基于SPA-FIG与优化ELM的滚动轴承性能退化趋势预测

PDF(1882 KB)

振动与冲击 ›› 2020, Vol. 39 ›› Issue (19) : 187-194.

论文

陈强强1,2，戴邵武1，戴洪德3，朱敏1，孙玉玉4

作者信息 +

Performance degradation trend prediction of rolling bearings based on SPA-FIG and optimized ELM

CHEN Qiangqiang1,2, DAI Shaowu1, DAI Hongde3, ZHU Min1, SUN Yuyu4

Author information +

文章历史 +

摘要

为了提高滚动轴承性能退化指标的预测精度，得到性能退化指标准确的预测范围，本文提出基于分解-模糊粒化与优化极限学习机（Extreme Learning Machine，ELM）的轴承性能退化趋势模糊粒化预测。首先利用平滑先验分析提取轴承性能退化指标序列的趋势项及波动项，再利用信息粒化方法对波动项进行模糊信息粒化；然后将趋势项及粒化后的波动项数据输入至ELM进行回归预测，并采用粒子群算法优化ELM参数；最后根据实测值和预测值的对比分析评估预测模型的优良性。实验结果表明，该方法可以有效跟踪轴承性能退化指标的变化趋势，并对其指标的波动范围进行有效预测。

Abstract

In order to improve prediction accuracy of rolling bearing performance degradation index, and obtain an accurate prediction range of performance degradation index, a novel performance degradation trend prediction method based on smooth prior analysis (SPA)-fuzzy information granulation (FID) and optimized extreme learning machine (ELM) was proposed.Firstly, SPA was used to extract the trend term and fluctuation term of bearing performance degradation index sequences, and FIG was used to do fuzzy information granulation for the fluctuation term.Then, the trend term and the granulated fluctuationtermwere input into ELM to perform regression prediction, and the particle swarm optimization (PSO) was used to optimize ELM parameters. Finally, the excellence of the prediction model was estimated according to the contrastive analysis of the measured values and the predicted ones. Test results showed that the proposed method can effectively track the change trend of bearing performance degradation index and predict the fluctuation range of the index.

导出引用

陈强强1,2，戴邵武1，戴洪德3，朱敏1，孙玉玉4. 基于SPA-FIG与优化ELM的滚动轴承性能退化趋势预测[J]. 振动与冲击, 2020, 39(19): 187-194

CHEN Qiangqiang1,2, DAI Shaowu1, DAI Hongde3, ZHU Min1, SUN Yuyu4. Performance degradation trend prediction of rolling bearings based on SPA-FIG and optimized ELM[J]. Journal of Vibration and Shock, 2020, 39(19): 187-194

参考文献

[1] 边杰. 基于遗传算法参数优化的变分模态分解结合1.5维谱的轴承故障诊断[J]. 推进技术, 2017, 38(07): 1618-1624.
BIAN Jie. Fault Diagnosis of Bearing Combining Parameter Optimized Variational Mode Decomposition Based on Genetic Algorithm with 1.5-Dimensional Spectrum[J]. Journal of Propulsion Technology, 2017, 38(07): 1618-1624.
[2] 陈果. 含复杂滚动轴承建模的航空发动机整机振动耦合动力学模型[J]. 航空动力学报, 2017, 32(09): 2193-2204.
CHEN Guo. Whole aero-engine vibration coupling dynamics model including modeling of complex ball and roller bearings[J]. Journal of Aerospace Power. 2017, 32(09): 2193-2204.
[3] 许迪，葛江华，王亚萍，等. 流形学习和M-KH-SVR的滚动轴承衰退预测[J]. 振动工程学报, 2018, 31(05): 892-901.
XU Di, GE Jianghua, WANG Yaping, et al. Prediction of rolling bearing performance degradation based on manifold learning and M-KH-SVR[J]. Journal of Vibration Engineering. 2018, 31(05): 892-901.
[4] GANGSAR P, TIWARI R. Multiclass Fault Taxonomy in Rolling Bearings at Interpolated and Extrapolated Speeds Based on Time Domain Vibration Data by SVM Algorithms[J]. Journal of Failure Analysis & Prevention, 2014, 14(6): 826-837.
[5] 周建民，张臣臣，王发令，等. 基于ARMA的滚动轴承振动数据预测[J]. 华东交通大学学报, 2018, 35(05): 99-103.
ZHOU Jianmin, ZHANG Chenchen, WANG Faling, et al. Rolling bearing vibration data prediction based on ARMA[J]. Journal of East China Jiaotong University, 2018, 35(05): 99-103.
[6] 陈法法，杨勇，马婧华，等. 信息熵与优化LS-SVM的轴承性能退化模糊粒化预测术[J]. 仪器仪表学报, 2016, 37(4): 779-787.
CHEN Fafa, YANG Yong, MA Jinghua, et al. Fuzzy granulation prediction for bearing performance degradation based on information entropy and optimized LS-SVM[J]. Chinese Journal of Scientific Instrument, 2016, 37(4): 779-787.
[7] 王付广. 基于ELM的滚动轴承退化趋势与剩余寿命预测方法研究[D]. 安徽工业大学, 2018.
WANG Fuguang. Research on the degradation trend and residual life prediction method of rolling bearing based on ELM[D]. Anhui University of Technology, 2018 .
[8] 李艳军，张建，曹愈远，等. 基于模糊信息粒化和优化SVM的航空发动机性能趋势预测[J]. 航空动力学报, 2017, 32(12): 3022-3030.
LI Yanjun, ZHANG Jian, CAO Yuyuan, et al. Forecasting of aero-engine performance trend based on fuzzy information granulation and optimized SVM[J]. Journal of Aerospace Power. 2017, 32(12): 3022-3030.
[9] 柳玉，曾德良，刘吉臻，等. 基于小波包变换的最小二乘支持向量机短期风速多步预测和信息粒化预测的研究[J]. 太阳能学报, 2014, 35(02): 214-220.
LIU Yu, CENG Deliang, LIU Jizen, et al. Wavelet packet transform and the least squares support machine in research of short-term wind speed multistep prediction and information granulation prediction[J]. Acta Energiae Solaris Sincia, 2014, 35(02): 214-220.
[10] 陈法法，杨勇，陈保家，等. 基于模糊信息粒化与小波支持向量机的滚动轴承性能退化趋势预测[J]. 中国机械工程, 2016, 27(12): 1655-1661.
CHEN Fafa, YANG Yong, CHEN Baojia, et al. Degradation Trend prediction of rolling bearings based on fuzzy information granulation and wavelet support vector machine[J]. China Mechanical Engineering, 2016, 27(12): 1655-1661.
[11] ZADEH L A. Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic[J]. Fuzzy Sets and Systems, 1997, 90(2): 111-127.
[12] 黄海峰，易武，易庆林，等. 滑坡位移分解预测中的平滑先验分析方法[J]. 水文地质工程地质, 2014, 41(05): 95-100.
HUANG Haifeng, YI Wu, YI Qinglin, et al. Smoothness priors approach in displacement decomposition and prediction of landslides[J]. Hydrogelogy & Engineering Geology. 2014, 41(05): 95-100.
[13] 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.
LI 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.
[14] CHRISTOPH B, BERND P. Permutation entropy: a natural complexity measure for time series[J]. Physical Review Letters, 2002, 88(17): 102-104.
[15] LI G, MA X, YANG H. A Hybrid Model for Monthly Precipitation Time Series Forecasting Based on Variational Mode Decomposition with Extreme Learning Machine[J]. Information, 2018, 9(7): 177.
[16] CHEN X, CUI B. Efficient modeling of fiber optic gyroscope drift using improved EEMD and extreme learning machine[J]. Signal Processing, 2016, 128: 1-7.
[17] GARCÍAGONZALO E, FERNÁNDEZMARTÍNEZ J L. A Brief Historical Review of Particle Swarm Optimization (PSO)[J]. Journal of Bioinformatics & Intelligent Control, 2012, 1(1): 3-16.
[18] 李滨，覃芳璐，吴茵，等. 基于模糊信息粒化与多策略灵敏度的短期日负荷曲线预测[J]. 电工技术学报, 2017, 32(09): 149-159.
LI Bin, QIN Fanglu, WU Yin, et al. Short-term daily liad curve forecasting based on fuzzy information granulation and multi-straegy sensitivity[J]. Transactions of China Electro Technical Society, 2017, 32(09): 149-159.
[19] 冯辅周，司爱威，江鹏程. 小波相关排列熵和HMM在故障预测中的应用[J]. 振动工程学报, 2013, 26(02): 269-276.
FENG Fuzhou, SI Aiwei, JIANG Pengcheng. Application of wavelet correlation permutation entropy and hidden Markov model to fault prognostic[J]. Journal of vibration Engineering, 2013, 26(02): 269-276.
[20] WANG W, LU Y. Analysis of the Mean Absolute Error (MAE) and the Root Mean Square Error (RMSE) in Assessing Rounding Model[J]. 2018, 324(1): 120-129.