Abstract
Sliding bearings have become essential components in rotating machinery and are widely used in robotics field. Wear is the major failure mode of sliding bearings, while traditional prognostics methods for wear mostly rely on iterative calculations based on physical models, which are time-consuming, inefficient, and have limited practicality. This paper proposes a novel prognostics method for wear based on the Sequential Hybrid of Finite Element and Neural Network (SFENN), which exhibits high accuracy in wear prognostics and instantaneous output capability. The proposed method integrates finite element physical model and deep neural network through a sequential hybrid approach. In the offline phase, we establish the wear physical model of sliding bearing based on wear theory and wear test, then simulated wear data can be obtained through numerical simulations under different conditions. Deep neural network is designed and trained according to the characteristics of simulated data. After SFENN is trained, it can provide instantaneous prognostics of wear profile for new conditions of bearing, overcoming the limitations of traditional methods. The experiment validated the effectiveness of the proposed method, providing a further solution for the digital twin degradation model of mechanical components.
This work was supported by the National Key Research and Development Project of China [grant number 2020YFB1709103, 2018YFB1700604]; the Beijing Municipal Natural Science Foundation [grant number 3182012].
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Luo, R.z., et al.: Rotating machinery fault diagnosis theory and implementation. Instrum. Tech. Sensor (3), 107–10 (2014)
Yin, Y., et al.: Research progress in sliding bearing materials. Lubr. Eng. 05, 183–187 (2006)
Wang, N.: Numerical calculation to the pressure distribution of journal bearing based on the Matlab. Thesis, Dalian University of Technology (2006)
Yang, Y., Zu, D., Huang, S.: Status and development of self-lubricating spherical plain bearings. Bearing (01), 58–61+65 (2009). https://doi.org/10.19533/j.issn1000-3762.2009.01.019
Zhao, D., Liu, Z., Ren, Z.: Analysis and experimental study of oil flow characteristics in sliding bearings. Lubr. Eng. 37(3), 81–84 (2012)
Fu, J., Li, K., Li, H., Peng, K., Liu, X.: Optimization design of fuel pump sliding bearing based on the analysis of lubrication characteristics. Tribology 38(5), 512–520 (2018)
Xue, Q.: Progress in Chinese tribology research and application. Sci. Technol. Rev. 26(23), 3 (2008)
Archard, J.F.: Contact and rubbing of flat surfaces. J. Appl. Phys. 24(8), 981–988 (1953). https://doi.org/10.1063/1.1721448
Li, C., Zeng, P., Lei, L., Song, J.: Research on sliding wear behavior of co-based alloy and its simulation prediction. J. Mech. Eng. 47(21), 97–103 (2011). https://doi.org/10.3901/JME.2011.21.097
Lu, J., Qiu, M., Li, Y.: Wear life models for self-lubricating radial spherical plain bearings. J. Mech. Eng. 51(11), 56–63 (2015). https://doi.org/10.3901/JME.2015.11.056
Jin, X.: Experiment study on wear of journal bearing of roted system with torque excitation. Thesis, Taiyuan University of Technology (2017)
Li, J., Yin, J.: On the wear simulation of self-lubrication bearings. Lubr. Eng. 43(11), 120–124 (2018)
Stankovic, M., Marinkovic, A., Grbovic, A., Miskovic, Z., Rosic, B., Mitrovic, R.: Determination of Archard’s wear coefficient and wear simulation of sliding bearings. Ind. Lubr. Tribol. 71(1), 119–125 (2019). https://doi.org/10.1108/ILT-08-2018-0302
König, F., Ouald Chaib, A., Jacobs, G., Sous, C.: A multiscale-approach for wear prediction in journal bearing systems - from wearing-in towards steady-state wear. Wear 426–427, 1203–1211 (2019). https://doi.org/10.1016/j.wear.2019.01.036. https://www.sciencedirect.com/science/article/pii/S0043164819300584
Pang, X., Xue, X., Jin, X.: Experimental study on wear life of journal bearings in the rotor system subjected to torque. Trans. Can. Soc. Mech. Eng. 44(2), 272–278 (2019)
Du, F.M., et al.: Overview of friction and wear performance of sliding bearings. Coatings 12(9) (2022). https://doi.org/10.3390/coatings12091303
Cybenko, G.: Approximation by superpositions of a sigmoidal function. Math. Control Signals Syst. 2(4), 303–314 (1989)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
Table 5.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Dai, J., Tian, L. (2023). A Novel Prognostic Method for Wear of Sliding Bearing Based on SFENN. In: Yang, H., et al. Intelligent Robotics and Applications. ICIRA 2023. Lecture Notes in Computer Science(), vol 14275. Springer, Singapore. https://doi.org/10.1007/978-981-99-6504-5_19
Download citation
DOI: https://doi.org/10.1007/978-981-99-6504-5_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6503-8
Online ISBN: 978-981-99-6504-5
eBook Packages: Computer ScienceComputer Science (R0)