多物理场迁移相关分析的旋转机械智能诊断方法

PDF(1470 KB)

振动与冲击 ›› 2023, Vol. 42 ›› Issue (22) : 332-338.

论文

孙原理1,2，宋志浩2

作者信息 +

Intelligent diagnosis method for rotating machinery based on multi-physics field signal transfer correlation analysis

SUN Yuanli1,2, SONG Zhihao2

Author information +

文章历史 +

摘要

针对传统旋转机械跨工况场景故障诊断中仅利用单一物理场信号而无法充分提取域不变特征以及跨工况诊断准确度提升困难等问题，提出了一种多物理场信号迁移相关分析的智能故障诊断方法。该方法提出的卷积相关分析的多物理场信号融合策略可有效提取多物理场信号之间的空间特性表示，采用最大均值差异优化并缩小不同数据域之间的多物理场信号特征相关度矩阵特征的差异，同时将特征相关度矩阵序列输入构建的长短期记忆神经网络提取信号的时序相关特征，该方法可充分提取多物理场信号的空间和时间相关性特征，有效地提高了迁移诊断准确度。通过搭建的泵组故障模拟试验台利用采集的数据对该方法进行了验证，结果表明，提出的方法能够充分提取多物理场信号的域不变特征，在跨工况故障诊断任务中诊断获得较好的诊断精度。

Abstract

Aiming at the problems that in the traditional fault diagnosis of rotating machinery across working conditions, only a single physical field signal is used to fully extract domain invariant features and the difficulty of improving the accuracy of cross-working condition diagnosis, an intelligent multi-physics field signal transfer correlation analysis is proposed. Fault diagnosis method. The multiphysics signal fusion strategy of convolution correlation analysis proposed by this method can effectively extract the spatial characteristic representation between multiphysics signals, and optimize and reduce the characteristic correlation matrix of multiphysics signals between different data domains by using the maximum mean difference At the same time, the feature correlation matrix sequence is input into the constructed long-term short-term memory neural network to extract the temporal correlation characteristics of the signal. This method can fully extract the spatial and temporal correlation characteristics of multi-physics field signals, effectively improving the accuracy of transfer diagnosis. Spend. The method is verified by using the collected data on the pump fault simulation test bench built. The results show that the proposed method can fully extract the domain invariant characteristics of multi-physics field signals, and obtain better diagnostic results in cross-condition fault diagnosis tasks.

导出引用

孙原理1,2，宋志浩2. 多物理场迁移相关分析的旋转机械智能诊断方法[J]. 振动与冲击, 2023, 42(22): 332-338

SUN Yuanli1,2, SONG Zhihao2. Intelligent diagnosis method for rotating machinery based on multi-physics field signal transfer correlation analysis[J]. Journal of Vibration and Shock, 2023, 42(22): 332-338

参考文献

[1] Biet M. Rotor faults diagnosis using feature selection and nearest neighbors rule: Application to a turbogenerator[J]. IEEE Transactions on Industrial Electronics, 2012, 60(9):4063–4073.
[2] Zhang Z, Wang Y, Wang K. Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network[J]. Journal of Intelligent Manufacturing, 2013, 24(6):1213–1227.
[3] Jiang H, Wang F, Shao H, et al. Rolling bearing fault identification using multilayer deep learning convolutional neural network[J]. Journal of Vibroengineering, 2017, 19(1):138–149.
[4] 王琦, 邓林峰, 赵荣珍. 基于改进一维卷积神经网络的滚动轴承故障识别[J]. 振动与冲击, 2022, 41(03):216–223.
WANG, Qi, DENF Linfeng, ZHAO Rongzhen. Fault recognition of rolling bearing based on improved 1D convolutional neural network [J]. Journal of Vibration and Shock, 2022, 41(03):216–223.
[5] Chen Z, Li W. Multisensor feature fusion for bearing fault diagnosis using sparse autoencoder and deep belief network[J]. IEEE Transactions on Instrumentation and Measurement, 2017, 66(7):1693–1702.
[6] Xia M, Li T, Xu L, et al. Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks[J]. IEEE/ASME transactions on mechatronics, 2017, 23(1):101–110.
[7] Xing Z, Liu Y, Wang Q, et al. Multi-sensor signals with parallel attention convolutional neural network for bearing fault diagnosis[J]. AIP Advances, 2022, 12(7):75020.
[8] Shao H, Jiang H, Zhang X, et al. Rolling bearing fault diagnosis using an optimization deep belief network[J]. Measurement Science and Technology, 2015, 26(11):115002.
[9] Chen X, Zhang B, Gao D. Bearing fault diagnosis base on multi-scale CNN and LSTM model[J]. Journal of Intelligent Manufacturing, 2021, 32(4):971–987.
[10] Pan S J, Tsang I W, Kwok J T, et al. Domain adaptation via transfer component analysis[J]. IEEE Transactions on Neural Networks, 2011, 22(2):199–210.
[11] Han T, Liu C, Wu R, et al. Deep transfer learning with limited data for machinery fault diagnosis[J]. Applied Soft Computing, 2021, 103:107150.
[12] 陈祝云, 钟琪, 黄如意等. 基于增强迁移卷积神经网络的机械智能故障诊断[J]. 机械工程学报, 2021, 57(21):96–105.
CHEN Zhuyun, ZHONG Qi, HUANG Ruyi, et.al. Intelligent Fault Diagnosis for Machinery Based on Enhanced Transfer Convolutional Neural Network[J].Journal of Mechanical Engineering,2021, 57(21):96–105.
[13] 雷亚国, 杨彬, 杜兆钧等. 大数据下机械装备故障的深度迁移诊断方法[J]. 机械工程学报, 2019, 55(07):1–8.
LEIYaguo, YANG Bin, DU Zhaojun. Deep Transfer Diagnosis Method for Machinery in Big Data Era[J]. Journal of Mechanical Engineering, 2019, 55(07):1–8.
[14] 张西宁, 余迪, 刘书语. 基于迁移学习的小样本轴承故障诊断方法研究[J]. 西安交通大学学报, 2021, 55(10):30–37.
ZHANG Xining, YU Di, LIU Shuyu. Fault diagnosis method for small sample bearing based on transfer learning[J]. Journal of xi'an jiaotong university, 2021, 55(10):30–37.
[15] Qiao M, Yan S, Tang X, et al. Deep Convolutional and LSTM Recurrent Neural Networks for Rolling Bearing Fault Diagnosis Under Strong Noises and Variable Loads[J]. IEEE Access, 2020, 8:66257–66269.
[16] An Z, Li S, Wang J, et al. Generalization of deep neural network for bearing fault diagnosis under different working conditions using multiple kernel method[J]. Neurocomputing, 2019, 352:42–53.