电源学报

一种特定系数小波重构数据增强逆变器故障诊断方法

PDF下载

周健耀中国电源学会会员 , 王天真中国电源学会会员 , 韩金刚中国电源学会高级会员 , 汤天浩中国电源学会会士

电源学报 | 可靠性与诊断 2025,23(5): 289-296

收起

电源学报 |可靠性与诊断 2025 , 23 (5) : 289 -296

一种特定系数小波重构数据增强逆变器故障诊断方法

全屏

[Author(id=1321485707860890314, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=202130210053@stu.shmtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1321485707953165004, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, authorId=1321485707860890314, language=EN, stringName=Jianyao ZHOU, firstName=Jianyao, middleName=null, lastName=ZHOU, prefix=null, suffix=Member, CPSS, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Logistics Engineering College, Shanghai Maritime University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1321485708133520077, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, authorId=1321485707860890314, language=CN, stringName=周健耀中国电源学会会员, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=上海海事大学物流工程学院，上海　201306, bio={"content":"

周健耀（1997—　），男，中国电源学会会员，硕士研究生。研究方向：逆变器故障诊断。E-mail：202130210053@stu.shmtu.edu.cn。

"}, bioImg=null, bioContent=

周健耀（1997—　），男，中国电源学会会员，硕士研究生。研究方向：逆变器故障诊断。E-mail：202130210053@stu.shmtu.edu.cn。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1321485707764421318, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, xref=null, ext=[AuthorCompanyExt(id=1321485707772809927, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, companyId=1321485707764421318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Logistics Engineering College, Shanghai Maritime University, Shanghai 201306, China), AuthorCompanyExt(id=1321485707785392840, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, companyId=1321485707764421318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=上海海事大学物流工程学院，上海　201306)])]), Author(id=1321485708204823247, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wtz0@sina.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1321485708305486545, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, authorId=1321485708204823247, language=EN, stringName=Tianzhen WANG, firstName=Tianzhen, middleName=null, lastName=WANG, prefix=null, suffix=Member, CPSS, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Logistics Engineering College, Shanghai Maritime University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1321485708393566930, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, authorId=1321485708204823247, language=CN, stringName=王天真中国电源学会会员, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=上海海事大学物流工程学院，上海　201306, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1321485707764421318, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, xref=null, ext=[AuthorCompanyExt(id=1321485707772809927, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, companyId=1321485707764421318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Logistics Engineering College, Shanghai Maritime University, Shanghai 201306, China), AuthorCompanyExt(id=1321485707785392840, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, companyId=1321485707764421318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=上海海事大学物流工程学院，上海　201306)])]), Author(id=1321485708473258708, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=jghan@shmtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1321485708557144790, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, authorId=1321485708473258708, language=EN, stringName=Jingang HAN, firstName=Jingang, middleName=null, lastName=HAN, prefix=null, suffix=Senior Member, CPSS, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Logistics Engineering College, Shanghai Maritime University, Shanghai 201306, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1321485708624253655, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1321485706896200385, authorId=1321485708473258708, language=CN, stringName=韩金刚中国电源学会高级会员, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=上海海事大学物流工程学院，上海　201306, bio={"content":"

韩金刚（1977—　），男，中国电源学会高级会员，博士，副教授。研究方向：电力电子技术与装置。E-mail：jghan@shmtu.edu.cn。

"}, bioImg=null, bioContent=

韩金刚（1977—　），男，中国电源学会高级会员，博士，副教授。研究方向：电力电子技术与装置。E-mail：jghan@shmtu.edu.cn。

汤天浩（1955—　），男，中国电源学会会士，博士，教授。研究方向：新能源电源变换技术。E-mail：thtang@shmtu.edu.cn。

"}, bioImg=null, bioContent=

汤天浩（1955—　），男，中国电源学会会士，博士，教授。研究方向：新能源电源变换技术。E-mail：thtang@shmtu.edu.cn。

周健耀中国电源学会会员, 王天真中国电源学会会员, 韩金刚中国电源学会高级会员, 汤天浩中国电源学会会士

作者信息

上海海事大学物流工程学院，上海　201306

通讯作者:

王天真（1978—　），女，中国电源学会会员，通信作者，博士，教授。研究方向：新能源发电系统故障诊断。E-mail：wtz0@sina.com。

作者简介:

周健耀（1997—　），男，中国电源学会会员，硕士研究生。研究方向：逆变器故障诊断。E-mail：202130210053@stu.shmtu.edu.cn。

韩金刚（1977—　），男，中国电源学会高级会员，博士，副教授。研究方向：电力电子技术与装置。E-mail：jghan@shmtu.edu.cn。

汤天浩（1955—　），男，中国电源学会会士，博士，教授。研究方向：新能源电源变换技术。E-mail：thtang@shmtu.edu.cn。

Fault Diagnosis Method for Inverter Based on Data Augmentation with Specific Coefficients Wavelet Reconstruction

Jianyao ZHOU Member, CPSS, Tianzhen WANG Member, CPSS, Jingang HAN Senior Member, CPSS, Tianhao TANG Fellow, CPSS

Affiliations

Logistics Engineering College, Shanghai Maritime University, Shanghai 201306, China

出版时间: 2025-09-30 doi: 10.13234/j.issn.2095-2805.2025.5.289

文章导航

摘要

收起

由于弱监督学习小样本场景下逆变器的故障数据数量不足且类别不平衡，使得基于数据驱动故障诊断方法的性能下降。为克服传统数据增强方法未考虑数据分布特性的缺陷，提出1种特定系数小波重构数据增强的逆变器故障诊断方法。首先对原始小样本数据进行小波包分解并通过计算获得特定系数，对其随机微调后通过小波包重构直接扩充样本，重复该过程以获取数量充足且类别平衡的训练集。然后基于卷积神经网络实现“端到端”的特征提取与故障分类。最后，实验结果表明，所提方法能有效扩充弱监督学习小样本场景下的故障数据，提高故障诊断精度，可作为逆变器小样本故障诊断的数据预处理环节。

关键词

小样本故障诊断 / 数据增强 / 卷积神经网络 / 小波包变换 / 信号分析

Abstract

收起

The performance of a data-driven fault diagnosis method deteriorates due to insufficient number and unbalanced classes of inverter fault data in the case of weakly supervised learning in few-shot scenarios. To overcome the defect of traditional data augmentation methods which do not consider the data distribution characteristics, an inverter fault diagnosis method based on data augmentation with specific coefficients wavelet reconstruction was proposed. First, the raw small sample data was decomposed by wavelet packet, and a specific coefficient was obtained through calculation. After random fine-tuning, the sample was directly expanded by wavelet packet reconstruction. The process was repeated to obtain a sufficient and class-balanced training set. Then, convolutional neural networks were used to achieve “end-to-end” fault feature extraction and classification. Finally, experimental results show that the proposed method can effectively expand the fault data in the case of weakly supervised learning in few-shot scenarios and improve the fault diagnostic accuracy. Therefore, it can be used as data preprocessing in few-shot fault diagnosis of inverters.

Key words

Few-shot fault diagnosis / data augmentation / convolutional neural networks (CNNs) / wavelet packet transform (WPT) / signal analysis

引用本文

周健耀中国电源学会会员, 王天真中国电源学会会员, 韩金刚中国电源学会高级会员, 汤天浩中国电源学会会士. 一种特定系数小波重构数据增强逆变器故障诊断方法. 电源学报, 2025 , 23 (5) : 289 -296 . DOI: 10.13234/j.issn.2095-2805.2025.5.289

Jianyao ZHOU, Tianzhen WANG, Jingang HAN, Tianhao TANG. Fault Diagnosis Method for Inverter Based on Data Augmentation with Specific Coefficients Wavelet Reconstruction[J]. Journal of Power Supply, 2025 , 23 (5) : 289 -296 . DOI: 10.13234/j.issn.2095-2805.2025.5.289

基金

收起

国家自然科学基金资助项目(62573283)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

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. Ma 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. (in Chinese)

[2]

高磊, 吕敬, 马骏超, 等. 基于电路等效的并网逆变器失稳分析与稳定控制[J]. 电工技术学报, 2024, 39(8): 2325-2341. Gao Lei, Lü Jing, Ma Junchao, et al. Instability analysis and stability control of grid-connected inverter based on impedance circuit equivalent[J]. Transactions of China Electrotechnical Society, 2024, 39(8): 2325-2341. (in Chinese)

[3]

孙权, 彭飞, 李宏胜, 等. 样本不均衡下基于CGAN-CNN的逆变器故障诊断方法[J]. 电源学报, 2024, 22(6): 318-326. Sun Quan, Peng Fei, Li Hongsheng, et al. Inverter fault diagnosis method based on CGAN-CNN under sample imbalance[J]. Journal of Power Supply, 2024, 22(6): 318-326. (in Chinese)

[4]

耿俊超, 王天真, 韩金刚, 等. 基于多级特征提取的并网逆变器故障诊断策略[J]. 电源学报, 2022, 20(4): 28-36. Geng Junchao, Wang Tianzhen, Han Jingang, et al. Fault diagnosis strategy based on multi-level feature extraction for grid-connected inverter[J]. Journal of Power Supply, 2022, 20(4): 28-36. (in Chinese)

[5]

王霞霞, 陈超波, 杨雪芹, 等. 基于ESO-MLD的逆变器开路故障快速诊断方法[J]. 电源学报, 2021, 19(3): 153-162. Wang Xiaxia, Chen Chaobo, Yang Xueqin, et al. Fast diagnosis method for open-circuit fault of inverter based on ESO-MLD[J]. Journal of Power Supply, 2021, 19(3): 153-162. (in Chinese)

[6]

Gao Zhiwei, Cecati C, Ding S X. A survey of fault diagnosis and fault-tolerant techniques: part I — Fault diagnosis with model-based and signal-based approaches[J]. IEEE Transactions on Industrial Electronics, 2015, 62(6): 3757-3767.

[7]

Gao Zhiwei, Cecati C, Ding S X. A survey of fault diagnosis and fault-tolerant techniques: part II: Fault diagnosis with knowledge-based and hybrid/active approaches[J]. IEEE Transactions on Industrial Electronics, 2015, 62(6): 3768-3774.

[8]

Cheng Shu, Chen Yating, Yu Tianjian, et al. A novel diagnostic technique for open-circuited faults of inverters based on output line-to-line voltage model[J]. IEEE Transactions on Industrial Electronics, 2016, 63(7): 4412-4421.

[9]

Anand A, Akhil Vinayak B, Raj N, et al. A generalized switch fault diagnosis for cascaded H-bridge multilevel inverters using mean voltage prediction[J]. IEEE Transactions on Industry Applications, 2020, 56(2): 1563-1574.

[10]

冯良骏. 面向零/少样本场景的弱监督学习方法、应用与实现[D]. 杭州: 浙江大学, 2022. Feng Liangjun. Weak supervised learning method, application and implementation for zero/few sample scenarios[D]. Hangzhou: Zhejiang University, 2022. (in Chinese)

[11]

Li Xiang, Zhang Wei, Ding Qian, et al. Intelligent rotating machinery fault diagnosis based on deep learning using data augmentation[J]. Journal of Intelligent Manufacturing, 2020, 31(2): 433-452.

[12]

Wu Fan, Qiu Gen, Zhang Lefei, et al. Disturbance auto-encoder generation model: few-shot learning method for IGBT open-circuit fault diagnosis in three-phase converters[J]. Frontiers in Energy Research, 2023, 10: 1077519.

[13]

Zhao Minghang, Fu Xuyun, Zhang Yongjian, et al. Data augmentation via randomized wavelet expansion and its application in few-shot fault diagnosis of aviation hydraulic pumps[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 71: 3503213.

[14]

Fan Jigang, Yuan Xianfeng, Miao Zhaoming, et al. Full attention Wasserstein GAN with gradient normalization for fault diagnosis under imbalanced data[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 3517516.

[15]

Wang Tianzhen, Qi Jie, Xu Hao, et al. Fault diagnosis method based on FFT-RPCA-SVM for cascaded-multilevel inverter[J]. ISA Transactions, 2016, 60: 156-163.

[16]

刘云鹏, 许自强, 和家慧, 等. 基于条件式Wasserstein生成对抗网络的电力变压器故障样本增强技术[J]. 电网技术, 2020, 44(4): 1505-1513. Liu Yunpeng, Xu Ziqiang, He Jiahui, et al. Data augmentation method for power transformer fault diagnosis based on conditional Wasserstein generative adversarial network[J]. Power System Technology, 2020, 44(4): 1505-1513. (in Chinese)

[17]

Yi Huaikuan, Jiang Qingchao, Yan Xuefeng, et al. Imbalanced classification based on minority clustering synthetic minority oversampling technique with wind turbine fault detection application[J]. IEEE Transactions on Industrial Informatics, 2021, 17(9): 5867-5875.

[18]

Li Hua, Liu Tao, Wu Xing, et al. Enhanced frequency band entropy method for fault feature extraction of rolling element bearings[J]. IEEE Transactions on Industrial Informatics, 2020, 16(9): 5780-5791.

[19]

宫文峰, 陈辉, 张泽辉, 等. 基于改进卷积神经网络的滚动轴承智能故障诊断研究[J]. 振动工程学报, 2020, 33(2): 400-413. Gong Wenfeng, Chen Hui, Zhang Zehui, et al. Intelligent fault diagnosis for rolling bearing based on improved convolutional neural network[J]. Journal of Vibration Engineering, 2020, 33(2): 400-413. (in Chinese)

[20]

Yu Kun, Lin Tian ran, Ma Hui, et al. A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning[J]. Mechanical Systems and Signal Processing, 2021, 146: 107043.

[21]

Zhou Ping, Zhang Ruiyao, Xie Jin, et al. Data-driven monitoring and diagnosing of abnormal furnace conditions in blast furnace ironmaking: an integrated PCA-ICA method[J]. IEEE Transactions on Industrial Electronics, 2021, 68(1): 622-631.

[22]

Fabila-Carrasco J S, Tan Chao, Escudero J. Permutation entropy for graph signals[J]. IEEE Transactions on Signal and Information Processing Over Networks, 2022, 8: 288-300.

[23]

Zhang Peiyun, Shu Sheng, Zhou Mengchu. An online fault detection model and strategies based on SVM-grid in clouds[J]. IEEE/CAA Journal of Automatica Sinica, 2018, 5(2): 445-456.

[24]

De Raadt A, Warrens M J, Bosker R J, et al. Kappa coefficients for missing data[J]. Educational and Psycho-logical Measurement, 2019, 79(3): 558-576.

2025年第23卷第5期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.13234/j.issn.2095-2805.2025.5.289

接收时间：2023-03-14
首发时间：2026-10-26
出版时间：2025-09-30

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2023-03-14
修回日期：2023-05-13
录用日期：2023-06-29

基金

National Natural Soience Foundation of china(62573283)

国家自然科学基金资助项目(62573283)

作者信息

上海海事大学物流工程学院，上海　201306

通讯作者:

王天真（1978—　），女，中国电源学会会员，通信作者，博士，教授。研究方向：新能源发电系统故障诊断。E-mail：wtz0@sina.com。

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2025.5.289

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT