A rolling bearing state evaluation method based on deep learning combined with Wiener process
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
As a key component of rotating parts, rolling bearings largely determine the operation safety of equipment. However, in practical applications, because the degradation trajectory of rolling bearings cannot be truly characterized, the existing model cannot accurately describe the degradation trajectory of rolling bearings, resulting in the running state of rolling bearings cannot be directly evaluated. Therefore, a method of rolling bearing state assessment based on deep learning combined with Wiener process is proposed in this paper. Firstly, a deep network model is constructed by deep learning to mine the degradation information of rolling bearings. Secondly, the mined degradation information is fused, and then the degradation indicator used to characterize the degraded trajectory of the rolling bearing is constructed. Then, based on Wiener process, the degradation model of rolling bearing is established to describe the degradation mode of rolling bearing. Finally, the constructed degradation indicator is input into the established degradation model to predict its RUL, and then the running state of the rolling bearing is evaluated.
How to Cite
##plugins.themes.bootstrap3.article.details##
Rolling bearing, Deep learning, Wiener process, State evaluation
7
Figure10. Bearing1_3 service status 4. CONCLUSION In order to evaluate the service status of rolling bearings, this paper proposes a rolling bearing status evaluation method based on deep learning combined with Wiener process. Since the existing DIs cannot characterize the degradation trajectory of rolling bearings. This paper uses a 1DCNN to extract the DIs of rolling bearings. Aiming at the problem of the RUL of rolling bearings, this paper constructs a degradation model of rolling bearings based on the Wiener process, and uses its PDF to estimate the RUL of rolling bearings. The RUL of the rolling bearing is mapped to its service status, thereby completing the service status assessment of the rolling bearing. This paper uses the IEEE PHM 2012 public data set to verify the method. The experimental results show that the extracted DI has good trend and monotonicity, and the service status assessment of the rolling bearing has good accuracy. However, the contribution of this paper is limited. From the verification results, the bearing prediction accuracy is largely determined by the constructed DI and the complexity of the model. Therefore, the follow-up work of this paper will start from mining the degradation information of bearings and establishing more complex prediction models to improve the prediction accuracy of bearings. memory network for rolling bearings', Advanced Engineering Informatics, 48. Hu, C. H., H. Pei, X. S. Si, D. B. Du, Z. N. Pang, and X. Wang. 2020. 'A Prognostic Model Based on DBN and Diffusion Process for Degrading Bearing', Ieee Transactions on Industrial Electronics, 67: 876777. Kogan, G., R. Klein, A. Kushnirsky, and J. Bortman. 2015. 'Toward a 3D dynamic model of a faulty duplex ball bearing', Mechanical Systems and Signal Processing, 54-55: 243-58.
Li, T. M., X. S. Si, H. Pei, and L. Sun. 2022. 'Data-model interactive prognosis for multi-sensor monitored stochastic degrading devices', Mechanical Systems and Signal Processing, 167. Li, Y. J., Z. J. Wang, F. Li, Y. F. Li, X. H. Zhang, H. Shi, L. Dong, and W. B. Ren. 2024. 'An ensembled remaining useful life prediction method with data fusion and stage division', Reliability Engineering & System Safety, 242. Qian, Y. N., R. Q. Yan, and R. X. Gao. 2017. 'A multi-time scale approach to remaining useful life prediction in rolling bearing', Mechanical Systems and Signal Processing, 83: 549-67. Qin, Y., J. H. Yang, J. H. Zhou, H. Y. Pu, and Y. F. Mao. 2023. 'A new supervised multi-head self-attention autoencoder for health indicator construction and similarity-based machinery RUL prediction', Advanced Engineering Informatics, 56. Ren, L., Y. Q. Sun, J. Cui, and L. Zhang. 2018. 'Bearing remaining useful life prediction based on deep autoencoder and deep neural networks', Journal of Manufacturing Systems, 48: 71-77. Rezamand, M., M. Kordestani, M. E. Orchard, R. Carriveau, D. S. K. Ting, and M. Saif. 2021. 'Improved Remaining Useful Life Estimation of Wind Turbine Drivetrain Bearings Under Varying Operating Conditions', Ieee Transactions on Industrial Informatics, 17: 1742-52. She, D. M., and M. P. Jia. 2019. 'Wear indicator construction of rolling bearings based on multichannel deep convolutional neural network with exponentially decaying learning rate', Measurement, 135: 368-75. Si, X. S., W. B. Wang, C. H. Hu, D. H. Zhou, and M. G. Pecht. 2012. 'Remaining Useful Life Estimation Based on a Nonlinear Diffusion Degradation Process', Ieee Transactions on Reliability, 61: 50-67.
8
Ta, Y. T., Y. F. Li, W. A. Cai, Q. Q. Zhang, Z. J. Wang, L. Dong, and W. H. Du. 2023. 'Adaptive staged remaining useful life prediction method based on multisensor and multi-feature fusion', Reliability Engineering & System Safety, 231. Wang, B., Y. G. Lei, N. P. Li, and N. B. Li. 2020. 'A Hybrid Prognostics Approach for Estimating Remaining Useful Life of Rolling Element Bearings', Ieee Transactions on Reliability, 69: 401-12. Wang, X., L. L. Cui, and H. Q. Wang. 2022. 'Remaining Useful Life Prediction of Rolling Element Bearings Based on Hybrid Drive of Data and Model', Ieee Sensors Journal, 22: 16985-93. Wang, Z. J., Y. T. Ta, W. N. Cai, and Y. F. Li. 2023. 'Research on a remaining useful life prediction method for degradation angle identification two-stage degradation process', Mechanical Systems and Signal Processing, 184. Xiahou, T. F., Z. G. Zeng, and Y. Liu. 2021. 'Remaining Useful Life Prediction by Fusing Expert Knowledge and Condition Monitoring Information', Ieee Transactions on Industrial Informatics, 17: 2653-63. Yoo, Y., and J. G. Baek. 2018. 'A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network', Applied Sciences-Basel, 8. Zhu, D., J. W. Lyu, Q. W. Gao, Y. X. Lu, and D. W. Zhao. 2024. 'Remaining useful life estimation of bearing using spatio-temporal convolutional transformer', Measurement Science and Technology, 35.
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.