基于模糊关联维数和最大熵粒子滤波的滚动轴承退化阶段预测

程立; 马文锁; 高作斌

doi:10.13224/j.cnki.jasp.20240006

基于模糊关联维数和最大熵粒子滤波的滚动轴承退化阶段预测

doi: 10.13224/j.cnki.jasp.20240006

程立^1,,
马文锁^2,*, ,,
高作斌²

1.
河南科技大学信息工程学院，河南洛阳 471023
2.
河南科技大学机电工程学院，河南洛阳 471003

详细信息

作者简介:
程立（1990-），男，讲师，博士，主要从事滚动轴承可靠性与退化趋势研究。E-mail：chengli0923@163.com

通讯作者:
马文锁（1969-），男，教授，博士，主要从事轴承性能与复合材料研究。E-mail：mawensuo@haust.edu.cn

中图分类号: V233.1；TH133.33
计量
- 文章访问数: 369
- HTML浏览量: 305
- PDF量: 25
- 被引次数: 0
出版历程
- 收稿日期: 2024-01-03
- 网络出版日期: 2024-09-10

Degradation stage prediction of rolling bearing based on fuzzy correlation dimension and maximum entropy particle filter

CHENG Li^1
,,
MA Wensuo^{2,*
, ,},
GAO Zuobin²

1.
School of Information Engineering，Henan University of Science and Technology，Luoyang Henan 471023，China
2.
School of Mechatronics Engineering，Henan University of Science and Technology，Luoyang Henan 471003，China

摘要

摘要:
针对使用硬阈值函数计算关联维数导致边界扰动问题，提出模糊关联维数方法，并将其用于提取滚动轴承退化特征。针对滚动轴承退化阶段小样本预测特点以及传统粒子滤波缺乏预测结果的置信区间估计问题，提出最大熵粒子滤波方法。试验研究结果表明：模糊关联维数与滚动轴承振动信号的演变趋势具有一致性，能够准确提取滚动轴承振动性能退化特征。同时，所提最大熵粒子滤波的平均相对误差显仅为1.31%，平均绝对误差仅为6.94，显著低于传统粒子滤波和GM模型，并且增加的区间预测功能使其预测结果更加丰富多样。
- 滚动轴承 /
- 退化阶段预测 /
- 关联维数 /
- 粒子滤波 /
- 最大熵
Abstract:
Considering the problem in calculating the correlation dimension using the hard threshold function that may lead to boundary disturbances, a fuzzy correlation dimension method was proposed and then used to extract the degradation features of rolling bearing. In view of the small sample prediction characteristics for the degradation stage of rolling bearing and the lack of confidence interval estimation for prediction results in traditional particle filtering, the maximum entropy particle filtering method was proposed. The experimental results showed that the fuzzy correlation dimension was consistent with the evolution trend of rolling bearing vibration signals, and can accurately extract the rolling bearing vibration performance degradation feature. Meanwhile, the average relative error of the proposed maximum entropy particle filter was only 1.31%, and the average absolute error was only 6.94, which was significantly lower than traditional particle filters and GM models. The added interval prediction function made the prediction results more diverse.
- rolling bearing /
- degradation stage prediction /
- correlation dimension /
- particle filter /
- maximum entropy

HTML

图 1 Heaviside函数与隶属度函数

Figure 1. Heaviside function and membership function

下载: 全尺寸图片幻灯片

图 2 滚动轴承退化阶段预测流程图

Figure 2. Flowchart of rolling bearing degradation stage prediction

下载: 全尺寸图片幻灯片

图 3 滚动轴承试验台示意图

Figure 3. Schematic of rolling bearing test rig

下载: 全尺寸图片幻灯片

图 4 滚动轴承全寿命振动性能时间序列

Figure 4. Lifetime vibration performance data of rolling bearing

下载: 全尺寸图片幻灯片

图 5 ln m-ln F₂（m, d）曲线图

Figure 5. Diagram of ln m-ln F₂（m, d） curves

下载: 全尺寸图片幻灯片

图 6 滚动轴承退化特征序列

Figure 6. Degradation feature sequence of rolling bearing

下载: 全尺寸图片幻灯片

图 7 基于最大熵粒子滤波的滚动轴承退化阶段预测

Figure 7. Degradation stage prediction of rolling bearing using maximum entropy particle filter

下载: 全尺寸图片幻灯片

图 8 基于传统粒子滤波的滚动轴承退化阶段预测

Figure 8. Degradation stage prediction of rolling bearing using traditional particle filter

