基于包络谱语义构建的零样本滚动轴承复合故障诊断方法

PDF(3725 KB)

振动与冲击 ›› 2024, Vol. 43 ›› Issue (14) : 189-200.

论文

基于包络谱语义构建的零样本滚动轴承复合故障诊断方法

甄冬1,2，孙赫明1，冯国金1,2,3，崔展博3，田少宁1，孔金震1,2

作者信息 +

Zero-shot rolling bearing compound fault diagnosis method based on envelope spectrum semantic construction

ZHEN Dong1,2,SUN Heming1,FENG Guojin1,2,3,CUI Zhanbo3,TIAN Shaoning1, KONG Jinzhen1,2

Author information +

文章历史 +

摘要

深度学习算法在训练集完备的情况下可以实现较高的故障识别率，然而在真实工业场景中，滚动轴承的多种故障可能复合存在，通常难以获取充足的数据用于训练。为解决该问题，提出了一种基于包络谱语义构建的零样本复合故障诊断方法，在训练阶段使用单一故障数据构建了一个语义空间和一个特征空间，然后在识别阶段通过语义空间和特征空间的复合，实现对零样本情况下的复合故障识别。此外，考虑到包络谱能很好地表征滚动轴承故障特征，采用包络谱预处理故障信号以增强轴承故障的特征，并借助信号包络谱的物理含义来构建轴承单一故障和复合故障的语义。实验结果显示，所提模型在复合故障识别上取得了87.83%的准确率，优于对比模型。

Abstract

In real industrial environments, various compound faults may coexist in rolling bearings, making it challenging to acquire ample data for training. To address this issue, a zero-shot compound fault diagnosis approach is proposed based on envelope spectrum semantic construction. During the training phase, a semantic space and a feature space are established using single fault data. Subsequently, during the recognition phase, compound fault recognition in zero-shot scenarios is realized through the combination of the semantic and feature spaces. Furthermore, recognizing the envelope spectrum's capability in effectively characterizing rolling bearing fault features, the fault signals are preprocessed using envelope spectrum to enhance the bearing fault characteristics. The physical significance of the signal envelope spectrum is leveraged to construct the semantics for both single and compound bearing faults. Experimental results reveal that the proposed model achieves an accuracy of 87.83% in compound fault recognition, outperforming the compared models.

导出引用

甄冬1, 2, 孙赫明1, 冯国金1, 2, 3, 崔展博3, 田少宁1, 孔金震1, 2. 基于包络谱语义构建的零样本滚动轴承复合故障诊断方法[J]. 振动与冲击, 2024, 43(14): 189-200

ZHEN Dong1, 2, SUN Heming1, FENG Guojin1, 2, 3, CUI Zhanbo3, TIAN Shaoning1, KONG Jinzhen1, 2. Zero-shot rolling bearing compound fault diagnosis method based on envelope spectrum semantic construction[J]. Journal of Vibration and Shock, 2024, 43(14): 189-200

