Fault feature extraction is the key of bearings’ health state description, however, features extracted with currently common methods may have higher dimensions or they are lack of information and unable to reflect bearings’ health state monotonously, and the predicted results cannot effectively reveal the degradation trend of bearings.Here, the cumulative sum and Mahalanobis distance (MD-CUSUM) was adopted to realize feature dimension reduction, obtain the health index (HI), and reflect monotonously health state of bearings with lower dimensions.Furthermore, a time delayed support vector regression (TD-SVR) model was constructed to improve the prediction accuracy for health state of rolling bearings.The advantages and disadvantages of MD-CUSUM and those of the isometric feature mapping were compared through test data analysis.The results showed that the combination of MD-CUSUM and TD-SVR has a better effect on predicting health state of bearings.
夏均忠，吕麒鹏，陈成法，刘鲲鹏，郑建波. 基于MD-CUSUM和TD-SVR的滚动轴承健康状态预测[J]. 振动与冲击, 2018, 37(19): 83-88.
XIA Junzhong, L Qipeng, CHEN Chengfa, LIU Kunpeng, ZHENG Jianbo. Health state prediction of rolling bearings based on MD-CUSUM and TD-SVR#br#. JOURNAL OF VIBRATION AND SHOCK, 2018, 37(19): 83-88.
[1] Sutrisno E, Oh H, Vasan A S S, et al. Estimation of remaining useful life of ball bearings using data driven methodologies[C]. Prognoics and Health Management IEEE, 2012: 1-7.
[2] Harmouche J, Delpha C, Diallo D. Improved fault diagnosis of ball bearings based on the global spectrum of vibration signals[J]. IEEE Transactions on Energy Conversion, 2015, 30(1): 376–383.
[3] Elbouchikhia E, Choqueuseb V, Benbouzid M. Induction machine bearing faults detection based on a multi-dimensional MUSIC algorithm and maximum likelihood estimation[J]. ISA Transactions, 2016, 63:413-424.
[4] Sakthivel N R, Nair B B, Elangovan M, et al. Comparison of dimensionality reduction techniques for the fault diagnosis of mono block centrifugal pump using vibration signals[J]. Engineering Science and Technology An International Journal, 2014, 17(1):30-38.
[5] Akhand Rai, Upadhyay S H. The use of MD-CUMSUM and NARX neural network for anticipating the remaining useful life of bearings[J]. Measurement, 2017, 111: 1-27.
[6] Tran V T, Hong T P, Yang B S, et al. Machine Performance Degradation assessment and remaining useful life prediction using proportional hazard model and support vector machine[J]. Mechanical Systems and Signal Processing, 2012, 32(4): 320-330.
[7] Nieto P J G, García-Gonzalo E, Lasheras F S, et al. Hybrid PSO-SVM-based method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability[J]. Reliability Engineering and System Safety, 2015, 138: 219-231.
[8] Liu ZH L, Zuo M J, Qin Y. Remaining useful life prediction of rolling element bearings based on health state assessment[J]. Proceedings of the Institution of Mechanical Engineers Part C Journal Mechanical Engineering Science 1989-1996(vols 203-210), 2015, 230(2): 314-330.
[9] Saidi L, Ali J B, Bechhoefer E, et al. Wind turbine high-speed shaft bearings health prognosis through a spectral Kurtosis-derived indices and SVR[J]. Applied Acoustics, 2017, 120: 1-8.
[10] 阴盼强, 路东明, 袁渊. 基于马氏距离的改进非局部均值图像去噪算法[J]. 计算机辅助设计与图形学学报, 2016, 28(3): 404-410.
Yin Pan-qiang, Lu Dong-ming, Yuan Yuan. An Improved Non-local Means Image De-noising Algorithm Using Mahalanobis Distance[J]. Journal of Computer-Aided Design and Computer Graphics, 2016, 28(3): 404-410.
[11] Gustavo Vedana, Filipe G Cardoso, Alexandre S Marcon, et al. Cumulative sum analysis score and phacoemulsification competency learning curve[J]. International Journal of Ophthalmology, 2017, 10(07): 1088-1093.
[12] Benkedjouh T, Medjaher K, Zerhouni N, et al. Remaining useful life estimation based on nonlinear feature reduction and support vector regression[J]. Engineering Applications of Artificial Intelligence, 2013, 26(7): 1751-1760.
[13] FEMTO-ST Institute Website[EB/OL].http://www.femto-st.fr/, 2010-12-01.
[14] Nectoux P, Gouriveau R, Medjaher K, et al. PRONOSTIA: An experimental platform for bearings accelerated degradation tests[C]. IEEE International Conference on Prognostics and Health Management, 2012: 1-8.
[15] Cerrada M, Sánchez R, Li C, et al. A review on data-driven fault severity assessment in rolling bearings[J]. Mechanical Systems and Signal Processing, 2018, 99: 169-196.
[16] 张全德, 陈果, 林桐, 等. 基于自组织神经网络的滚动轴承状态评估方法[J]. 中国机械工程,2017,28(05):550-558.
Zhang Quan-de, Chen Guo, Lin Tong, et al. Condition assessment for bearing based on SOM[J]. China Mechanical Engineering, 2017, 28(5):550-558.
