Remaining Useful Life Prediction for Rolling Bearings based on Linear Regression and EEMD
-
摘要: 滚动轴承的剩余使用寿命(Remaining useful life,RUL)预测是轴承健康管理的关键一环。然而,对于滚动轴承RUL预测的两个关键问题:开始预测时间点(Start prediction time,SPT)的选择;对于寿命虚假波动的处理。为了解决这两个问题,提出一种基于数据驱动的滚动轴承RUL预测方法。该方法先利用集合经验模态(Ensemble empirical mode decomposition,EEMD)对振动信号进行降噪处理,然后依靠均方根(Root mean square,RMS)梯度来选择SPT点进行RUL预测,最后,在RUL预测的同时,使用线性回归来进行寿命虚假波动修复。为了验证方法的有效性,采用仿真模拟数据,以及真实数据进行了验证。实验结果表明,所提出的方法能够有效选择合适的SPT以及修复寿命虚假波动。Abstract: The prediction on the remaining useful life of rolling bearings is a key part of bearing health management. However, the two key issues for the prediction of rolling bearing RUL:The selection of start prediction time; For the treatment of false fluctuations in life. In order to solve these two problems, a data-driven rolling bearing RUL prediction method is proposed in this paper. The method first uses the ensemble empirical mode decomposition (EEMD) to denoise the vibration signal, and then selects the SPT point based on the RMS gradient to perform RUL prediction. Finally, in the RUL prediction, the linear regression is used to repair the false life fluctuation. In order to verify the validity of the method, this paper uses simulation data and real data to verify. Experimental results show that the proposed method can effectively select the appropriate SPT and repair the false life fluctuations.
-
表 1 SPT选择结果
方法 轴承1 轴承2 轴承3 Wasim Ahmad的方法 18 350 min 12 670 min 1 440 min Naipeng Li的方法 19 510 min 18 300 min 7 020 min 本文所提出的方法 18 680 min 16 280 min 5 280 min 表 2 SPT选择所对应的预测误差
方法 轴承1 轴承2 轴承3 Wasim Ahmad的方法 13.41 30.27 19.83 Naipeng Li的方法 5.13 10.24 4.05 本文方法 6.09 15.32 4.32 表 3 进行虚假波动修复的RUL预测误差
方法 轴承1 轴承2 轴承3 未修复 6.09 15.32 4.32 Lei Ren方法 3.51 12.34 3.64 本文方法 2.01 8.24 1.83 -
[1] Thorsen O V, Dalva M. Failure identification and analysis for high-voltage induction motors in the petrochemical industry[J]. IEEE Transactions on Industry Applications, 1999, 35(4):810-818 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0711d6fb9f1d72a7de0f0ac6f7028c2c [2] Qian Y N, Yan R Q, Hu S J. Bearing degradation evaluation using recurrence quantification analysis and Kalman filter[J]. IEEE Transactions on Instrumentation and Measurement, 2014, 63(11):2599-2610 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=22612a8b2ae350049d8fb9f35150fec0 [3] Soualhi A, Razik H, Clerc G, et al. Prognosis of bearing failures using hidden Markov models and the adaptive Neuro-fuzzy inference system[J]. IEEE Transactions on Industrial Electronics, 2014, 61(6):2864-2874 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=a7eb8bdf0341e93a0e620acf49249ae6 [4] Li N P, Lei Y G, Lin J, et al. An improved exponential model for predicting remaining useful life of rolling element bearings[J]. IEEE Transactions on Industrial Electronics, 2015, 62(12):7762-7773 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=91075c7f8f546da778f24024a499e572 [5] Singleton R K, Strangas E G, Aviyente S. Extended Kalman filtering for remaining-useful-life estimation of bearings[J]. IEEE Transactions on Industrial Electronics, 2015, 62(3):1781-1790 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=74b2c3160e08a390ab859ee717e791d4 [6] Wang Y, Peng Y Z, Zi Y Y, et al. A two-stage data-driven-based prognostic approach for bearing degradation problem[J]. IEEE Transactions on Industrial Informatics, 2016, 12(3):924-932 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=25c0e27c1158d4d70d7e76182feab9f4 [7] Liao H T, Zhao W B, Guo H R. Predicting remaining useful life of an individual unit using proportional hazards model and logistic regression model[C]//Annual Reliability and Maintainability Symposium, 2006. Newport Beach, CA, USA: IEEE, 2006: 127-132 [8] Tian Z G, Liao H T. Condition based maintenance optimization for multi-component systems using proportional hazards model[J]. Reliability Engineering & System Safety, 2011, 96(5):581-589 http://cn.bing.com/academic/profile?id=764ff3dc07891241cdc44afef59214e1&encoded=0&v=paper_preview&mkt=zh-cn [9] 董绍江, 王军, 徐向阳, 等.基于多SVM误差加权的轴承剩余寿命预测[J].制造技术与机床, 2017(12):103-106, 111 http://d.old.wanfangdata.com.cn/Periodical/zzjsyjc201712028Dong S J, Wang J, Xu X Y, et al. Rolling bearing residual life prediction based on error weighted multiple improved support vector machine model[J]. Manufacturing Technology & Machine Tool, 2017(12):103-106, 111(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/zzjsyjc201712028 [10] Ren L, Sun Y Q, Wang H, et al. Prediction of bearing remaining useful life with Deep convolution neural network[J]. IEEE Access, 2018, 6:13041-13049 http://cn.bing.com/academic/profile?id=1cf0dd4393ef3613a774cfc788374315&encoded=0&v=paper_preview&mkt=zh-cn [11] 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 http://cn.bing.com/academic/profile?id=b683222080a51992081477ce9ccf580c&encoded=0&v=paper_preview&mkt=zh-cn [12] Ahmad W, Khan S A, Kim J M. A hybrid prognostics technique for rolling element bearings using adaptive predictive models[J]. IEEE Transactions on Industrial Electronics, 2018, 65(2):1577-1584 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=ea574023edc11ddcf65e35d27f195a88 [13] 刘吉彪, 程军圣, 刘燕飞.基于LCD和GMM的滚动轴承寿命预测方法[J].现代制造工程, 2016(7):120-124 http://d.old.wanfangdata.com.cn/Periodical/jxgys201607025Liu J B, Cheng J S, Liu Y F. The life forecasting method for rolling bearing based on LCD and GMM[J]. Modern Manufacturing Engineering, 2016(7):120-124(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jxgys201607025 [14] 欧龙辉, 彭晓燕, 杨宇, 等.GS-ASTFA方法及其在滚动轴承寿命预测中的应用[J].振动与冲击, 2017, 36(11):14-19 http://d.old.wanfangdata.com.cn/Periodical/zdycj201711003Ou L H, Peng X Y, Yang Y, et al. GS-ASTFA method and its application in life prediction of rolling bearings[J]. Journal of Vibration and Shock, 2017, 36(11):14-19(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/zdycj201711003 [15] 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 http://d.old.wanfangdata.com.cn/Periodical/jxgcxb200710026Xi L F, Huang R Q, Li X L, et al. Residual life predictions for ball bearing based on neural networks[J]. Modern Mechanical Engineering, 2007, 43(10):137-143(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jxgcxb200710026 [16] 张鑫, 赵建民, 倪祥龙, 等.基于神经网络和维修窗的轴承维修建模[J].机械强度, 2018, 40(1):45-49 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxqd201801008Zhang X, Zhao J M, Ni X L, et al. Modeling of bearing maintenance based on neural network and maintenance window[J]. Journal of Mechanical Strength, 2018, 40(1):45-49(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxqd201801008 [17] Elwany A H, Gebraeel N Z. Sensor-driven prognostic models for equipment replacement and spare parts inventory[J]. ⅡE Transactions, 2008, 40(7):629-639 http://cn.bing.com/academic/profile?id=0959c8e9ad339cb0b8fdfc7fed720735&encoded=0&v=paper_preview&mkt=zh-cn [18] Gebraeel N. Sensory-updated residual life distributions for components with exponential degradation patterns[J]. IEEE Transactions on Automation Science and Engineering, 2006, 3(4):382-393 http://cn.bing.com/academic/profile?id=b247a0abb828a2c4ee5a0a70b4b45b8f&encoded=0&v=paper_preview&mkt=zh-cn [19] Van Tung Tran, Yang B S. An intelligent condition-based maintenance platform for rotating machinery[J]. Expert Systems with Applications 2012, 39(3):2977-2988 [20] 彭进, 王维庆, 王海云, 等.基于EEMD峭度-相关系数准则的多特征量风电机组轴承故障诊断[J].可再生能源, 2016, 34(10):1481-1490 http://d.old.wanfangdata.com.cn/Periodical/ncny201610010Peng J, Wang W Q, Wang H Y, et al. Fault diagnosis method of wind turbine's bearing based on EEMD kurtosis-correlation coefficients criterion and multiple features[J]. Renewable Energy Resources, 2016, 34(10):1481-1490(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/ncny201610010 [21] 申卯兴, 薛西锋, 张小水.灰色关联分析中分辨系数的选取[J].空军工程大学学报, 2003, 4(1):67-70 http://d.old.wanfangdata.com.cn/Periodical/kjgcdxxb200301019Shen M X, Xue X F, Zhang X S. Determination of discrimination coefficient in grey incidence analysis[J]. Journal of Air Force Engineering University, 2003, 4(1):67-70(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/kjgcdxxb200301019 [22] Wang Y F, Kootsookos P J. Modeling of low shaft speed bearing faults for condition monitoring[J]. Mechanical Systems and Signal Processing, 1998, 12(3):415-426 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=6a3160a398906ace14e39be3a2ed5678 [23] 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(4-5):1066-1090 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=2bd8f1285baca76cc6d25c17bebea775