基于跨域均值逼近的轴承剩余使用寿命预测

doi:10.16088/j.issn.1001-6600.2021071401

摘要/Abstract

摘要： 由于轴承退化数据较少及不同工况之间轴承数据分布差异较大,实现在一个轴承上训练的剩余寿命预测模型,能够预测其他同一工况或不同工况不同轴承的剩余使用寿命,是一个待解决的难题。本文提出基于跨域均值逼近的联合分布自适应轴承剩余使用寿命预测方法,首先,对轴承原始振动信号数据进行归一化处理;其次,通过投影矩阵将源域和目标域数据映射到一个低维公共特征子空间中,利用基于跨域均值逼近的联合分布自适应方法对源数据和目标轴承数据进行领域适配;最后,利用门控循环单元对轴承剩余使用寿命进行预测。在IEEE PHM Challenge 2012数据集上进行多组迁移实验,结果表明,所提方法在同一工况或不同工况下不同轴承间有良好的预测精度。

关键词: 领域自适应, 跨域均值逼近, 门控循环单元, 滚动轴承, 剩余使用寿命预测

Abstract: In recent years, deep learning provides a new method for predicting the remaining useful life of bearings. In practice, due to the small number of bearing degradation data and the large difference in the distribution of bearing data under different working conditions, it is hard to realize that the remaining useful life prediction model trained on one bearing, which can be used for other bearings remaining useful life prediction under the same or different working conditions. In order to deal with the aforementioned shortcomings, a joint distribution adaptation based on cross domain mean approximation for bearing remaining useful life prediction method is proposed. Firstly, the original vibration signal data of the bearing is normalized. Then the source domain and target domain data are projected to a corresponding lowdimensional common feature subspace by projection matrix. In the subspace, a joint distribution adaptation based on cross domain mean approximation method is used to perform domain adaptation for source and target data. Finally, the gated recurrent unit is used for the bearing remaining useful life prediction. The validity of the proposed method is demonstrated by experiments on IEEE PHM Challenge 2012 dataset. The results show that the proposed method has good prediction accuracy under the same working condition or different working conditions for different bearings.

Key words: domain adaptation, cross domain mean approximation, gated recurrent unit, rolling bearing, remaining useful life prediction

中图分类号:

TP181

蒋瑞, 徐娟, 李强. 基于跨域均值逼近的轴承剩余使用寿命预测[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 121-131.

JIANG Rui, XU Juan, LI Qiang. A Prediction Method of Bearing Remaining Useful Life Based on Cross Domain Mean Approximation[J]. Journal of Guangxi Normal University(Natural Science Edition), 2022, 40(3): 121-131.

