A new Wasserstein distance- and cumulative sum-dependent health indicator and its application in prediction of remaining useful life of bearing

The safety and reliability of mechanical performance are affected by the condition (health status) of the bearings. A health indicator (HI) with high monotonicity and robustness is a helpful tool to simplify the predictive model and improve prediction accuracy. In this paper, a new health indicator based on the Wasserstein distance (WD) and cumulative sum (CUSUM) is proposed. First, a standard normal signal is simulated as the reference. The second step is to calculate the frequency distribution histogram of the reference signal and that of monitoring signals for the bearing. The next step is to obtain the WD between the frequency distribution histogram of the reference signal and that of the monitoring signal. Finally, the fluctuation of the WD is amplified by applying the CUSUM. The performance of the proposed HI is evaluated by testing three run-to-failure datasets. The results show that the proposed HI has better monotonicity and robustness and can be effectively used to predict the remaining useful life of bearings.

[1]  E. S. Page.  CONTINUOUS INSPECTION SCHEMES , 1954 .

[2]  R. M. Stewart,et al.  Detection of Rolling Element Bearing Damage by Statistical Vibration Analysis , 1978 .

[3]  David Mumford,et al.  Mathematical theories of shape: do they model perception? , 1991, Optics & Photonics.

[4]  Peter J. Bickel,et al.  The Earth Mover's distance is the Mallows distance: some insights from statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[5]  Nagi Gebraeel,et al.  Residual life predictions from vibration-based degradation signals: a neural network approach , 2004, IEEE Transactions on Industrial Electronics.

[6]  Günter Rote,et al.  Matching point sets with respect to the Earth mover's distance , 2005, EuroCG.

[7]  K. Goebel,et al.  Prognostic information fusion for constant load systems , 2005, 2005 7th International Conference on Information Fusion.

[8]  Hai Qiu,et al.  Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics , 2006 .

[9]  Alaa Elwany,et al.  Sensor-driven prognostic models for equipment replacement and spare parts inventory , 2008 .

[10]  K. Goebel,et al.  Metrics for evaluating performance of prognostic techniques , 2008, 2008 International Conference on Prognostics and Health Management.

[11]  Zheng Bao,et al.  Variational Color Image Segmentation via Chromaticity-Brightness Decomposition , 2010, MMM.

[12]  Chao Hu,et al.  Ensemble of data-driven prognostic algorithms for robust prediction of remaining useful life , 2011, 2011 IEEE Conference on Prognostics and Health Management.

[13]  Robert X. Gao,et al.  Prognosis of Defect Propagation Based on Recurrent Neural Networks , 2011, IEEE Transactions on Instrumentation and Measurement.

[14]  P. Maravelakis,et al.  A CUSUM control chart for monitoring the variance when parameters are estimated , 2011 .

[15]  Brigitte Chebel-Morello,et al.  PRONOSTIA : An experimental platform for bearings accelerated degradation tests. , 2012 .

[16]  Theodoros H. Loutas,et al.  Remaining Useful Life Estimation in Rolling Bearings Utilizing Data-Driven Probabilistic E-Support Vectors Regression , 2013, IEEE Transactions on Reliability.

[17]  Gang Yu,et al.  A new statistical modeling and detection method for rolling element bearing faults based on alpha–stable distribution , 2013 .

[18]  Noureddine Zerhouni,et al.  Data-driven prognostics based on health indicator construction: Application to PRONOSTIA's data , 2013, 2013 European Control Conference (ECC).

[19]  Ruqiang Yan,et al.  Bearing Degradation Evaluation Using Recurrence Quantification Analysis and Kalman Filter , 2014, IEEE Transactions on Instrumentation and Measurement.

[20]  E. Jantunen,et al.  A descriptive model of wear evolution in rolling bearings , 2014 .

[21]  M. Lewis,et al.  A generalized residual technique for analysing complex movement models using earth mover's distance , 2014, 1402.1805.

[22]  Christoph Schnörr,et al.  Globally Optimal Joint Image Segmentation and Shape Matching Based on Wasserstein Modes , 2014, Journal of Mathematical Imaging and Vision.

[23]  Selin Aviyente,et al.  Extended Kalman Filtering for Remaining-Useful-Life Estimation of Bearings , 2015, IEEE Transactions on Industrial Electronics.

[24]  Youxian Sun,et al.  Remaining Useful Life Prediction for a Nonlinear Heterogeneous Wiener Process Model With an Adaptive Drift , 2015, IEEE Transactions on Reliability.

[25]  Brigitte Chebel-Morello,et al.  Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network , 2015 .

[26]  Yaguo Lei,et al.  An Improved Exponential Model for Predicting Remaining Useful Life of Rolling Element Bearings , 2015, IEEE Transactions on Industrial Electronics.

[27]  Brigitte Chebel-Morello,et al.  Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals , 2015 .

[28]  Noureddine Zerhouni,et al.  Enabling Health Monitoring Approach Based on Vibration Data for Accurate Prognostics , 2015, IEEE Transactions on Industrial Electronics.

[29]  Myeongsu Kang,et al.  A Massively Parallel Approach to Real-Time Bearing Fault Detection Using Sub-Band Analysis on an FPGA-Based Multicore System , 2016, IEEE Transactions on Industrial Electronics.

[30]  Yaguo Lei,et al.  A New Method Based on Stochastic Process Models for Machine Remaining Useful Life Prediction , 2016, IEEE Transactions on Instrumentation and Measurement.

[31]  Yaguo Lei,et al.  A Model-Based Method for Remaining Useful Life Prediction of Machinery , 2016, IEEE Transactions on Reliability.

[32]  Bin Zhang,et al.  Degradation Feature Selection for Remaining Useful Life Prediction of Rolling Element Bearings , 2016, Qual. Reliab. Eng. Int..

[33]  Bing Wang,et al.  The application of a general mathematical morphological particle as a novel indicator for the performance degradation assessment of a bearing , 2017 .

[34]  Wenhai Wang,et al.  Remaining useful life prediction for an adaptive skew-Wiener process model , 2017 .

[35]  Hesam Addin Arghand,et al.  Estimation of Remaining Useful Life of Rolling Element Bearings Using Wavelet Packet Decomposition and Artificial Neural Network , 2018, Iranian Journal of Science and Technology, Transactions of Electrical Engineering.

[36]  Xuanqin Mou,et al.  Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss , 2017, IEEE Transactions on Medical Imaging.

[37]  Lin Li,et al.  Route Planning Based on Genetic Algorithm , 2018 .

[38]  A. Haq,et al.  Improved CUSUM charts for monitoring process mean , 2018 .

[39]  Jong-Myon Kim,et al.  A Hybrid Prognostics Technique for Rolling Element Bearings Using Adaptive Predictive Models , 2018, IEEE Transactions on Industrial Electronics.

[40]  Equivalence Testing of Complex Particle Size Distribution Profiles Based on Earth Mover’s Distance , 2018, The AAPS Journal.

[41]  Yaguo Lei,et al.  Machinery health prognostics: A systematic review from data acquisition to RUL prediction , 2018 .

[42]  Lei Ren,et al.  Bearing remaining useful life prediction based on deep autoencoder and deep neural networks , 2018, Journal of Manufacturing Systems.

[43]  Jong-Myon Kim,et al.  A reliable technique for remaining useful life estimation of rolling element bearings using dynamic regression models , 2018, Reliab. Eng. Syst. Saf..

[44]  Weiwen Peng,et al.  Estimation of Bearing Remaining Useful Life Based on Multiscale Convolutional Neural Network , 2019, IEEE Transactions on Industrial Electronics.

[45]  H. Kirkegaard,et al.  Crowding in the emergency department in the absence of boarding – a transition regression model to predict departures and waiting time , 2019, BMC Medical Research Methodology.