压缩感知字典迁移重构的小样本轴承故障诊断

PDF(3265 KB)

振动与冲击 ›› 2024, Vol. 43 ›› Issue (5) : 62-71.

论文

孙洁娣1,2，赵彬集1，温江涛3，时培明3

作者信息 +

Small sample bearing fault diagnosis based on compressed sensing reconstruction and dictionary transfer

SUN Jiedi1,2,ZHAO Binji1,WEN Jiangtao3,SHI Peiming3

Author information +

文章历史 +

摘要

针对实际应用中智能轴承故障诊断面临标签样本严重不足的问题，本文提出一种结合压缩感知、字典学习和迁移的数据增强算法，用于小样本故障诊断研究。首先，利用源域标签数据通过小波包字典学习和优化方法生成特定源域字典，并得到共享表示系数，获取故障内在信息；之后采用少量目标域信号微调共享表示系数，并更新源域字典生成迁移字典；最后通过共享表示系数和迁移字典生成大量具有目标域特征的新样本，实现数据增强。文中采用常用的深度故障诊断网络对本文的数据增强算法进行了诊断性能验证，结果表明该方法产生的信号具有故障的有效信息，用于模型训练和识别能够取得较好的诊断性能。本文方法为小样本故障诊断问题提出了新的思路。

Abstract

To address the problem of the severe shortage of label samples for intelligent bearing fault diagnosis in practical applications, this paper proposes a data enhancement method combining compressed sensing, dictionary learning and transfer for small sample fault diagnosis research. Firstly, the source domain label data is used to generate a specific source domain dictionary through wavelet packet dictionary learning and optimization processing, and the shared representation coefficients are obtained to acquire the intrinsic fault information; then a small amount of target domain signals are used to fine-tune the shared representation coefficients, and the source domain dictionary is updated to generate a transfer dictionary; finally, a large number of new samples with target domain characteristics are generated through the representation coefficients and transfer dictionary to achieve data enhancement. The data augmentation algorithm is validated using a commonly used deep fault diagnosis network, and the results show that the signals generated by the method have valid information about the fault and can be used for model training and identification with good diagnostic performance. The proposed method provides a new idea for the small sample fault diagnosis.

导出引用

孙洁娣1,2，赵彬集1，温江涛3，时培明3. 压缩感知字典迁移重构的小样本轴承故障诊断[J]. 振动与冲击, 2024, 43(5): 62-71

SUN Jiedi1,2,ZHAO Binji1,WEN Jiangtao3,SHI Peiming3. Small sample bearing fault diagnosis based on compressed sensing reconstruction and dictionary transfer[J]. Journal of Vibration and Shock, 2024, 43(5): 62-71