参考文献

[1]SI X S, WANG W B, HU C H, et al. Remaining useful life estimation:a review on the statistical data driven approaches[J]. European Journal of Operational Research, 2011, 213(1):1-14. DOI: 10.1016/j.ejor.2010.11.018.
[2]张小丽, 王保建, 马猛,等. 滚动轴承寿命预测综述[J]. 机械设计与制造, 2015(10):221-224.
[3]康守强, 邢颖怡, 王玉静,等. 基于无监督深度模型迁移的滚动轴承寿命预测方法[J/OL]. 自动化学报, [2021-07-14]. https://doi.org/10.16383/j.aas.c200890.
[4]周玉辉, 康锐. 基于退化失效模型的旋转机械寿命预测方法[J]. 核科学与工程, 2009,29(2):146-151.
[5]侯南, 刘珑, 江婷,等. 基于实时监测的轴承寿命预测方法[J]. 山东科学, 2021, 34(3):42-48.
[6]杨彦宇. 以振动信号为基础的数字信号处理方法对滚动轴承寿命预测的研究[D].北京: 北京化工大学, 2016.
[7]欧龙辉, 彭晓燕, 杨宇,等. GS-ASTFA方法及其在滚动轴承寿命预测中的应用[J]. 振动与冲击, 2017, 36(11): 14-19.
[8]李华新, 王衍学. 基于分层稀疏编码的轴承剩余寿命预测方法[J]. 现代制造工程, 2019(5):7-12.
[9]张成龙, 刘杰, 李想. 基于改进PSO-SVR的多轴承健康寿命协同预测[J]. 机床与液压, 2020,48(16):206-211.
[10]曾大懿, 蒋雨良, 邹益胜, 等. 一种新的轴承寿命预测特征评价指标构建与验证[J]. 振动与冲击, 2021, 40(22):18-27.
[11]CHEN Y H, PENG G L, ZHU Z Y, et al. A novel deep learning method based on attention mechanism for bearing remaining useful life prediction[J]. Applied Soft Computing, 2020, 86:105919. DOI: 10.1016/j.asoc.2019.105919.
[12]ZANG S F, CHENG Y H, WANG X S, et al. Cross domain mean approximation for unsupervised domain adaptation[J]. IEEE Access, 2020,8:139052-139069. DOI: 10.1109/ACCESS.2020.3012152.
[13]ZHAO L, WANG X. A deep feature optimization fusion method for extracting bearing degradation features[J]. IEEE Access, 2018,6:19640-19653. DOI: 10.1109/ACCESS.2018.2824352.
[14]SATEESH BABU G, ZHAO P L, LI X L. Deep convolutional neural network based regression approach for estimation of remaining useful life[C]// Database Systems for Advanced Applications. Cham: Springer, 2016:214-228.
[15]RAO M, LI Q, WEI D D, et al. A deep bi-directional long short-term memory model for automatic rotating speed extraction from raw vibration signals[J]. Measurement, 2020, 158:107719. DOI: 10.1016/j.measurement.2020.107719.
[16]PEI H, SI X S, HU C H, et al. An adaptive prognostics method for fusing CDBN and diffusion process: application to bearing data[J]. Neurocomputing, 2021, 421:303-315. DOI: 10.1016/j.neucom.2020.09.021.
[17]HARIS M, HASAN M N, QIN S Y. Early and robust remaining useful life prediction of supercapacitors using BOHB optimized deep belief network[J]. Applied Energy, 2021,286:116541. DOI: 10.1016/j.apenergy.2021.116541.
[18]GUO L, LEI Y G, LI N P, et al. Machinery health indicator construction based on convolutional neural networks considering trend burr[J]. Neurocomputing, 2018, 292:142-150. DOI: 10.1016/j.neucom.2018.02.083.
[19]REN L, CUI J, SUN Y Q, et al. Multi-bearing remaining useful life collaborative prediction: a deep learning approach[J]. Journal of Manufacturing Systems, 2017,43(2):248-256. DOI: 10.1016/j.jmsy.2017.02.013.
[20]WU Y T, MEI Y, DONG S P, et al. Remaining useful life estimation of engineered systems using vanilla LSTM neural networks[J]. Neurocomputing, 2018,275:167-179. DOI: 10.1016/j.neucom.2017.05.063.
[21]ZHAO R, WANG D Z, YAN R Q, et al. Machine health monitoring using local feature-based gated recurrent unit networks[J]. IEEE Transactions on Industrial Electronics, 2018, 65(2):1539-1548. DOI: 10.1109/TIE.2017.2733438.
[22]HUANG J Y, SMOLA A J, GRETTON A, et al. Correcting sample selection bias by unlabeled data[C]// Proceedings of the 19th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2006:601-608.
[23]SUN B C, SAENKO K. Subspace distribution alignment for unsupervised domain adaptation[C]// Proceedings of the British Machine Vision Conference. Swansea: BMVA Press, 2015: 24.1-24.10. DOI: 10.52244/c.29.24.
[24]WANG C, MAHADEVAN S. Manifold alignment preserving global geometry[C]// Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2013:1743-1749.
[25]XIA R, HU X L, LU J F, et al. Instance selection and instance weighting for cross-domain sentiment classification via PU learning[C]// Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2013:2176-2182.
[26]LONG M S, WANG J M, DING G G, et al. Transfer joint matching for unsupervised domain adaptation[C]// 2014 IEEE Conference on Computer Vision & Pattern Recognition. Piscataway: IEEE, 2014:1410-1417.
[27]欧琦媛, 祝恩. 基于压缩子空间对齐的多核聚类算法[J]. 计算机工程与科学, 2021, 43(10):1730-1735.
[28]张祖于. 基于特征分布差异自适应的无监督迁移学习方法研究[D].重庆:重庆邮电大学, 2019.
[29]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. DOI: 10.1109/tnn.2010.2091281.
[30]LONG M S, WANG J M, DING G G, et al. Transfer feature learning with joint distribution adaptation[C]// Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013:2200-2207.
[31]LI J J, JING M M, LU K, et al. Locality preserving joint transfer for domain adaptation[J]. IEEE Transactions on Image Processing, 2019, 28(12):6103-6115. DOI: 10.1109/TIP.2019.2924174.
[32]LI J J, LU K, HUANG Z, et al. Heterogeneous domain adaptation through progressive alignment[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(5):1381-1391. DOI: 10.1109/TNNLS.2018.2868854.
[33]YAN H l, DING Y K, LI P H, et al. Mind the class weight bias: weighted maximum mean discrepancy for unsupervised domain adaptation[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017:945-954. DOI: 10.1109/CVPR.2017.107.
[34]ZANG S F, CHENG Y H, WANG X S, et al. Semi-supervised transfer discriminant analysis based on cross-domain mean constraint[J]. Artificial Intelligence Review, 2018,49(4):581-595. DOI: 10.1007/s10462-016-9533-3.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed