Remaining useful life prediction of rolling bearings based on TET and DSRNet-AttBiLSTM

ZHOU Yuguo1, ZHANG Jinchao1, SUN Yiping1, YU Chunfeng2, ZHOU Lijian1

Journal of Vibration and Shock ›› 2024, Vol. 43 ›› Issue (19) : 163-173.

PDF(4340 KB)
PDF(4340 KB)
Journal of Vibration and Shock ›› 2024, Vol. 43 ›› Issue (19) : 163-173.

Remaining useful life prediction of rolling bearings based on TET and DSRNet-AttBiLSTM

  • ZHOU Yuguo1, ZHANG Jinchao1, SUN Yiping1, YU Chunfeng2, ZHOU Lijian1
Author information +
History +

Abstract

To accurately extract the degradation characteristics of bearings and perform effective Remaining Useful Life (RUL) prediction for rolling bearings in this paper, we propose a rolling bearing RUL prediction method based on Transient Extraction Transform and DSRNet-AttBiLSTM. Firstly, the original vibration signal is segmented and reorganized,and the time-frequency map is obtained by Transient Extracting Transform (TET). The time-frequency map is downscaled using bilinear interpolation further and channel spliced to obtain the time-frequency pictorial features of the bearing. Secondly, to accurately and efficiently extract the degradation features of rolling bearings, basic SConv and DConv modules containing depth-separable convolution and spatial-channel attention are constructed. DSRNet based on SConv and DConv is constructed to extract the bearing degradation features in both spatial and channel dimensions. Again, to make the Bidirectional Long and Short-Term Memory network pay more attention to the input features with more important information while training, an attention layer is constructed at the feature input layer. And it and BiLSTM form the AttBiLSTM prediction module to calculate the HI. Finally, linear regression fitting is used to predict the RUL of rolling bearings. The experimental results on the PHM2012 dataset and the XJTU-SY dataset show that the proposed method is effective for predicting the RUL of rolling bearings.

Key words

rolling bearing / remaining useful life / attention mechanism / feature extraction

Cite this article

Download Citations
ZHOU Yuguo1, ZHANG Jinchao1, SUN Yiping1, YU Chunfeng2, ZHOU Lijian1. Remaining useful life prediction of rolling bearings based on TET and DSRNet-AttBiLSTM[J]. Journal of Vibration and Shock, 2024, 43(19): 163-173

