Degradation trend prediction of rolling bearing vibration performance based on fusion grey entropy and bootstrap Markov chain
-
摘要:
针对现有的基于熵的非线性动力学方法存在计算结果与非线性动力学系统不一致、计算结果在不同尺度上不一致、计算所需数据长度较长的缺点,提出一种新的非线性时间序列复杂性测度:融合灰色熵算法,并将其用于滚动轴承退化特征提取。针对滚动轴承退化趋势序列数据长度短、预测困难的问题,提出了自助马尔科夫链预测模型。试验研究结果表明,融合灰色熵对数据长度要求较低,并且在不同尺度上的计算结果具有一致性。同时,所提的自助马尔科夫链预测模型的平均相对误差仅为8.4973%,低于GM模型的平均相对误差。这说明所提模型能够有效地对滚动轴承的振动性能退化趋势进行预测。
Abstract:In view of the shortcomings of existing entropy-based nonlinear dynamics methods that the calculation results are inconsistent with the nonlinear dynamics system at different scales and the data length required for the calculation is long, the fusion gray entropy algorithm, a new measure of nonlinear time series complexity, was proposed and then used to extract the degradation features of rolling bearing. Considering the problems of very short data length of the rolling bearing degradation trend sequence that it is difficult for prediction, Bootstrap Markov chain prediction model was proposed. The experimental results showed that the data length requirement of fusion gray entropy was low, and the calculation results of the fusion gray entropy at different scales were consistent. Meanwhile, the average relative error of the proposed bootstap Markov chain prediction model was only 8.4973%, which was lower than that of the GM model. This showed that the proposed model can effectively predict the vibration performance degradation trend of rolling bearings.
-
表 1 GM模型预测与残差
Table 1. GM model predictions and residuals
序号 融合灰色熵 GM模型预测 残差 1 0.38616 0.38616 0 2 0.434173 0.426765 0.007408 3 0.393394 0.420918 −0.02752 4 0.421035 0.415151 0.005883 5 0.402322 0.409464 −0.00714 6 0.430665 0.403854 0.026811 7 0.429364 0.39832 0.031043 8 0.364764 0.392863 −0.0281 9 0.381094 0.38748 −0.00639 10 0.380181 0.382172 −0.00199 表 2 马尔科夫状态区间
Table 2. Markov state interval
区间符号 区间值 ΔI1 [0, 0.0078] ΔI2 [0.0078, 0.0155] ΔI3 [0.0155, 0.0233] ΔI4 [0.0233, 0.0310] 表 3 第11个残差状态预测
Table 3. The 11th residual state prediction
序号 绝对残差 初始状态 转移步数 状态ΔI1 状态ΔI2 状态ΔI3 状态ΔI4 10 0.00199 ΔI1 1 0.8168 0.1761 0.0071 0 9 0.00639 ΔI1 2 0.8177 0.1751 0.0072 0 8 0.0281 ΔI4 3 0.7857 0.1767 0.0220 0.0156 7 0.031043 ΔI4 4 0.8097 0.1755 0.0109 0.0039 概率分布P|ΔIj 3.2299 0.7034 0.0472 0.0195 表 4 预测结果的平均相对误差和平均绝对误差
Table 4. Averaged relative errors and absolute errors of prediction results
模型 平均相对误差/% 平均绝对误差 GM 9.2616 0.0273 自助马尔科夫链 8.4973 0.0253 -
[1] LI Hongru,WANG Yukui,WANG Bing,et al. The application of a general mathematical morphological particle as a novel indicator for the performance degradation assessment of a bearing[J]. Mechanical Systems and Signal Processing,2017,82: 490-502. doi: 10.1016/j.ymssp.2016.05.038 [2] 李锋,向往,陈勇,等. 基于双隐层量子线路循环单元神经网络的状态退化趋势预测[J]. 机械工程学报,2019,55(6): 83-92. doi: 10.3901/JME.2019.06.083LI Feng,XIANG Wang,CHEN Yong,et al. State degradation trend prediction based on double hidden layer quantum circuit recurrent unit neural network[J]. Journal of Mechanical Engineering,2019,55(6): 83-92. (in Chinese) doi: 10.3901/JME.2019.06.083 [3] YAN Ruqiang,LIU Yongbin,GAO R X. Permutation entropy: a nonlinear statistical measure for status characterization of rotary machines[J]. Mechanical Systems and Signal Processing,2012,29: 474-484. doi: 10.1016/j.ymssp.2011.11.022 [4] 李洪儒,于贺,田再克,等. 基于二元多尺度熵的滚动轴承退化趋势预测[J]. 中国机械工程,2017,28(20): 2420-2425, 2433. doi: 10.3969/j.issn.1004-132X.2017.20.005LI Hongru,YU He,TIAN Zaike,et al. Degradation trend prediction of rolling bearings based on two-element multiscale entropy[J]. China Mechanical Engineering,2017,28(20): 2420-2425, 2433. (in Chinese) doi: 10.3969/j.issn.1004-132X.2017.20.005 [5] 王冰,胡雄,李洪儒,等. 