Abstract
Background
Rolling bearings are an essential equipment component, and evaluating its remaining useful life (RUL) is vital in guaranteeing safety and maintenance decision-making. While prior researchers utilize the D-CNN architecture to resolve the inadequacies of roller bearing remaining useful life prediction strategies, the extraction approach of operational deterioration attributes has a significant influence on the accuracy of the data-driven RUL prediction system.
Purpose
Unfortunately, the present network has many constraints when merging data into the model.
Method
The current research proposed a novel prediction method that combines a Deep Convolutional Neural Network (DCNN) and a gated recurrent unit (GRU), in which feature extraction utilizes a DCNN to extract vibration signal characteristics, where the fully connected layer substituted with the max-pooling layer to increase extraction accuracy. Simultaneously, the Gated recurrent unit (BiGRU) has been utilized to anticipate the remaining useful longevity of a rolling bearing. Moreover, this research builds up a bidirectional recurrent layer that can concentrate on past data while embedding future information to enhance the GRU model's potential to assimilate data.
Results
The experimental results show that the proposed technique reduces the time by incorporating DCNN with Bidirectional GRU compared with the baseline Simple Recurrent Unit (SRU) Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) takes more time than our proposed technique to complete. The error indexes of models, including Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), are compared with existing models. The results show that the proposed hybrid model gives less error value to improve the prediction results.
Conclusion
The simulation results show that the DCNN-BiGRU methodology has been established to lower manual intervention and time expenses while also providing an intelligent method of estimating the remaining useable life of roller bearings, founded on the idea of ensuring prediction accuracy.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig12_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig13_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig14_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig15_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs42417-022-00620-x/MediaObjects/42417_2022_620_Fig16_HTML.png)
Similar content being viewed by others
References
Liu H, Mo Z, Zhang H, Zeng X, Wang J, Miao Q (2018) Investigation on rolling bearing remaining useful life prediction: a review. In: 2018 Prognostics and System Health Management Conference (PHM-Chongqing) (pp. 979–984). IEEE. https://doi.org/10.1109/PHM-Chongqing.2018.00175
Delpha C, Diallo D, Youssef A (2017) Kullback-Leibler divergence for fault estimation and isolation: application to gamma distributed data. Mech Syst Signal Process 93:118–135
Glowacz A (2019) Acoustic fault analysis of three commutator motors. Mech Syst Signal Process 133:106226
Glowacz A, Glowacz W, Kozik J, Piech K, Gutten M, Caesarendra W, Khan ZF (2019) Detection of deterioration of three-phase induction motor using vibration signals. Measur Sci Rev 19(6):241–249
Qin Y, Li C, Cao F, Chen H (2020) A fault dynamic model of high-speed angular contact ball bearings. Mech Mach Theory 143:103627
Shi HT, Bai XT (2020) Model-based uneven loading condition monitoring of full ceramic ball bearings in starved lubrication. Mech Syst Signal Process 139:106583
Kumar A, Kumar R (2019) Role of signal processing, modeling and decision making in the diagnosis of rolling element bearing defect: a review. J Nondestr Eval 38(1):1–29
Wang D, Tsui K, Miao Q (2018) Prognostics and health management: a review of vibration based bearing and gear health indicators. IEEE Access 6:665–676
Heng A, Zhang S, Tan AC, Mathew J (2009) Rotating machinery prognostics: state of the art, challenges and opportunities. Mech Syst Signal Process 23:724–739
Cubillo A, Perinpanayagam S, Esperon-Miguez M (2016) A review of physics-based models in prognostics: application to gears and bearings of rotating machinery. Adv Mech Eng 8(8):1687814016664660
Qian Y, Yan R, Gao RX (2017) A multi-time scale approach to remaining useful life prediction in rolling bearing. Mech Syst Signal Process 83:549–567
Lei Y, Li N, Gontarz S, Lin J, Radkowski S, Dybala J (2016) A model-based method for remaining useful life prediction of machinery. IEEE Trans Reliab 65(3):1314–1326
Meng Z, Li J, Yin N, Pan Z (2020) Remaining useful life prediction of rolling bearing using fractal theory. Measurement 156:107572
Qian Y, Yan R, Hu S (2014) Bearing degradation evaluation using recurrence quantification analysis and Kalman filter. IEEE Trans Instrum Meas 63(11):2599–2610
Xiao L, Chen X, Zhang X, Liu M (2017) A novel approach for bearing remaining useful life estimation under neither failure nor suspension histories condition. J Intell Manuf 28(8):1893–1914
Dong S, Luo T (2013) Bearing degradation process prediction based on the PCA and optimized LS-SVM model. Measurement 46(9):3143–3152
Ahmad W, Khan SA, Kim JM (2017) A hybrid prognostics technique for rolling element bearings using adaptive predictive models. IEEE Trans Industr Electron 65(2):1577–1584
Hanachi H, Liu J, Banerjee A, Chen Y, Koul A (2014) A physics-based modeling approach for performance monitoring in gas turbine engines. IEEE Trans Reliab 64(1):197–205
Yu J (2013) A nonlinear probabilistic method and contribution analysis for machine condition monitoring. Mech Syst Signal Process 37(1–2):293–314
Dui H, Si S, Zuo MJ, Sun S (2015) Semi-Markov process-based integrated importance measure for multi-state systems. IEEE Trans Reliab 64(2):754–765
Si XS, Wang W, Hu CH, Zhou DH, Pecht MG (2012) Remaining useful life estimation based on a nonlinear diffusion degradation process. IEEE Trans Reliab 61(1):50–67
Farsi MA, Masood Hosseini S (2019) Statistical distributions comparison for remaining useful life prediction of components via ANN. Int J Syst Assur Eng Manag 10(3):429–436
Ordóñez C, Lasheras FS, Roca-Pardiñas J, de Cos Juez FJ (2019) A hybrid ARIMA–SVM model for the study of the remaining useful life of aircraft engines. J Comput Appl Math 346:184–191
Chen Z, Li Y, Xia T, Pan E (2019) Hidden Markov model with auto-correlated observations for remaining useful life prediction and optimal maintenance policy. Reliab Eng Syst Saf 184:123–136
Pan Y, Hong R, Chen J, Wu W (2020) A hybrid DBN-SOM-PF-based prognostic approach of remaining useful life for wind turbine gearbox. Renew Energy 152:138–154
Hinchi AZ, Tkiouat M (2018) Rolling element bearing remaining useful life estimation based on a convolutional long-short-term memory network. Proc Comput Sci 127:123–132
Jiang J-R, Lee J-E, Zeng Y-M (2020) Time series multiple channel convolutional neural network with attention-based long short-term memory for predicting bearing remaining useful life. Sensors 20(1):166
Qin Y, Chen D, Xiang S, Zhu C (2020) Gated dual attention unit neural networks for remaining useful life prediction of rolling bearings. IEEE Trans Industr Inf 17(9):6438–6447
Mao W, He J, Zuo MJ (2019) Predicting remaining useful life of rolling bearings based on deep feature representation and transfer learning. IEEE Trans Instrum Meas 69(4):1594–1608
Huang G, Zhang Y, Jiayu Ou (2021) Transfer remaining useful life estimation of bearing using depth-wise separable convolution recurrent network. Measurement 176:109090
Ding Y, MinpingJia QM, Huang P (2021) Remaining useful life estimation using deep metric transfer learning for kernel regression. Reliab Eng Syst Saf 212:107583
Yan M, Wang X, Wang B, Chang M, Muhammad I (2020) Bearing remaining useful life prediction using support vector machine and hybrid degradation tracking model. ISA Trans 98:471–482
Wang R, Shi R, Xiong H, Shen C (2021) Remaining Useful life prediction of rolling bearings based on multiscale convolutional neural network with integrated dilated convolution blocks. Shock Vib. https://doi.org/10.1155/2021/6616861
Yao D, Li B, Liu H, Yang J, Jia L (2021) Remaining useful life prediction of roller bearings based on improved 1D-CNN and simple recurrent unit. Measurement 175:109166
Nectoux P, Gouriveau R, Medjaher K, Ramasso E, Chebel-Morello B, Zerhouni N, Varnier C (2012) PRONOSTIA: an experimental platform for bearings accelerated degradation tests. In: IEEE International Conference on prognostics and health management, PHM'12., Jun 2012, Denver, Colorado, United States. pp. 1-8. (hal-00719503). https://hal.archives-ouvertes.fr/hal-00719503
Jin W, Chen Y, Lee J (2013) Methodology for ball screw component health assessment and failure analysis. In: International Manufacturing Science and Engineering Conference, 55461: V002T02A031. American Society of Mechanical Engineers. https://doi.org/10.1115/MSEC2013-1252
Ahmad W, Khan SA, Kim JM (2017) A hybrid prognostics technique for rolling element bearings using adaptive predictive models. IEEE Trans Ind Electron 65(2):1577–1584
Lee J, Qiu, H, Yu G, Lin J, Rexnord Technical Services (2007) IMS, University of Cincinnati. Bearing Data Set. NASA Ames Prognostics Data Repository, NASA Ames Research Center, Moffett Field, CA. http://ti.arc.nasa.gov/project/prognostic-data-repository
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Eknath, K.G., Diwakar, G. Prediction of Remaining useful life of Rolling Bearing using Hybrid DCNN-BiGRU Model. J. Vib. Eng. Technol. 11, 997–1010 (2023). https://doi.org/10.1007/s42417-022-00620-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42417-022-00620-x