参考文献

[1] 杨新敏, 郭瑜, 华健翔. 基于阶频谱相干的变转速滚动轴承内外圈复合故障特征分离提取[J]. 振动与冲击, 2022, 41(22): 211-218. YANG Xinmin, GUO Yu, HUA Jianxiang. Feature separation and extraction of compound faults of inner and outer rings of rolling bearings at variable speed based on order-frequency spectral coherence[J]. JOURNAL OF VIBRATION AND SHOCK, 2022, 41(22): 211-218. [2] 袁静, 姚泽, 胡雯玥, 等. 滚动轴承复合故障的时频能量聚集谱诊断方法[J]. 振动与冲击, 2023, 42(2): 285-292+320. YUAN Jing, YAO ze, Z, HU Wenyue, et al. Time-frequency energy aggregation spectrum diagnosis method for compound faults of rolling bearings[J]. JOURNAL OF VIBRATION AND SHOCK, 2023, 42(2): 285-292+320. [3] 张伟, 李军霞, 陈维望. 基于蝙蝠算法优化VMD参数的滚动轴承复合故障分离方法[J]. 振动与冲击, 2022, 41(20): 133-141. ZHANG Wei, LI Junxia, CHEN Weiwang. A compound fault feature separation method of rolling bearings based on vmd optimizeed by the bat algorithm[J]. JOURNAL OF VIBRATION AND SHOCK, 2022, 41(20): 133-141. [4] LI M, LIU Y, ZHI S, et al. Short-time Fourier Transform Using Odd Symmetric Window Function[J]. Journal of Dynamics, Monitoring and Diagnostics, 2021, 1(1): 37-45. [5] 杜康宁，宁少慧，基于迁移学习的滚动轴承复合故障诊断研究[J]. 机床与液压, 2023, 51(13): 198-205. DU Kangning, NING Shaohui,. Research on composite fault diagnosis of rolling bearings based on transfer learning[J]. MACHINE TOOL&HYDRAULICS, 2023, 51(13): 198-205. [6] SHEN J, LI S, JIA F, et al. A Deep Multi-Label Learning Framework for the Intelligent Fault Diagnosis of Machines[J]. IEEE Access, 2020, 8: 113557-113566. [7] LIANG P, WANG W, YUAN X, et al. Intelligent fault diagnosis of rolling bearing based on wavelet transform and improved ResNet under noisy labels and environment[J]. Engineering Applications of Artificial Intelligence, 2022, 115: 105269. [8] 韩涛，袁建虎，唐建，等. 基于MWT和CNN的滚动轴承智能复合故障诊断方法[J]. 机械传动, 2016, 40(12): 139-143. HAN Tao, YUAN Jianhu, Tang jian, et al. An approach of intelligent compound fault diagnosis of rolling bearing based on MWT and CNN[J]. Journal of Mechanical Transmission, 2016, 40(12): 139-143. [9] LI Z, JIANG Y, HU C, et al. Recent progress on decoupling diagnosis of hybrid failures in gear transmission systems using vibration sensor signal: A review[J]. Measurement, 2016, 90: 4-19. [10] YUAN H, WU N, CHEN X. Mechanical Compound Fault Analysis Method Based on Shift Invariant Dictionary Learning and Improved FastICA Algorithm[J]. Machines, 2021, 9(8), 144. [11] XIE W, ZHOU J, LIU T. Blind Fault Extraction of Rolling-Bearing Compound Fault Based on Improved Morphological Filtering and Sparse Component Analysis[J]. Sensors, 2022 22(18), 7093. [12] 张鲁宁, 左信, 刘建伟. 零样本学习研究进展[J]. 自动化学报, 2020, 46(1): 1-23. ZHANG Luning, ZUO Xin, LIU Jianwei. Research and development on zero-shot learning[J]. ACTA AUTOMATICA SINICA, 2020, 46(1): 1-23. [13] 兰红，方治屿. 零样本图像识别[J]. 电子与信息学报, 2020, 42(5): 1188-1200. LAN Hong, FANG Zhiyu. Recent advances in zero-shot learning[J]. Journal of Electronics & Information Technology, 2020, 42(5): 1188-1200. [14] HUANG R, LIAO Y, ZHANG S, et al. Deep Decoupling Convolutional Neural Network for Intelligent Compound Fault Diagnosis[J]. IEEE Access, 2019, 7: 1848-1858. [15] DIBAJ A, Ettefagh M.M, Hassannejad R, A hybrid fine-tuned VMD and CNN scheme for untrained compound fault diagnosis of rotating machinery with unequal-severity faults[J]. Expert Systems with Applications, 2021, 167: 114094. [16] XING S, LEI Y, WANG S, et al. A label description space embedded model for zero-shot intelligent diagnosis of mechanical compound faults[J]. Mechanical Systems and Signal Processing, 2022, 162: 108036. [17] XU Q, LIU C, YANG E, et al. An Improved Convolutional Capsule Network for Compound Fault Diagnosis of RV Reducers[J]. Sensors, 2022, 22(17): 6442. [18] HUANG R, LI J, CHEN J, et al. A Transferable Capsule Network for Decoupling Compound Fault of Machinery[C]//2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). Dubrovnik: IEEE Instrumentation and Measurement Society, 2020 [19] HUANG R, LI J, LIAO Y, et al. Deep Adversarial Capsule Network for Compound Fault Diagnosis of Machinery Toward Multidomain Generalization Task[J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70: 3506311 [20] XU J, LI K. Generative Zero-shot Learning Compound Fault Diagnosis of Bearings[C]//2021 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD). Nanjing: IEEE Instrumentation & Measurement Society，2021. [21] 周龙. 基于零样本学习的轴承复合故障诊断方法研究[D]. 合肥：合肥工业大学，2022. [22] XU J, LIANG S, DING X, et al. A zero-shot fault semantics learning model for compound fault diagnosis[J]. Expert Systems with Applications, 2023, 221: 119642. [23] XU J, LI K, FAN Y, et al. A label information vector generative zero-shot model for the diagnosis of compound faults[J]. Expert Systems With Applications, 2023. 233: 120875. [24] MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed Representations of Words and Phrases and their Compositionality[C] //Conference and Workshop on Neural Information Processing Systems 2013. Stateline: NEURAL INFORMATION PROCESSING SYSTEMS, 2013. [25] SCHONFELD E, EBRAHIMI S, SINHA S, et al. Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach: eprint arXiv:1812.01784, 2019. 8239-8247.