下载: 全尺寸图片幻灯片

图 9 基于GM模型的滚动轴承退化阶段预测

Figure 9. Degradation stage prediction of rolling bearing using GM model

下载: 全尺寸图片幻灯片

表 1 各个振动序列的延迟时间与饱和嵌入维数

Table 1. Delay time and saturation embedding dimension of each vibration sequence

振动序列号延迟时间t 饱和嵌入维数d₀

1 2 28
2 1 30
3 2 20
4 1 24
5 3 26
6 1 20
7 2 18
8 2 26
9 2 26
10 3 16

下载: 导出CSV

表 2 不同方法预测结果

Table 2. Prediction results using different methods

参数平均绝对误差平均相对误差/%

最大熵粒子滤波 6.94 1.31
传统粒子滤波 197.89 33.30
GM模型 71.67 16.47

下载: 导出CSV

参考文献(21)

[1]	王进花,胡佳伟,曹洁,等. 基于自适应变分模态分解和集成极限学习机的滚动轴承多故障诊断[J]. 吉林大学学报(工学版),2022,52(2): 318-328. WANG Jinhua,HU Jiawei,CAO Jie,et al. Multi-fault diagnosis of rolling bearing based on adaptive variational modal decomposition and integrated extreme learning machine[J]. Journal of Jilin University (Engineering and Technology Edition),2022,52(2): 318-328. (in Chinese WANG Jinhua, HU Jiawei, CAO Jie, et al. Multi-fault diagnosis of rolling bearing based on adaptive variational modal decomposition and integrated extreme learning machine[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(2): 318-328. (in Chinese)
[2]	WANG Zhijian,ZHAO Wenyan,LI Yanfeng,et al. Adaptive staged RUL prediction of rolling bearing[J]. Measurement,2023,222: 113478. doi: 10.1016/j.measurement.2023.113478
[3]	SHENG Yuanyuan,LIU Huanyu,LI Junbao. Bearing performance degradation assessment and remaining useful life prediction based on data-driven and physical model[J]. Measurement Science and Technology,2023,34(5): 055002. doi: 10.1088/1361-6501/acb374
[4]	SHI Mingkuan,DING Chuancang,QUE Hongbo,et al. Multilayer-graph-embedded extreme learning machine for performance degradation prognosis of bearing[J]. Measurement,2023,207: 112299. doi: 10.1016/j.measurement.2022.112299
[5]	LI Chunyun,NOMAN K,LIU Zheng,et al. Optimal symbolic entropy: an adaptive feature extraction algorithm for condition monitoring of bearings[J]. Information Fusion,2023,98: 101831. doi: 10.1016/j.inffus.2023.101831
[6]	程立,马文锁,夏新涛,等. 基于融合灰色熵和自助马尔科夫链的滚动轴承振动性能退化趋势预测[J]. 航空动力学报,2023,38(9): 2221-2230. CHENG Li,MA Wensuo,XIA Xintao,et al. Degradation trend prediction of rolling bearing vibration performance based on fusion grey entropy and bootstrap Markov chain[J]. Journal of Aerospace Power,2023,38(9): 2221-2230. (in Chinese CHENG Li, MA Wensuo, XIA Xintao, et al. Degradation trend prediction of rolling bearing vibration performance based on fusion grey entropy and bootstrap Markov chain[J]. Journal of Aerospace Power, 2023, 38(9): 2221-2230. (in Chinese)
[7]	WANG Yaping,HOU Dekang,XU Di,et al. Prediction of rolling bearing performance degradation based on sae and TCN-attention models[J]. Journal of Mechanical Science and Technology,2023,37(4): 1567-1583. doi: 10.1007/s12206-023-0301-4
[8]	LOGAN D,MATHEW J. Using the correlation dimension for vibration fault diagnosis of rolling element bearings: Ⅰ basic concepts[J]. Mechanical Systems and Signal Processing,1996,10(3): 241-250. doi: 10.1006/mssp.1996.0018
[9]	WANG W J,CHEN J,WU X K,et al. The application of some non-linear methods in rotating machinery fault diagnosis[J]. Mechanical Systems and Signal Processing,2001,15(4): 697-705. doi: 10.1006/mssp.2000.1316
[10]	CHEN Changrui,HE Tian,WU Dengyun,et al. A fault diagnosis method for satellite flywheel bearings based on 3D correlation dimension clustering technology[J]. IEEE Access,2018,6: 78483-78492. doi: 10.1109/ACCESS.2018.2885046
