A Time-Series Data Generation Method to Predict Remaining Useful Life

Accurate predictions of remaining useful life (RUL) of equipment using machine learning (ML) or deep learning (DL) models that collect data until the equipment fails are crucial for maintenance scheduling. Because the data are unavailable until the equipment fails, collecting sufficient data to train a model without overfitting can be challenging. Here, we propose a method of generating time-series data for RUL models to resolve the problems posed by insufficient data. The proposed method converts every training time series into a sequence of alphabetical strings by symbolic aggregate approximation and identifies occurrence patterns in the converted sequences. The method then generates a new sequence and inversely transforms it to a new time series. Experiments with various RUL prediction datasets and ML/DL models verified that the proposed data-generation model can help avoid overfitting in RUL prediction model.

[1]  A. Notaristefano,et al.  Data size reduction with symbolic aggregate approximation for electrical load pattern grouping , 2013 .

[2]  Xianzhi Zhang,et al.  In-process tool condition forecasting based on a deep learning method , 2020, Robotics Comput. Integr. Manuf..

[3]  M. Pecht,et al.  Estimation of remaining useful life of ball bearings using data driven methodologies , 2012, 2012 IEEE Conference on Prognostics and Health Management.

[4]  Theodoros Loutas,et al.  Rolling element bearings diagnostics using the Symbolic Aggregate approXimation , 2015 .

[5]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[6]  Rafael Gouriveau,et al.  Remaining Useful Life Estimation by Classification of Predictions Based on a Neuro-Fuzzy System and Theory of Belief Functions , 2014, IEEE Transactions on Reliability.

[7]  Jae-Yoon Jung,et al.  SAX-ARM: Deviant event pattern discovery from multivariate time series using symbolic aggregate approximation and association rule mining , 2020, Expert Syst. Appl..

[8]  Biqing Huang,et al.  Remaining useful life estimation via transformer encoder enhanced by a gated convolutional unit , 2021, Journal of Intelligent Manufacturing.

[9]  Shahrul Kamaruddin,et al.  An overview of time-based and condition-based maintenance in industrial application , 2012, Comput. Ind. Eng..

[10]  Jiuyong Li,et al.  An improvement of symbolic aggregate approximation distance measure for time series , 2014, Neurocomputing.

[11]  Rajkumar Roy,et al.  Overview of Remaining Useful Life Prediction Techniques in Through-life Engineering Services☆ , 2014 .

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

[13]  Chetan Gupta,et al.  Long Short-Term Memory Network for Remaining Useful Life estimation , 2017, 2017 IEEE International Conference on Prognostics and Health Management (ICPHM).

[14]  Yu Guo,et al.  A Two-Stage Transfer Learning-Based Deep Learning Approach for Production Progress Prediction in IoT-Enabled Manufacturing , 2019, IEEE Internet of Things Journal.

[15]  Mohamed Benbouzid,et al.  Wind turbine high-speed shaft bearings health prognosis through a spectral Kurtosis-derived indices and SVR , 2017 .

[16]  Shichang Du,et al.  A Hybrid Prognostics Deep Learning Model for Remaining Useful Life Prediction , 2020, Electronics.

[17]  Enrique López Droguett,et al.  A novel deep capsule neural network for remaining useful life estimation , 2020, Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability.

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

[19]  Eamonn J. Keogh,et al.  A symbolic representation of time series, with implications for streaming algorithms , 2003, DMKD '03.

[20]  Yun Zhang,et al.  Joint model for residual life estimation based on Long-Short Term Memory network , 2020, Neurocomputing.

[21]  Linxia Liao,et al.  Review of Hybrid Prognostics Approaches for Remaining Useful Life Prediction of Engineered Systems, and an Application to Battery Life Prediction , 2014, IEEE Transactions on Reliability.

[22]  Tangbin Xia,et al.  Recent advances in prognostics and health management for advanced manufacturing paradigms , 2018, Reliab. Eng. Syst. Saf..

[23]  David He,et al.  Using Deep Learning-Based Approach to Predict Remaining Useful Life of Rotating Components , 2018, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[24]  Nam H. Kim,et al.  Prediction of remaining useful life under different conditions using accelerated life testing data , 2018, Journal of Mechanical Science and Technology.

[25]  Donghua Zhou,et al.  Remaining useful life estimation - A review on the statistical data driven approaches , 2011, Eur. J. Oper. Res..

[26]  Bin Zhang,et al.  Bearing performance degradation assessment using long short-term memory recurrent network , 2019, Comput. Ind..