参考文献

[1] Lei Y, Yang B, Jiang X, et al. Applications of machine learning to machine fault diagnosis: A review and roadmap[J]. Mechanical Systems and Signal Processing, 2020,138:106587. [2] Kumar A, Gandhi C P, Zhou Y Q, et al. Latest developments in gear defect diagnosis and prognosis: A review[J]. Measurement, 2020,158:107735. [3] Deng W, Liu H L, Xu J J, et al. An Improved Quantum-Inspired Differential Evolution Algorithm for Deep Belief Network [J]. IEEE Transactions on Instrumentation and Measurement, 2020,69(10):7319-7327. [4] Kiranyaz S, Avci O, Abdeljaber O, et al. 1D convolutional neural networks and applications: A survey[J]. Mechanical Systems and Signal Processing, 2021,151:107398. [5] Sun J, Yan C, Wen J. Intelligent Bearing Fault Diagnosis Method Combining Compressed Data Acquisition and Deep Learning[J]. IEEE Transactions on Instrumentation and Measurement, 2018, 67(1):185-195. [6] Li X, Zhang W, Ding Q. Cross-Domain Fault Diagnosis of Rolling Element Bearings Using Deep Generative Neural Networks[J]. IEEE Transactions on Industrial Electronics, 2019,66(7): 5525-5534. [7] Shao S, Mcaleer S, Yan R, et al. Highly Accurate Machine Fault Diagnosis Using Deep Transfer Learning[J]. IEEE Transactions on Industrial Informatics, 2019,15(4): 2446-2455. [8] Sejdinovic D, Sriperumbudur B, Gretton A, et al. Equivalence of Distance-Based and RKHS-Based Statistics In Hypothesis Testing [J]. Annals of Statistics, 2013,41(5):2263-2291. [9] Wan L J, Li Y Y, Chen K Y, et al. A novel deep convolution multi-adversarial domain adaptation model for rolling bearing fault diagnosis[J]. Measurement, 2022,191. [10] Jiao J Y, Zhao M, Lin J, et al. Residual joint adaptation adversarial network for intelligent transfer fault diagnosis[J]. Mechanical Systems and Signal Processing, 2020, 145:106962. [11] Wu Z, Jiang H, Liu S, et al. A deep reinforcement transfer convolutional neural network for rolling bearing fault diagnosis.[J]. ISA transactions, 2022, 129: 505-524. [12] Yin Z, Zhao M, Zhang W, et al. Physiological-signal-based mental workload estimation via transfer dynamical autoencoders in a deep learning framework[J]. Neurocomputing, 2019, 347:212-229. [13] Si J, Shi H, Chen J, et al. Unsupervised deep transfer learning with moment matching: A new intelligent fault diagnosis approach for bearings [J]. Measurement, 2021,172: 108827. [14] Yu K, Lin T R, Ma H, 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. [15] Li X, Zhang W, Ding Q, et al. Intelligent rotating machinery fault diagnosis based on deep learning using data augmentation[J]. Journal of Intelligent Manufacturing, 2020, 31(2):433-452. [16] Zhang W, Li C, Peng G, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J]. Mechanical Systems and Signal Processing, 2018,100:439-453. [17] Nath A G, Sharma A, Udmale S S, et al. An Early Classification Approach for Improving Structural Rotor Fault Diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2021,70:1-13. [18] Gong X, Qiao W. Current-Based Mechanical Fault Detection for Direct-Drive Wind Turbines via Synchronous Sampling and Impulse Detection[J]. IEEE Transactions on Industrial Electronics, 2015, 62(3): 1693-1702. [19] W. L, B. L, Y. C, et al. Deep Model Based Domain Adaptation for Fault Diagnosis[J]. IEEE Transactions on Industrial Electronics, 2017,64(3): 2296-2305. [20] Lv H, Chen J, Zhang T, et al. SDA: Regularization with Cut-Flip and Mix-Normal for machinery fault diagnosis under small dataset[J]. ISA Transactions, 2021,111:337-349. [21] Wei J, Huang H, Yao L, et al. New imbalanced fault diagnosis framework based on Cluster-MWMOTE and MFO-optimized LS-SVM using limited and complex bearing data[J]. Engineering Applications of Artificial Intelligence, 2020,96:103966. [22] Vo M T, Nguyen T, Vo H A, et al. Noise-adaptive synthetic oversampling technique[J]. Applied Intelligence, 2021,51(11):7827-7836. [23] Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative Adversarial Nets: Advances In Neural Information Processing Systems 27 (NIPS 2014), 28th Conference on Neural Information Processing Systems (NIPS), 2014[C].2014. [24] Zhang T, Chen J, Li F, et al. A Small Sample Focused Intelligent Fault Diagnosis Scheme of Machines via Multimodules Learning With Gradient Penalized Generative Adversarial Networks[J]. IEEE Transactions on Industrial Electronics, 2021,68(10):10130-10141. [25] Zhang W, Li X, Jia X, et al. Machinery fault diagnosis with imbalanced data using deep generative adversarial networks[J]. Measurement, 2020,152:107377. [26] Wan W, He S, Chen J, et al. QSCGAN: An Un-Supervised Quick Self-Attention Convolutional GAN for LRE Bearing Fault Diagnosis Under Limited Label-Lacked Data[J]. IEEE Transactions on Instrumentation and Measurement, 2021,70:1-16. [27] 温江涛，闫常弘，孙洁娣，乔艳雷. 基于压缩采集与深度学习的轴承故障诊断方法[J]，仪器仪表学报，2018, 39(01): 171-179. WEN J, YAN C, SUN J. Bearing fault diagnosis method based on compressed acquisition and deep learning[J]. Chinese Journal of Scientific Instrument, 2018, 39(01):171-179. [28] Qin Y, Zou J Q, Tang B P, et al. Transient Feature Extraction by the Improved Orthogonal Matching Pursuit and K-SVD Algorithm With Adaptive Transient Dictionary[J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2020,16(1):215-227. [29] Huang K K, Wu Y M, Long C, et al. Adaptive process monitoring via online dictionary learning and its industrial application[J]. ISA Transactions, 2021, 114: 399-412. [30] Wang H, Dong G M, Chen J, et al. A novel dictionary learning named deep and shared dictionary learning for fault diagnosis[J]. Mechanical Systems and Signal Processing, 2023,182. [31] Zhao Y K, Zhang X, Wang J X, et al. A new data fusion driven-sparse representation learning method for bearing intelligent diagnosis in small and unbalanced samples[J]. Engineering Applications of Artificial Intelligence, 2023,117. [32] Chen Z Q, Guo L, Gao H L, et al. A fault pulse extraction and feature enhancement method for bearing fault diagnosis[J]. Measurement, 2021,182. [33] Pan T, Chen J, Zhang T, et al. Generative adversarial network in mechanical fault diagnosis under small sample: A systematic review on applications and future perspectives[J]. ISA Transactions, 2022,128:1-10. [34] Candes E J, Wakin M B. An introduction to compressive sampling[J]. IEEE Signal Processing Magazine, 2008,25(2):21-30. [35] Wang C, Gan M, Zhu C A. Fault feature extraction of rolling element bearings based on wavelet packet transform and sparse representation theory[J]. Journal of Intelligent Manufacturing, 2018,29(4):937-951. [36] 郭俊锋, 石斌, 魏兴春, 等. 基于K-SVD字典学习算法的稀疏表示振动信号压缩测量重构方法[J]. 机械工程学报, 2018,54(07): 97-106. GUO Junfeng, SHI Bin, WEI Xingchun, et al. A method of reconstruction of compressed measuring for mechanical vibration signals based on K-SVD Dictionary-training algorithm spares representation [J], Journal of Mechanical Engineering, 2018,54(07): 97-106. [37] 温江涛, 孙洁娣, 于洋, 等. 基于小波包字典优化的旋转机械振动信号压缩感知重构方法[J]. 振动与冲击, 2018, 37(22):164-172. WEN Jiangtao, SUN Jiedi, YU Yang, et al. Compressed sensing reconstruction for rotating machinery vibration signals based on the wavelet packet dictionary optimization [J], Journal of Vibration and Shock, 2018, 37(22):164-172. [38] Wen J, Zhou Z, Wang J, et al. A Sharp Condition for Exact Support Recovery With Orthogonal Matching Pursuit[J]. IEEE Transactions on Signal Processing, 2017, 65(6):1370-1382. [39] Kong Y, Wang T Y, Qin Z Y, et al. Sparse Representation Classification With Structured Dictionary Design Strategy for Rotating Machinery Fault Diagnosis[J]. IEEE Access, 2021,9:10012-10024. [40] Case Western Reserve University[EB/OL]. http: //csegroups.case.edu/bearingdatacenter/home. [41] Society for machinery failure prevention technology[EB/OL].