基于基本尺度熵与GG模糊聚类的轴承性能退化状态识别[J]. 振动与冲击,2019,38(5): 190-197, 221.WANG Bing,HU Xiong,LI Hongru,et al. Rolling bearing performance degradation state recognition based on basic scale entropy and GG fuzzy clustering[J]. Journal of Vibration and Shock,2019,38(5): 190-197, 221. (in Chinese) [6] 于重重,宁亚倩,秦勇,等. 基于T-SNE样本熵和TCN的滚动轴承状态退化趋势预测[J]. 仪器仪表学报,2019,40(8): 39-46.YU Chongchong,NING Yaqian,QIN Yong,et al. Prediction of rolling bearing state degradation trend based on T-SNE sample entropy and TCN[J]. Chinese Journal of Scientific Instrument,2019,40(8): 39-46. (in Chinese) [7] 李永健,宋浩,刘吉华,等. 基于改进多尺度排列熵的列车轴箱轴承诊断方法研究[J]. 铁道学报,2020,42(1): 33-39.LI Yongjian,SONG Hao,LIU Jihua,et al. A study on fault diagnosis method for train axle box bearing based on modified multiscale permutation entropy[J]. Journal of the China Railway Society,2020,42(1): 33-39. (in Chinese) [8] 赵荣珍,李霁蒲,邓林峰. EWT多尺度排列熵与GG聚类的轴承故障辨识方法[J]. 振动 测试与诊断,2019,39(2): 416-423, 451.ZHAO Rongzhen,LI Jipu,DENG Linfeng. Method integrate EWT multi-scale permutation entropy with GG clustering for bearing fault diagnosis[J]. Journal of Vibration, Measurement & Diagnosis,2019,39(2): 416-423, 451. (in Chinese) [9] 陈东宁,张运东,姚成玉,等. 基于FVMD多尺度排列熵和GK模糊聚类的故障诊断[J]. 机械工程学报,2018,54(14): 16-27.CHEN Dongning,ZHANG Yundong,YAO Chengyu,et al. Fault diagnosis based on FVMD multi-scale permutation entropy and GK fuzzy clustering[J]. Journal of Mechanical Engineering,2018,54(14): 16-27. (in Chinese) [10] 戴邵武,陈强强,戴洪德,等. 基于平滑先验分析和模糊熵的滚动轴承故障诊断[J]. 航空动力学报,2019,34(10): 2218-2226.DAI Shaowu,CHEN Qiangqiang,DAI Hongde,et al. Rolling bearing fault diagnosis based on smoothness priors approach and fuzzy entropy[J]. Journal of Aerospace Power,2019,34(10): 2218-2226. (in Chinese) [11] RICHMAN J S,MOORMAN J R. Physiological time-series analysis using approximate entropy and sample entropy[J]. American Journal of Physiology Heart and Circulatory Physiology,2000,278(6): 2039-2049. doi: 10.1152/ajpheart.2000.278.6.H2039 [12] BANDT C,POMPE B. Permutation entropy: a natural complexity measure for time series[J]. Physical Review Letters,2002,88(17): 174102. doi: 10.1103/PhysRevLett.88.174102 [13] CHEN Weiting,WANG Zhizhong,XIE Hongbo,et al. Characterization of surface EMG signal based on fuzzy entropy[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering,2007,15(2): 266-272. doi: 10.1109/TNSRE.2007.897025 [14] COSTA M,GOLDBERGER A L,PENG C K. Multiscale entropy analysis of complex physiologic time series[J]. Physical Review Letters,2002,89(6): 068102. doi: 10.1103/PhysRevLett.89.068102 [15] 邓聚龙. 灰理论基础[M]. 武汉: 华中科技大学出版社, 2002. [16] 邢海燕,孙晓军,王犇,等. 基于模糊加权马尔科夫链的焊缝隐性损伤磁记忆特征参数定量预测[J]. 机械工程学报,2017,53(12): 70-77. doi: 10.3901/JME.2017.12.070XING Haiyan,SUN Xiaojun,WANG Ben,et al. Quantitative MMM characteristic parameter prediction for weld hidden damage status based on the fuzzy weighted Markov chain[J]. Journal of Mechanical Engineering,2017,53(12): 70-77. (in Chinese) doi: 10.3901/JME.2017.12.070 [17] EFRON B,TIBSHIRANI R. Bootstrap methods for standard errors, confidence intervals, and other measures of statistical accuracy[J]. Statistical Science,1986,1(1): 54-75. [18] 郑近德,陈敏均,程军圣,等. 多尺度模糊熵及其在滚动轴承故障诊断中的应用[J]. 振动工程学报,2014,27(1): 145-151.ZHENG Jinde,CHEN Minjun,CHENG Junsheng,et al. Multiscale fuzzy entropy and its application in rolling bearing fault diagnosis[J]. Journal of Vibration Engineering,2014,27(1): 145-151. (in Chinese)