多退化变量灰色预测模型的滚动轴承剩余寿命预测
|
摘要
针对单一退化变量预测滚动轴承性能退化趋势时可靠性和误差精度较低的问题,提出了基于多退化变量灰色预测模型的滚动轴承剩余寿命预测方法。该方法通过提取滚动轴承全寿命周期振动信号的退化趋势特征参数集,结合退化趋势特征参数集及故障早期突变点,实现滚动轴承的早期故障识别;并根据轴承寿命与特征参数之间的映射关系建立多退化变量灰色预测模型对轴承的剩余寿命进行预测。仿真实验结果表明,多退化变量灰色预测模型具有更高的误差精度和可靠性,其预测效果优于BP神经网络、单一退化变量灰色预测以及SVR(支持向量回归)预测模型,能够更好对滚动轴承寿命的变化趋势进行表征。
Aiming at the low reliability and error accuracy in predicting the degradation trend in rolling bearing when using single degenerate variable, a novel method based on grey prediction model with multiple degenerate variables was proposed to predict the residual life of rolling bearings. First of all, the characteristic parameter set related to degradation vibration signals of lifetime bearing was extracted. Then, the early fault identification of rolling bearing was completed by integrating the degradation trend characteristic parameter set and early breakdown point. And the grey prediction model with multiple degenerate variables was established through the mapping relationship between bearing life and characteristic parameters to predict the residual life of the rolling bearing. The simulation results showed that the grey prediction model with multiple degradation variables had higher error accuracy and reliability when compared with the grey prediction model with single degenerate variable, the prediction model of BP neural network and the prediction model of SVR(Support Vector Regression). It could characterize the degradation trend of rolling bearing life better.
Aiming at the low reliability and error accuracy in predicting the degradation trend in rolling bearing when using single degenerate variable, a novel method based on grey prediction model with multiple degenerate variables was proposed to predict the residual life of rolling bearings. First of all, the characteristic parameter set related to degradation vibration signals of lifetime bearing was extracted. Then, the early fault identification of rolling bearing was completed by integrating the degradation trend characteristic parameter set and early breakdown point. And the grey prediction model with multiple degenerate variables was established through the mapping relationship between bearing life and characteristic parameters to predict the residual life of the rolling bearing. The simulation results showed that the grey prediction model with multiple degradation variables had higher error accuracy and reliability when compared with the grey prediction model with single degenerate variable, the prediction model of BP neural network and the prediction model of SVR(Support Vector Regression). It could characterize the degradation trend of rolling bearing life better.
引文
[1]Heng A,Zhang S,Tan A C C,et al.Rotating machinery prognostics:State of the art,challenges and opportunities[J].Mechanical Systems & Signal Processing,2009,23(3):724-739.
[2] 周玉辉,康锐,苏荔,等.基于加速磨损试验的止推轴承磨损寿命预测[J].北京航空航天大学学报,2011,37(8):1016-1020.
[3] 宁峰平,姚建涛,滕志程,等.基于空间轴承寿命预测的预紧力优化分析[J].工程力学,2016,33(12):225-231.
[4] 奚立峰,黄润青,李兴林,等.基于神经网络的球轴承剩余寿命预测[J].机械工程学报,2007,43(10):137-143.
[5] 徐东,徐永成,陈循,等.基于EMD的灰色模型的疲劳剩余寿命预测方法研究[J].振动工程学报,2011,24(1):104-110.
[6] 崔建国,滑娇娇,董世良,等.基于SK和LSSVM的飞机空气制冷机寿命趋势分析[J].振动测试与诊断,2016,36(3):471-477.
[7] 翟军,盛建明.MGM(1,n)灰色模型及应用[J].系统工程理论与实践,1997,17(5):109-113.
[8] 赵敏,高宏力,许明恒,等.多变量灰色模型在滚珠丝杠剩余寿命预测中的应用[J].计算机集成制造系统,2011,17(4):846-851.
[9] Khan A,Chatterjee S,Bisai D,et al.Analysis of change point in surface temperature time series using cumulative sum chart and bootstrapping for asansol weather observation station,west Bengal,india[J].American Journal of Climate Change,2014,3(1):12.
[10] 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 & Vibration,2006,289(4):1066-1090.
[11] Shao Y,Nezu K.Prognosis of remaining bearing life using neural networks[J].Proceedings of the Institution of Mechanical Engineers—Part I,2005,214(3):217-230.
[12] Gebraeel N,Lawley M,Liu R,et al.Residual life predictions from vibration-based degradation signals:a neural network approach[J].IEEE Transactions on Industrial Electronics,2004,51(3):694-700.
[13] Hajnayeb A,Ghasemloonia A,Khadem S E,et al.Application and comparison of an ANN-based feature selection method and the genetic algorithm in gearbox fault diagnosis[J].Expert Systems with Applications,2011,38(8):10205-10209.
[14] 张利群,朱利民,钟秉林.几个机械状态监测特征量的特性研究[J].振动与冲击,2001,20(1):20-21.
[15] 李玉庆,王日新,徐敏强,等.针对滚动体损伤的滚动轴承损伤严重程度评估方法[J].振动与冲击,2013,32(18):169-173.
[16] 胡爱军,马万里,唐贵基.基于集成经验模态分解和峭度准则的滚动轴承故障特征提取方法[J].中国电机工程学报,2012,32(11):106-111.
[17] 袁冠雷,李顺才,杨睿,等.不同磨损状态下刀具车削振动特性试验研究[J].江苏师范大学学报(自然科学版),2016,34(1):76-78.
[18] Williams T,Ribadeneira X,Billington S,et al.Rolling element bearing diagnostics in run-to-failure lifetime testing[J].Mechanical Systems & Signal Processing,2001,15(5):979-993.
[19] 康守强,叶立强,王玉静,等.基于MCEA-KPCA和组合SVR的滚动轴承剩余使用寿命预测[J].电子测量与仪器学报,2017,31(9):1365-1371.
[20] 王恒,马海波,黄希,等.基于Kolmogorov-Smirnov检验和LS-SVM的机械设备故障预测[J].中南大学学报(自然科学版),2016,47(6):1924-1929.
[21] 张龙,黄文艺,熊国良,等.基于多域特征与高斯混合模型的滚动轴承性能退化评估[J].中国机械工程,2014,25(22):3066-3072.
[22] 李巍华,戴炳雄,张绍辉.基于小波包熵和高斯混合模型的轴承性能退化评估[J].振动与冲击,2013,32(21):35-40.
[23] Moriasi D N,Arnold J G,Van Liew M W,et al.Model evaluation guidelines for systematic quantification of accuracy in watershed simulations[J].Transactions of the Asabe,2007,50(3):885-900.
[2] 周玉辉,康锐,苏荔,等.基于加速磨损试验的止推轴承磨损寿命预测[J].北京航空航天大学学报,2011,37(8):1016-1020.
[3] 宁峰平,姚建涛,滕志程,等.基于空间轴承寿命预测的预紧力优化分析[J].工程力学,2016,33(12):225-231.
[4] 奚立峰,黄润青,李兴林,等.基于神经网络的球轴承剩余寿命预测[J].机械工程学报,2007,43(10):137-143.
[5] 徐东,徐永成,陈循,等.基于EMD的灰色模型的疲劳剩余寿命预测方法研究[J].振动工程学报,2011,24(1):104-110.
[6] 崔建国,滑娇娇,董世良,等.基于SK和LSSVM的飞机空气制冷机寿命趋势分析[J].振动测试与诊断,2016,36(3):471-477.
[7] 翟军,盛建明.MGM(1,n)灰色模型及应用[J].系统工程理论与实践,1997,17(5):109-113.
[8] 赵敏,高宏力,许明恒,等.多变量灰色模型在滚珠丝杠剩余寿命预测中的应用[J].计算机集成制造系统,2011,17(4):846-851.
[9] Khan A,Chatterjee S,Bisai D,et al.Analysis of change point in surface temperature time series using cumulative sum chart and bootstrapping for asansol weather observation station,west Bengal,india[J].American Journal of Climate Change,2014,3(1):12.
[10] 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 & Vibration,2006,289(4):1066-1090.
[11] Shao Y,Nezu K.Prognosis of remaining bearing life using neural networks[J].Proceedings of the Institution of Mechanical Engineers—Part I,2005,214(3):217-230.
[12] Gebraeel N,Lawley M,Liu R,et al.Residual life predictions from vibration-based degradation signals:a neural network approach[J].IEEE Transactions on Industrial Electronics,2004,51(3):694-700.
[13] Hajnayeb A,Ghasemloonia A,Khadem S E,et al.Application and comparison of an ANN-based feature selection method and the genetic algorithm in gearbox fault diagnosis[J].Expert Systems with Applications,2011,38(8):10205-10209.
[14] 张利群,朱利民,钟秉林.几个机械状态监测特征量的特性研究[J].振动与冲击,2001,20(1):20-21.
[15] 李玉庆,王日新,徐敏强,等.针对滚动体损伤的滚动轴承损伤严重程度评估方法[J].振动与冲击,2013,32(18):169-173.
[16] 胡爱军,马万里,唐贵基.基于集成经验模态分解和峭度准则的滚动轴承故障特征提取方法[J].中国电机工程学报,2012,32(11):106-111.
[17] 袁冠雷,李顺才,杨睿,等.不同磨损状态下刀具车削振动特性试验研究[J].江苏师范大学学报(自然科学版),2016,34(1):76-78.
[18] Williams T,Ribadeneira X,Billington S,et al.Rolling element bearing diagnostics in run-to-failure lifetime testing[J].Mechanical Systems & Signal Processing,2001,15(5):979-993.
[19] 康守强,叶立强,王玉静,等.基于MCEA-KPCA和组合SVR的滚动轴承剩余使用寿命预测[J].电子测量与仪器学报,2017,31(9):1365-1371.
[20] 王恒,马海波,黄希,等.基于Kolmogorov-Smirnov检验和LS-SVM的机械设备故障预测[J].中南大学学报(自然科学版),2016,47(6):1924-1929.
[21] 张龙,黄文艺,熊国良,等.基于多域特征与高斯混合模型的滚动轴承性能退化评估[J].中国机械工程,2014,25(22):3066-3072.
[22] 李巍华,戴炳雄,张绍辉.基于小波包熵和高斯混合模型的轴承性能退化评估[J].振动与冲击,2013,32(21):35-40.
[23] Moriasi D N,Arnold J G,Van Liew M W,et al.Model evaluation guidelines for systematic quantification of accuracy in watershed simulations[J].Transactions of the Asabe,2007,50(3):885-900.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |