件下D1二极管开路励磁电流

Figure 13. Waveform of D1 diode open circuit excitation current under no load condition

下载: 全尺寸图片幻灯片

表 1 主发电机基本参数

Table 1. Basic parameters of main generator

额定功率/kVA	额定电压/V	额定频率/Hz	极对数
40	115	400	2

下载: 导出CSV

表 2 二极管开路故障下的5类故障状态

Table 2. Five kinds of fault states under diode open circuit fault

故障类型	状态描述	故障二极管
类别Ⅰ	二极管正常
类别Ⅱ	单个二极管开路	D1、D2、D3、D4、D5、D6
类别Ⅲ	同桥臂双二极管开路	D1D6、D2D5、D3D4
类别Ⅳ	不同桥臂双二极管开路（同为上桥臂或下桥臂）	D1D2、D1D3、D2D3、D6D5、D6D4、D5D4
类别Ⅴ	不同桥臂双二极管开路（一个为上桥臂一个为下桥臂）	D1D5、D1D4、D2D6、D2D4、D3D6、D3D5

下载: 导出CSV

表 3 不同负载条件下各分类方法仿真结果性能对比

Table 3. Simulation result of performance comparison of different classification methods under different load conditions

负载条件	训练时间/s					测试时间/s
负载条件	本文方法	ELM	PSO-ELM	SVM	SSA-SVM	本文方法	ELM	PSO-ELM	SVM	SSA-SVM
空载	10.2598	0.0128	100	0	0.0129	0.0127	84.00	10.9653	14.6525	0.0127
1.5 kW负载	10.3564	0.0135	100	0	0.0145	0.0136	86.00	11.3256	14.7869	0.0145
3 kW负载	10.3256	0.0139	100	0	0.0142	0.0137	87.60	10.2569	14.6598	0.0144
混合负载	29.8579	0.0405	100	0	0.0435	0.0412	81.20	32.1546	44.2698	0.0412

负载条件	准确率/%					诊断方差
负载条件	本文方法	ELM	PSO-ELM	SVM	SSA-SVM	本文方法	ELM	PSO-ELM	SVM	SSA-SVM
空载	95.60	2.5689	82.5320	0.0232	91.60	0.2365	20.3012	0.0362	100	0
1.5 kW负载	96.40	3.2564	83.2365	0.0210	94.00	0.2589	20.2562	0.0359	100	0
3 kW负载	95.60	2.3546	82.4562	0.0234	93.20	0.3545	20.2564	0.0362	100	0
混合负载	95.60	8.2546	247.6020	0.0694	89.6	0.8456	60.6526	0.1089	100	0

下载: 导出CSV

表 4 不同负载条件下各分类方法实验结果性能对比

Table 4. Experimental results of performance comparison of different classification methods under different load conditions

负载条件	训练时间/s					测试时间/s
负载条件	本文方法	ELM	PSO-ELM	SVM	SSA-SVM	本文方法	ELM	PSO-ELM	SVM	SSA-SVM
空载	10.2598	0.0128	100	0	0.0129	0.0127	84.00	10.2489	14.6525	0.0127
1.5 kW负载	10.3564	0.0135	100	0	0.0145	0.0136	86.00	10.2587	14.7869	0.0145
3 kW负载	10.3256	0.0139	100	0	0.0142	0.0137	87.60	10.8596	14.6598	0.0144
混合负载	29.8579	0.0405	100	0	0.0435	0.0412	81.20	30.2156	44.2698	0.0412

负载条件	准确率/%					诊断方差
负载条件	本文方法	ELM	PSO-ELM	SVM	SSA-SVM	本文方法	ELM	PSO-ELM	SVM	SSA-SVM
空载	95.60	2.3568	82.5320	0.0232	91.60	0.2156	20.3012	0.0362	100	0
1.5 kW负载	96.40	2.9586	83.2365	0.0210	94.00	0.2698	20.2562	0.0359	100	0
3 kW负载	95.60	2.4788	82.4562	0.0234	93.20	0.2568	20.2564	0.0362	100	0
混合负载	95.60	7.8964	247.6020	0.0694	89.6	0.7549	60.6526	0.1089	100	0

下载: 导出CSV

参考文献(15)

[1]	孔祥浩, 张卓然, 陆嘉伟, 等. 分布式电推进飞机电力系统研究综述[J]. 航空学报, 2018, 39(1): 021651. KONG X H, ZHANG Z R, LU J W, et al. Review of electric power system of distributed electric propulsion aircraft[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(1): 021651(in Chinese).
[2]	MADONNA V, GIANGRANDE P, GALEA M. Electrical power generation in aircraft: Review, challenges, and opportunities[J]. IEEE Transactions on Transportation Electrification, 2018, 4(3): 646-659. doi: 10.1109/TTE.2018.2834142
[3]	唐军祥. 航空三级式发电机旋转整流器故障诊断技术研究[D]. 南京: 南京航空航天大学, 2017: 1-3. TANG J X. Research on fault diagnosis technology of aircraft three-stage generator rotating rectifier[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2017: 1-3(in Chinese) .
[4]	BATZEL T D, SWANSON D C. Prognostic health management of aircraft power generators[J]. IEEE Transactions on Aerospace and Electronic Systems, 2009, 45(2): 473-482. doi: 10.1109/TAES.2009.5089535
[5]	任磊, 韦徵, 龚春英, 等. 电力电子电路功率器件故障特征参数提取技术综述[J]. 中国电机工程学报, 2015, 35(12): 3089-3101. doi: 10.13334/j.0258-8013.pcsee.2015.12.021 REN L, WEI Z, GONG C Y, et al. Fault feature extraction techniques for power devices in power electronic converters: A review[J]. Proceedings of the CSEE, 2015, 35(12): 3089-3101(in Chinese). doi: 10.13334/j.0258-8013.pcsee.2015.12.021
[6]	TANTAWY A, KOUTSOUKOS X, BISWAS G. Aircraft power generators: Hybrid modeling and simulation for fault detection[J]. IEEE Transactions on Aerospace and Electronic Systems, 2012, 48(1): 552-571. doi: 10.1109/TAES.2012.6129655
[7]	BATZEL T D, SWANSON D C, DEFENBAUGH J F. Predictive diagnostics for the main field winding and rotating rectifier assembly in the brushless synchronous generator[C]//4th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives. Piscataway: IEEE Press, 2003: 349-354.
[8]	叶纪青. 航空发电机旋转整流器故障特征提取技术研究[D]. 南京: 南京航空航天大学, 2017: 29-40. YE J Q. Research on feature extraction method for rotating rectifier of aircraft generator[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2017: 29-40(in Chinese).
[9]	张敬, 李颖晖, 朱喜华, 等. 三级式发电机旋转整流器故障特征提取[J]. 微电机, 2011, 44(7): 92-96. doi: 10.3969/j.issn.1001-6848.2011.07.022 ZHANG J, LI Y H, ZHU X H, et al. Fault feature extraction for rotating rectifie of three-stage generator[J]. Micromotors, 2011, 44(7): 92-96(in Chinese). doi: 10.3969/j.issn.1001-6848.2011.07.022
[10]	刘勇智, 刘聪. 基于EMD和LS-SVM的旋转整流器故障诊断方法研究[J]. 微电机, 2012, 45(4): 21-24. doi: 10.3969/j.issn.1001-6848.2012.04.006 LIU Y Z, LIU C. Fault diagnose of rotating rectifier based on EMD and LS-SVM[J]. Micromotors, 2012, 45(4): 21-24(in Chinese). doi: 10.3969/j.issn.1001-6848.2012.04.006
[11]	王潇雅, 崔江, 唐军祥, 等. 基于极限学习机的航空旋转整流器故障诊断技术研究[J]. 机械制造与自动化, 2017, 46(5): 219-222. doi: 10.19344/j.cnki.issn1671-5276.2017.05.056 WANG X Y, CUI J, TANG J X, et al. Fault diagnosis technology research of aircraft generator rotating rectifier based on extreme learning machine[J]. Machine Building & Automation, 2017, 46(5): 219-222(in Chinese). doi: 10.19344/j.cnki.issn1671-5276.2017.05.056
[12]	崔江, 郭瑞东, 张卓然, 等. 基于改进DBN的发电机旋转整流器故障特征提取技术[J]. 中国电机工程学报, 2020, 40(7): 2369-2376. doi: 10.13334/j.0258-8013.pcsee.190858 CUI J, GUO R D, ZHANG Z R, et al. Generator rotating rectifier fault feature extraction technique based on improved DBN[J]. Proceedings of the CSEE, 2020, 40(7): 2369-2376(in Chinese). doi: 10.13334/j.0258-8013.pcsee.190858
[13]	崔江, 冯赛, 张卓然, 等. 基于BLS的无刷发电机旋转整流器特征提取技术研究[J]. 中国电机工程学报, 2020, 40(12): 4004-4013. doi: 10.13334/J.0258-8013.PCSEE.190983 CUI J, FENG S, ZHANG Z R, et al. Research on feature extraction technology of brushless generator rotating rectifier based on BLS[J]. Proceedings of the CSEE, 2020, 40(12): 4004-4013(in Chinese). doi: 10.13334/J.0258-8013.PCSEE.190983
[14]	周小麟, 童晓阳. 基于CEEMD-SBO-LSSVR的超短期风电功率组合预测[J]. 电网技术, 2021, 45(3): 855-864. doi: 10.13335/j.1000-3673.pst.2020.0584 ZHOU X L, TONG X Y. Ultra-short-term wind power combined prediction based on CEEMD-SBO-LSSVR[J]. Power System Technology, 2021, 45(3): 855-864(in Chinese). doi: 10.13335/j.1000-3673.pst.2020.0584
[15]	韩宏泉, 吴珊, 侯本伟. 采用核极限学习机的短期需水量预测模型[J]. 哈尔滨工业大学学报, 2022, 54(2): 17-24. doi: 10.11918/202012021 HAN H Q, WU S, HOU B W. Short-term water demand prediction model using kernel-based extreme learning machine[J]. Journal of Harbin Institute of Technology, 2022, 54(2): 17-24(in Chinese). doi: 10.11918/202012021