[11]	WANG Dong,ZHONG Jingjing,SHEN Changqing,et al. Correlation dimension and approximate entropy for machine condition monitoring: Revisited[J]. Mechanical Systems and Signal Processing,2021,152: 107497. doi: 10.1016/j.ymssp.2020.107497
[12]	叶亮,邓四二,崔永存,等. 滚动轴承振动性能状态演变的非线性特征和不确定性特征的灰关系分析[J]. 航空动力学报,2022,37(6): 1121-1133. YE Liang,DENG Sier,CUI Yongcun,et al. Grey relation analysis on nonlinear characteristics and uncertainty characteristics of evolution of rolling bearing vibration performance state[J]. Journal of Aerospace Power,2022,37(6): 1121-1133. (in Chinese YE Liang, DENG Sier, CUI Yongcun, et al. Grey relation analysis on nonlinear characteristics and uncertainty characteristics of evolution of rolling bearing vibration performance state[J]. Journal of Aerospace Power, 2022, 37(6): 1121-1133. (in Chinese)
[13]	王宇,刘秋发,彭一真. 非均匀监测条件下滚动轴承剩余寿命预测方法[J]. 机械工程学报,2023,59(23): 96-104. WANG Yu,LIU Qiufa,PENG Yizhen. A remaining useful life prediction approach with nonuniform monitoring conditions for rolling bearings[J]. Journal of Mechanical Engineering,2023,59(23): 96-104. (in Chinese doi: 10.3901/JME.2023.23.096 WANG Yu, LIU Qiufa, PENG Yizhen. A remaining useful life prediction approach with nonuniform monitoring conditions for rolling bearings[J]. Journal of Mechanical Engineering, 2023, 59(23): 96-104. (in Chinese) doi: 10.3901/JME.2023.23.096
[14]	丁显,徐进,黎曦琳,等. 融合维纳过程和粒子滤波的风力发电机轴承剩余寿命预测[J]. 太阳能学报,2022,43(12): 248-255. DING Xian,XU Jin,LI Xilin,et al. Remaining life prediction of wind turbine bearing based on Wiener process and particle filter[J]. Acta Energiae Solaris Sinica,2022,43(12): 248-255. (in Chinese DING Xian, XU Jin, LI Xilin, et al. Remaining life prediction of wind turbine bearing based on Wiener process and particle filter[J]. Acta Energiae Solaris Sinica, 2022, 43(12): 248-255. (in Chinese)
[15]	ZHANG Tianyu,WANG Qingfeng,SHU Yue,et al. Remaining useful life prediction for rolling bearings with a novel entropy-based health indicator and improved particle filter algorithm[J]. IEEE Access,2023,11: 3062-3079. doi: 10.1109/ACCESS.2023.3234286
[16]	LIU Hengyu,YUAN Rui,LV Yong,et al. Remaining useful life prediction of rolling bearings based on segmented relative phase space warping and particle filter[J]. IEEE Transactions on Instrumentation and Measurement,2022,71: 3527415.
[17]	CUI Lingli,LI Wenjie,WANG Xin,et al. Comprehensive remaining useful life prediction for rolling element bearings based on time-varying particle filtering[J]. IEEE Transactions on Instrumentation and Measurement,2022,71: 3510010.
[18]	夏新涛,叶亮,常振,等. 乏信息条件下滚动轴承振动性能可靠性变异过程预测[J]. 振动与冲击,2017,36(8): 105-112,143. XIA Xintao,YE Liang,CHANG Zhen,et al. Prediction for variation process of reliability on vibration performance of rolling bearings under the condition of poor information[J]. Journal of Vibration and Shock,2017,36(8): 105-112,143. (in Chinese XIA Xintao, YE Liang, CHANG Zhen, et al. Prediction for variation process of reliability on vibration performance of rolling bearings under the condition of poor information[J]. Journal of Vibration and Shock, 2017, 36(8): 105-112, 143. (in Chinese)
[19]	FRASER A M,SWINNEY H L. Independent coordinates for strange attractors from mutual information[J]. Physical Review A,General Physics,1986,33(2): 1134-1140. doi: 10.1103/PhysRevA.33.1134
[20]	GRASSBERGER P,PROCACCIA I. Measuring the strangeness of strange attractors[J]. Physica D: Nonlinear Phenomena,1983,9(1/2): 189-208.
[21]	QIU H,LEE J,LIN J,et al. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics[J]. Journal of Sound and Vibration,2006,289(4): 1066-1090.