基于领域自适应改进胶囊网络的跨工况同步电机故障诊断

李俊卿; 刘若尧; 韩小平; 黄涛; 何玉灵

doi:10.19912/j.0254-0096.tynxb.2024-0157

PDF(2627 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (5) : 629-638. DOI: 10.19912/j.0254-0096.tynxb.2024-0157

基于领域自适应改进胶囊网络的跨工况同步电机故障诊断

李俊卿¹, 刘若尧¹, 韩小平¹, 黄涛¹, 何玉灵²

作者信息 +

ACROSS WORKING CONDITIONS FAULT DIAGNOSIS OF SYNCHRONOUS GENERATOR BASED ON DOMAIN ADAPTATION AND IMPROVED CAPSULE NETWORK

Li Junqing¹, Liu Ruoyao¹, Han Xiaoping¹, Huang Tao¹, He Yuling²

Author information +

文章历史 +

摘要

为提高风力发电中同步电机绕组短路故障特征提取能力,解决同步电机运行工况变化引起监测数据分布差异和待诊断样本标签不足的问题,提出一种基于领域自适应改进胶囊网络（DA-ICN）的同步电机故障诊断方法。首先利用改进后的胶囊网络提取源域和目标域中同步电机数据的带有空间信息的故障特征,其次结合领域自适应方法将不同工况中的特征映射到公共特征空间,随后通过改进局部最大均值距离（ILMMD）方法消除不同工况同类故障特征间的分布差异,最终得到跨工况下的同步电机故障诊断模型。经实验室数据验证,DA-ICN模型在各类跨工况实验中的平均诊断精度达到98.44%,特征提取能力、诊断精度和迁移性均优于其他方法,并且能在工况差异较大时有效实现同步电机的跨工况故障诊断。

Abstract

To enhance the extraction of short circuit fault characteristics in synchronous generators used in wind power, this paper introduces a Domain Adaptive Improved Capsule Network （DA-ICN） method tailored for synchronous generator fault diagnosis. This method leverages an improved capsule network to capture fault characteristics enriched with spatial information from generator data across different domains. It then utilizes domain adaptive techniques to align features from varying operating conditions into a unified feature space. The Improved Local Maximum Mean Discrepancy （ILMMD） approach is applied to mitigate the distribution discrepancies of similar fault characteristics under diverse conditions. The culmination of this process is a robust fault diagnosis model that functions effectively across different operating conditions. Experimental results using laboratory data validate the effectiveness of the DA-ICN model, which achieves an impressive average diagnostic accuracy of 98.44% in tests across different operating conditions. The proposed method not only demonstrates superior feature extraction, diagnostic precision, and adaptability compared to existing methods but also effectively handles significant disparities in operating conditions, ensuring reliable fault diagnosis in synchronous generators.

导出引用

李俊卿, 刘若尧, 韩小平, 黄涛, 何玉灵. 基于领域自适应改进胶囊网络的跨工况同步电机故障诊断[J]. 太阳能学报. 2025, 46(5): 629-638 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0157

Li Junqing, Liu Ruoyao, Han Xiaoping, Huang Tao, He Yuling. ACROSS WORKING CONDITIONS FAULT DIAGNOSIS OF SYNCHRONOUS GENERATOR BASED ON DOMAIN ADAPTATION AND IMPROVED CAPSULE NETWORK[J]. Acta Energiae Solaris Sinica. 2025, 46(5): 629-638 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0157

中图分类号： TM341

参考文献

[1] TEYMOORI V, KAMPER M, WANG R J, et al.Sensorless control of dual three-phase permanent magnet synchronous machines: a review[J]. Energies, 2023, 16(3): 1326.
[2] SUTI A, DI RITO G, GALATOLO R.Novel approach to fault-tolerant control of inter-turn short circuits in permanent magnet synchronous motors for UAV propellers[J]. Aerospace, 2022, 9(8): 401.
[3] 戴显阳, 陈前, 宋向金, 等. 采用贝叶斯优化和多尺度卷积网络的五相永磁同步电机匝间短路诊断[J]. 电气工程学报, 2023,18(4):114-123.
DAI X Y, CHEN Q, SONG X J, et al.ITSC fault diagnosis for five-phase permanent magnet synchronous motors using Bayesian optimization and multiscale convolutional neural network[J]. Journal of electrical engineering, 2023, 18(4): 114-123.
[4] JEONG H, MOON S, KIM S W.An early stage interturn fault diagnosis of PMSMs by using negative-sequence components[J]. IEEE transactions on industrial electronics, 2017, 64(7): 5701-5708.
[5] 李俊卿, 李斯璇, 陈雅婷, 等. 一种基于CGAN-CNN的同步电机转子绕组匝间短路故障诊断方法[J]. 电力自动化设备, 2021,41(8):169-174.
LI J Q, LI S X, CHEN Y T, et al.Fault diagnosis method of inter-turn short circuit of rotor winding of synchronous motor based on CGAN-CNN[J]. Electric power automation equipment, 2021, 41(8): 169-174.
[6] SABOUR S, FROSST N, HINTON G E, et al.Dynamic routing between capsules[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach 2017: 3859-3869.
[7] 刘红艳, 刘华新, 朱霄珣. 基于胶囊网络的风电机组主轴承故障诊断研究[J]. 自动化仪表, 2022, 43(3): 15-19.
LIU H Y, LIU H X, ZHU X X.Research on main bearing fault diagnosis of wind turbine based on capsule network[J]. Process automation instrumentation, 2022, 43(3): 15-19.
[8] 张辉, 戈宝军, 韩斌, 等. 基于GAF-CapsNet的电机轴承故障诊断方法[J]. 电工技术学报, 2023, 38(10): 2675-2685.
ZHANG H, GE B J, HAN B, et al.Fault diagnosis method of motor bearing based on GAF-CapsNet[J]. Transactions of China Electrotechnical Society, 2023, 38(10): 2675-2685.
[9] 田淼, 苏晓明, 陈长征, 等. 基于领域自适应的风力机发电机轴承故障诊断方法研究[J]. 太阳能学报, 2023, 44(11): 310-317.
TIAN M, SU X M, CHEN C Z, et al.Research on fault diagnosis method of wind turbine generator bearings based on domain adaptation[J]. Acta energiae solaris sinica, 2023, 44(11): 310-317.
[10] LU W N, LIANG B, CHENG Y, et al.Deep model based domain adaptation for fault diagnosis[J]. IEEE transactions on industrial electronics, 2017, 64(3): 2296-2305.
[11] WEN L, GAO L, LI X Y.A new deep transfer learning based on sparse auto-encoder for fault diagnosis[J]. IEEE Transactions on systems, man, and cybernetics: systems, 2019, 49(1): 136-144.
[12] 袁壮, 董瑞, 张来斌, 等. 深度领域自适应及其在跨工况故障诊断中的应用[J]. 振动与冲击, 2020, 39(12): 281-288.
YUAN Z, DONG R, ZHANG L B, et al.Deep domain adaptation and its application in fault diagnosis across working conditions[J]. Journal of vibration and shock, 2020, 39(12): 281-288.
[13] 宋向金, 孙文举, 刘国海, 等. 深度子领域自适应网络电机滚动轴承跨工况故障诊断[J]. 电工技术学报, 2024, 39(1): 182-193.
SONG X J, SUN W J, LIU G H, et al.Across working conditions fault diagnosis for motor rolling bearing based on deep subdomain adaption network[J]. Transactions of China Electrotechnical Society, 2024, 39(1): 182-193.
[14] 金亮, 闫银刚, 杨庆新, 等. 小样本条件下永磁同步电机深度迁移学习性能预测方法[J]. 电工技术学报, 2023, 38(18): 4921-4931.
JIN L, YAN Y G, YANG Q X, et al.Prediction method of deep transfer learning performance of permanent magnet synchronous motor under the condition of few-shot[J]. Transactions of China Electrotechnical Society, 2023, 38(18): 4921-4931.
[15] PAN X, YU Z M, YANG Z.A deep learning multimodal fusion framework for wood species identification using near-infrared spectroscopy GADF and RGB image[J]. Holzforschung, 2023, 77(11/12): 816-827.
[16] 段晓燕, 焦孟萱, 雷春丽, 等. 基于MTF-MSMCNN的小样本滚动轴承故障诊断方法[J]. 航空动力学报, 2024, 39(1): 240-252.
DUAN X Y, JIAO M X, LEI C L, et al.A rolling bearing fault diagnosis method based on MTF-MSMCNN with small sample[J]. Journal of aerospace power, 2024, 39(1): 240-252.
[17] SZEGEDY C, LIU W, JIA Y Q, et al.Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015: 1-9.
[18] SZEGEDY C, VANHOUCKE V, IOFFE S, et al.Rethinking the inception architecture for computer vision[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016: 2818-2826.
[19] 薛晨兴, 张军, 邢家源. 基于GoogLeNet Inception V3的迁移学习研究[J]. 无线电工程, 2020, 50(2): 118-122.
XUE C X, ZHANG J, XING J Y.Research on transfer learning based on GoogLeNet Inception V3[J]. Radio engineering, 2020, 50(2): 118-122.
[20] PAN C Y, HUANG J, HAO J G, et al.Towards zero-shot learning generalization via a cosine distance loss[J]. Neurocomputing, 2020, 381: 167-176.
[21] LI J Q, LIU J, CHEN Y T.A fault warning for inter-turn short circuit of excitation winding of synchronous generator based on GRU-CNN[J]. Global energy interconnection, 2022, 5(2): 236-248.
[22] 李俊卿, 刘静. 结合卷积神经网络和迁移学习的电机轴承故障诊断方法[J]. 华北电力大学学报(自然科学版), 2023, 50(1):76-83,91.
LI J Q, LIU J.Fault diagnosis method of motor bearing based on CNN and transfer learning[J]. Journal of North China Electric Power University (natural science edition), 2023, 50(1): 76-83, 91.
[23] SVANTESSON M, OLAUSSON H, EKLUND A, et al.Get a new perspective on EEG: convolutional neural network encoders for parametric t-SNE[J]. Brain sciences, 2023, 13(3): 453.