Remaining useful life prediction of silicon foam material based on double exponential particle filter model
-
摘要: 针对传统基于模型的硅泡沫材料长时使用寿命评估方法存在的物理模型解释性差、预测精度不高等问题，本文提出了一种双指数粒子滤波模型的剩余寿命预测方法。选取硅泡沫结构的载荷保持率作为特征量，基于硅泡沫材料的应力松弛失效机制，建立了更具解释性的双指数应力退化模型。首先利用最小二乘法对观测数据进行拟合，初始化模型参数和健康状态，然后通过贝叶斯理论对历史样本进行状态跟踪建模，更新状态传递函数，实现载荷保持率退化趋势预测和剩余寿命评估。通过仿真和实验验证了双指数粒子滤波模型预测硅泡沫材料剩余寿命的泛化适用性和准确性，同时与传统指数模型预测结果进行了对比，结果表明本文所提方法预测精度和稳定性更优。Abstract: The traditional physical model has poor interpretability and low prediction accuracy in evaluating remaining useful life of silicon foam materials. This paper presents a remaining useful life prediction method based on double exponential particle filter model. Based on the stress relaxation mechanism of silicon foam material, a more interpretability double exponential stress degradation model was established by selecting the load retention rate of silicon foam structure as the characteristic quantity. Firstly, the least square method was used to fit the observed data for initializing the model parameters and health state. Then, the Bayesian theory was used to track the state of historical samples, update the state transfer function, and realize the degradation trend prediction of load retention rate and remaining useful life assessment. The generalization applicability and accuracy of the double exponential particle filter model for predicting the residual life of silicon foam materials were verified by simulation and experiment. At the same time, the prediction results were compared with those of the traditional exponential model. The results show that the proposed method has better prediction accuracy and stability.
-
图 1 贝叶斯滤波过程
Figure 1. Bayesian filtering process
xk—Prior predicted value at time k; xk'—Posteriori updated value at time k; yk—Observations at time k
图 2 重采样过程示意
Figure 2. Representation of resampling process
wk—Update weight of the kth particle
图 4 硅泡沫材料剩余寿命预测流程
Figure 4. Remaining useful life prediction process of silicon foam materials
图 5 硅泡沫载荷保持率仿真样本退化趋势及剩余寿命预测
Figure 5. Degradation trend and remaining useful life prediction of load retention rate simulation samples of silicon foam materials
CI—Confidence interval
图 7 硅泡沫载荷保持率后验概率分布
Figure 7. Posterior probability distribution of load retention rate of silicon foam materials
图 8 硅泡沫载荷保持率退化趋势及剩余寿命预测
Figure 8. Degradation trend and remaining useful life prediction results of load retention rate of silicon foam materials
图 9 硅泡沫载荷保持率退化趋势不同预测算法对比
Figure 9. Comparison of prediction results of degradation trend prediction results of load retention rate of silicon foam materials by different algorithms
图 10 硅泡沫不同训练样本的寿命预测结果
Figure 10. Life prediction results of different training samples of silicon foam materials
表 1 仿真模型参数
Table 1. Simulation model parameters
Parameter a b c d t Initial value 0.4 −0.5 0.6 −0.004 1∶100 
下载: 导出CSV
-
[1] 夏乔琦, 李扬, 曹承飞, 等. 硅橡胶泡沫复合材料的制备、性能与应用[J]. 中国材料进展, 2018, 37(3):168-177.XIA Q Q, LI Y, CAO C F, et al. Preparation, properties and application of silicone rubber foam composites[J]. Materials China,2018,37(3):168-177(in Chinese). [2] LIU B, HUANG W, AO Y Y, et al. Dose rate effects of gamma irradiation on silicone foam[J]. Polymer Degradation and Stability,2018,147:97-102. [3] 刘占芳, 王江, 张华. 带预紧硅泡沫垫层减振结构的动力特性[J]. 中国机械工程, 2007, 18(14):1668-1672.LIU Z F, WANG J, ZHANG H. Dynamics property of structure with pre-tightening silicone rubber cushion[J]. China Mechanical Engineering,2007,18(14):1668-1672(in Chinese). [4] KIM N H, AN D, CHOI J H. Prognostics and health management of engineering systems[M]. Berlin: Springer International Publishing, 2017. [5] 张小丽, 王保建, 马猛, 等. 滚动轴承寿命预测综述[J]. 机械设计与制造, 2015(10): 221-224.ZHANG X L, WANG B J, MA M, et al. A review of life prediction for roller bearing[J]. Machinery Design & Manufacture, 2015(10): 221-224. [6] ZHU L S, JIANG B, CHENG Y. Life prediction methods based on data-driven: Review and trend[C]//2016 IEEE Chinese Guidance, Navigation and Control Conference (CGNCC). IEEE, 2016. [7] 段小成, 上官文斌, 王小莉, 等. 变幅载荷下填充型天然橡胶疲劳试验与预测方法研究[J]. 机械工程学报, 2016, 52(14):58-66. doi: 10.3901/JME.2016.14.058DUAN X C, SHANGGUAN W B, WANG X L, et al. Experiment and fatigue life prediction of filled natural rubber under variable amplitude loading conditions[J]. Journal of Mechanical Engineering,2016,52(14):58-66(in Chinese). doi: 10.3901/JME.2016.14.058 [8] 黄远红, 张方晓, 胡文军. 硅橡胶泡沫材料的应力松弛性能究[J]. 化工新型材料, 2009(8):85-87. doi: 10.3969/j.issn.1006-3536.2009.08.029HUANG Y H, ZHANG F X, HU W J. The research of the stress relaxation of cellular silicone materials[J]. New Chemical Materials,2009(8):85-87(in Chinese). doi: 10.3969/j.issn.1006-3536.2009.08.029 [9] ZHANG C S, LUO S K, SHI Y G, et al. Preparation and compression properties of silicon rubber foam with mixed cell structure[J]. Materials for Mechanical Engineering,2010,34(9):34-36. [10] LIU J, LI Q, HAN Y, et al. PEMFC residual life prediction using sparse autoencoder-based deep neural network[J]. IEEE Transactions on Transportation Electrification,2019,5(4):1279-1293. [11] SBARUFATTI C, CORBETTA M, MANES A, et al. Sequential Monte-Carlo sampling based on a committee of artificial neural networks for posterior state estimation and residual lifetime prediction[J]. International Journal of Fatigue, 2016, 83: 10-23. [12] LEI X, CHEN X, ZHANG X, et al. A novel approach for bearing remaining useful life estimation under neither failure nor suspension histories condition[J]. Journal of Intelligent Manufacturing,2017,28:1893-1914. [13] LIU F, LIU Y, CHEN F, et al. Residual life prediction for ball bearings based on joint approximate diagonalization of eigen matrices and extreme learning machine[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2015, 231(9): 203-210. [14] HANACHI H, MECHEFSKE C, LIU J, et al. Enhancement of prognostic models for short-term degradation of gas turbines[C]. IEEE International Conference on Prognostics and Health Management (ICPHM). Dallas, 2017: 66-69. [15] ARULAMPALAM M S, MASKELL S, GORDON N, et al. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking[J]. IEEE Transactions on Signal Processing, 2002, 50(2): 174-188. [16] HANACHI H, YU W, KIM I Y, et al. Hybrid data-driven physics-based model fusion framework for tool wear prediction[J]. The International Journal of Advanced Manufacturing Technology, 2018, 101: 2861-2872. [17] WANG D, YANG F, TSUI K L, et al. Remaining useful life prediction of lithium-ion batteries based on spherical cubature particle filter[J]. IEEE Transactions on Instrumentation & Measurement,2016,65(6):1282-1291. [18] AN H, WANG G, DONG Y, et al. Tool life prediction based on Gauss importance resampling particle filter[J]. International Journal of Advanced Manufacturing Technology,2019,103:4627-4634. [19] QIAN Y, YAN R. Remaining useful life prediction of rolling bearings using an enhanced particle filter[J]. IEEE Transactions on Instrumentation and Measurement,2015,64(10):2696-2707. doi: 10.1109/TIM.2015.2473935 [20] 沙艳松, 张长生, 李静莉, 等. 泡孔结构对硅橡胶泡沫材料性能的影响[J]. 机械工程材料, 2013, 37(2):25-28.SHA Y S, ZHANG C S, LI J L, et al. Effects of cell structure on properties of silicone rubber foam material[J]. Materials for Mechanical Engineering,2013,37(2):25-28(in Chinese). [21] KINNEY J H, MARSHALL G W, MARSHALL S J, et al. Three-dimensional imaging of large compressive deformations in elastomeric foams[J]. Journal of Applied Polymer Science, 2001, 80: 1746-1755. -
下载:
点击查看大图
计量
- 文章访问数: 906
- HTML全文浏览量: 397
- PDF下载量: 70
- 被引次数: 0
