Health prediction of rolling bearing based on digital twin
-
摘要: 滚动轴承的健康状态在很大程度上决定了机械设备的可靠性水平。对滚动轴承进行健康状态预测有助于机械设备的安全性运行。因此,提出了一种基于数字孪生的滚动轴承剩余寿命实时预测方法。首先,该方法基于数字孪生的数字化技术手段获取滚动轴承的实时感知信息,从而建立考虑实时工况变化的滚动轴承数字孪生模型。其次,通过非线性布朗运动建立考虑测量误差的剩余寿命预测模型。然后,采用极大似然估计方法求解模型中的未知参数,并利用贝叶斯理论实时更新参数,从而对滚动轴承的剩余寿命进行实时预测。最后,通过滚动轴承的全寿命周期信息分析验证了该方法的可行性和有效性。Abstract: The health status of rolling bearings largely determines the reliability level of mechanical equipment. The health state prediction of rolling bearings can help the safe operation of mechanical equipment. Therefore, this paper proposes a real-time prediction method of the remaining life of rolling bearings based on digital twin. Firstly, the method is based on digital twin technology means to obtain real-time sensing information of rolling bearings, so as to establish a digital twin model of rolling bearings considering real-time working condition changes. Secondly, a remaining life prediction model considering the measurement error is established by non-linear Brownian motion. Then, the unknown parameters in the model are solved by using the great likelihood estimation method, and the parameters are updated in real time by using Bayesian theory, so that the remaining life of the rolling bearing can be predicted in real time. Finally, the feasibility and effectiveness of the method are verified by analyzing the information of the whole life cycle of rolling bearings.
-
Key words:
- digital twin /
- remaining life prediction /
- rolling bearing /
- brownian motion
-
表 1 3种评价指标值
RMSE R2 η M0 50.4943 0.7483 0.0181(0-2) M1 36.5041 0.8721 0.0169(1-2) M2 34.5041 0.8825 — -
[1] 汪立雄, 王志刚, 徐增丙, 等. 基于深度迁移学习的滚动轴承剩余使用寿命预测[J]. 制造技术与机床, 2020(12): 130-134. doi: 10.19287/j.cnki.1005-2402.2020.12.025 [2] Li N, Lei Y, Lin J, et al. An improved exponential model for predicting remaining useful life of rolling element bearings[J]. IEEE Transactions on Industrial Electronics, 2015, 62(12): 7762-7773. doi: 10.1109/TIE.2015.2455055 [3] Lei Y, Li N, Guo L, et al. Machinery health prognostics: A systematic review from data acquisition to RUL prediction[J]. Mechanical Systems and Signal Processing, 2018, 104(MAY1): 799-834. [4] 刘佳俊, 胡昌华, 周志杰, 等. 基于证据推理和置信规则库的装备寿命评估[J]. 控制理论与应用, 2015, 32(2): 231-238. doi: 10.7641/CTA.2015.40406 [5] 黄志平, 黄新宇, 李亮, 等. 基于数据驱动的铣削刀具寿命预测研究[J]. 制造技术与机床, 2020(1): 153-161. doi: 10.19287/j.cnki.1005-2402.2020.01.029 [6] Si X S, Wang W, Hu C H, et al. Remaining useful life estimation based on a nonlinear diffusion degradation process[J]. IEEE Transactions on Reliability, 2012, 61(1): 50-67. doi: 10.1109/TR.2011.2182221 [7] Yan M, Wang X, Wang B, et al. Bearing remaining useful life prediction using support vector machine and hybrid degradation tracking model[J]. ISA Transactions, 2019, 98: 471-482. [8] Li X, Cheng J, Shao H, et al. A fusion CWSMM-based framework for rotating machinery fault diagnosis under strong interference and imbalanced case[J]. IEEE Transactions on Industrial Informatics, 2021, 18(8): 5180-5189. [9] 董霁泽. 工作条件对滚动轴承寿命的影响[J]. 中国石油和化工标准与质量, 2017, 37(9): 84-85. doi: 10.3969/j.issn.1673-4076.2017.09.041 [10] Li Y X, Huang X Z, Ding P F, et al. Wiener-based remaining useful life prediction of rolling bearings using improved Kalman filtering and adaptive modification[J]. Measurement, 2021, 182: 109706. doi: 10.1016/j.measurement.2021.109706 [11] 陶飞, 刘蔚然, 刘检华, 等. 数字孪生及其应用探索[J]. 计算机集成制造系统, 2018, 24(1): 18. doi: 10.13196/j.cims.2018.01.001 [12] 陶飞, 刘检华, 王军强, 等. 前言[J]. 计算机集成制造系统, 2019, 25(6): 前插1-前插2. [13] Lei Y G, Li N P, Li J. A new method based on stochastic process models for machine remaining useful life prediction[J]. IEEE Transactions on Instrumentation and Measurement, 2016, 65(12): 2671-2684. doi: 10.1109/TIM.2016.2601004 [14] Si X S, Wang W, Hu C H, et al. Estimating remaining useful life with three-source variability in degradation modeling[J]. IEEE Transactions on Reliability, 2014, 63(1): 167-190. doi: 10.1109/TR.2014.2299151 [15] Guo J, Yang Z, Chen C, Luo W, Hu W. Real-time prediction of remaining useful life and preventive maintenance strategy based on digital Twin[J]. Journal of Computing and Information Science in Engineering, 2021, 21(3): 031003. doi: 10.1115/1.4049153 [16] 白灿, 胡昌华, 司小胜, 等. 随机冲击影响的非线性退化设备剩余寿命预测[J]. 系统工程与电子技术, 2018, 40(12): 114-120. doi: 10.3969/j.issn.1001-506X.2018.12.16 [17] Basu A P , Chhikara R S , Folks J L. The inverse Gaussian distribution[J]. Technometrics, 1990, 32(2): 235. [18] Liu D, Zhou J, Liao H, et al. A health indicator extraction and optimization framework for lithium-ion battery degradation modeling and prognostics[J]. IEEE Transactions on Systems Man & Cybernetics Systems, 2015, 45(6): 915-928.