References

[1] Chen J X, Mao W T, Liu J, et al. Remaining useful life prediction of bearing based on deep temporal feature transfer[J]. Control and Decision, 2021, 36(7):1699-1706.
[2] Cheng C, Ma G, Zhang Y, et al. A deep learning-based remaining useful life prediction approach for bearings[J]. IEEE/ASME transactions on mechatronics, 2020, 25(3): 1243-1254.
[3] Cubillo A, Perinpanayagam S, Esperon-Miguez M. A review of physics-based models in prognostics: Application to gears and bearings of rotating machinery[J]. Advances in Mechanical Engineering, 2016, 8(8): 1687814016664660.
[4] Wang T, Liu Z, Mrad N. A probabilistic framework for remaining useful life prediction of bearings[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 70: 1-12.
[5] Liu L, Song X, Chen K, et al. An enhanced encoder–decoder framework for bearing remaining useful life prediction[J]. Measurement, 2021, 170: 108753.
[6] Lim P, Goh C K, Tan K C. A novel time series-histogram of features (TS-HoF) method for prognostic applications[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2018, 2(3): 204-213.
[7] Yang H, Sun Z, Jiang G, et al. Remaining useful life prediction for machinery by establishing scaled-corrected health indicators[J]. Measurement, 2019, 163: 108035.
[8] Zhao R, Yan R, Chen Z, et al. Deep learning and its applications to machine health monitoring[J]. Mechanical Systems and Signal Processing, 2019, 115: 213-237.
[9] Guo L, Lei Y, Li N, et al. Machinery health indicator construction based on convolutional neural networks considering trend burr[J]. Neurocomputing, 2018, 292: 142-150.
[10] 马占伟,袁逸萍,樊盼盼,等.基于多尺度卷积神经网络的轴承剩余寿命预测[J]. 机械设计与制造,2023(1):5-8.
MA Zhanwei, YUAN Yiping,FAN Panpan,et al. Prediction of Bearing Residual Useful Life Based on Multi-Scale Convolutional Neural Network[J]. Mechanical Design and Manufacturing, 2023(1): 5-8.
[11] 张继冬,邹益胜,邓佳林,等. 基于全卷积层神经网络的轴承剩余寿命预测[J].中国机械工程,2019,30(18):2231-2235.
ZHANG Jidong, ZOU Yisheng, DENG Jialin, et al. Bearing remaining life prediction based on full convolutional layer neural network[J]. China Mechanical Engineering, 2019, 30(18): 2231-2235.
[12] Zhu J, Chen N, Peng W. Estimation of bearing remaining useful life based on multiscale convolutional neural network[J]. IEEE Transactions on Industrial Electronics, 2018, 66(4): 3208-3216.
[13] Wang X, Wang T, Ming A, et al. Spatiotemporal non-negative projected convolutional network with bidirectional NMF and 3DCNN for remaining useful life estimation of Bearings[J]. Neurocomputing, 2021, 450: 294-310.
[14] Ren L,Sun Y, Wang H, et al. Prediction of bearing remaining useful life with deep convolution neural network[J]. IEEE access, 2018, 6: 13041-13049.
[15] Zhou Y, Yan S , Ren Y , et al. Rolling Bearing fault diagnosis using transient-extracting transform and linear discriminant analysis[J]. Measurement, 2021, 178:109298.
[16] 陈保家,陈正坤,陈学良,等.基于注意力TCN的滚动轴承剩余使用寿命预测方法[J].电子测量技术,2021,44(24):153-160.
CHEN Baojia, CHEN Zhengkun, CHEN Xueliang, et al. Prediction method of remaining useful life of rolling bearing based on attentional temporal convolutional network [J]. Electronic Measurement Technology,2021,44(24):153-160.
[17] 惠憬明,王健,吴双,等.基于自注意力CNN-BiLSTM的滚动轴承剩余使用寿命预测方法[J].轴承:1-8.
HUI Gingming,WANG Jian,WU Shuang,et al. Remaining useful life prediction method of rolling bearing based on self-attention-CNN-BiLSTM[J]. Bearing:1-8.
[18] 朱若岭,张昊.基于时空注意力机制的双向门控递归单元网络的轴承剩余使用寿命预测[J].轴承,2022(07):61-66.
ZHU Ruoling, ZHANG Hao. Remaining Useful Life Prediction of Bearings by Bidirectional Gating Recursive Unit Network Based on Temporal-Spatial Attention Mechanism [J].Bearing, 2022(07):61-66.
[19] Tan M, Le Q. Efficientnetv2: Smaller models and faster training[C]//International conference on machine learning. PMLR, 2021: 10096-10106.
[20] Wang B, Lei Y, Yan T, et al. Recurrent convolutional neural network: A new framework for remaining useful life prediction of machinery[J]. Neurocomputing, 2020, 379: 117-129.
[21] 蔡薇薇,徐彦伟,颉潭成,等. 基于CNN-LSTM的轴承剩余使用寿命预测[J]. 机械传动,2022,46(10):17-23.
CAI Weiwei, XU Yanwei, JIE Tancheng, et al. Prediction of bearing remaining service life based on CNN-LSTM[J]. Journal Mechanical Transmission, 2022, 46(10): 17-23.
[22] 赵潇雅,郜志英,周晓敏,等.基于FDA-LSTM的冷轧过程多源异构时序数据处理及颤振预测[J].振动与冲击,2022,41(22):202-210.
ZHAO Xiaoya, GAO Zhiying, ZHOU Xiaomin, et al. Multi-source heterogeneous time series data processing and chatter prediction based on the method of FDA-LSTM in cold rolling processes[J]. Journal of Vibration and Shock, 2022, 41(22):202-210.
[23] 姚德臣,李博阳,刘恒畅,等.基于注意力GRU算法的滚动轴承剩余寿命预测[J].振动与冲击,2021,40(17):116-123.
YAO Dechen, LI Boyang, LIU Hengchang, et al. Remaining life prediction of rolling bearings based on attention GRU algorithm[J]. Journal of Vibration and Shock, 2021, 40(17):116-123.
[24] Wu J, Hu K, Cheng Y, et al. Data-driven remaining useful life prediction via multiple sensor signals and deep long short-term memory neural network[J]. ISA transactions, 2021 97: 241-250.
[25] Nectoux P, Gouriveau R, Medjaher K, et al. PRONOSTIA: An experimental platform for bearings accelerated degradation tests[C]//IEEE International Conference on Prognostics and Health Management, PHM'12. IEEE Catalog Number: CPF12PHM-CDR, 2012: 1-8.
[26] 周哲韬,刘路,宋晓,等.基于Transformer模型的滚动轴承剩余使用寿命预测方法[J].北京航空航天大学学报,2023,49(2):430-443.
ZHOU Zhetao, LIU Lu, SONG Xiao, et al. Remaining useful life prediction method of rolling bearing based on Transformer model [J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(2): 430-443.
[27] Chen Y, Peng G, Zhu Z, et al. A novel deep learning method based on attention mechanism for bearing remaining useful life prediction[J]. Applied Soft Computing, 2020, 86: 105919.
[28] 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.
[29] Wang B, Lei Y, Yan T, et al. Recurrent convolutional neural network: A new framework for remaining useful life prediction of machinery[J]. Neurocomputing, 2020, 379: 117-129.
[30] Wei Y, Wu D. Remaining useful life prediction of bearings with attention-awared graph convolutional network[J]. Advanced Engineering Informatics, 2023, 58: 102143.
[31] Cheng H, Kong X, Wang Q, et al. Deep transfer learning based on dynamic domain adaptation for remaining useful life prediction under different working conditions[J]. Journal of Intelligent Manufacturing, 2023, 34(2): 587-613.
[32] Li X, Zhang W, Ding Q. Deep learning-based remaining useful life estimation of Bearings using multi-scale feature extraction[J]. Reliability engineering & system safety, 2019, 182: 208-218.
[33] Suh S, Jang J, Won S, et al. Supervised health stage prediction using convolutional neural networks for Bearing wear[J]. Sensors, 2020, 20(20): 5846.
[34] Suh S, Lukowicz P, Lee Y O. Generalized multiscale feature extraction for remaining useful life prediction of Bearings with generative adversarial networks[J]. Knowledge-Based Systems, 2022, 237: 107866.
PDF(4340 KB)

Accesses

Citation

Detail

Sections
Recommended

/