Abstract
Prognosis and Health Management (PHM) refer specifically to the prediction phase of the future behavior of the system or subsystem, including the remaining useful life (RUL). It is helpful to early detect incipient failures in many domains as aircraft, nuclear reactor, turbine gas, etc. In this paper we propose a new approach based on the implementation of data-driven methods for fault prognosis. Such methods require the availability of data describing the degradation process; when there is a lack of data, it is difficult to predict the states using deep models, which require a large amount of training data. In this paper, we propose to use a simple data augmentation strategy to solve the problem of data scarcity in prediction of RUL provided through the use of a long-short term memory (LSTM), which is a type of recurrent neural network. The results of our experiments demonstrate that using a simple data augmentation strategy can increase RUL prediction performance by using LSTM technics. We analyze our approach using data from NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS).
REFERENCES
Li, L.-L., Zhang, X.-B., Tseng, M.-L., and Zhou, Ya-T., Optimal scale Gaussian process regression model in insulated gate bipolar transistor remaining life prediction, Appl. Soft Comput., 2019, vol. 78, pp. 261–273. https://doi.org/10.1016/j.asoc.2019.02.035
Wang, Yu., Deng, Ch., Wu, Ju., Wang, Yi., and Xiong, Ya., A corrective maintenance scheme for engineering equipment, Eng. Failure Anal., 2014, vol. 36, p. 269–283. https://doi.org/10.1016/j.engfailanal.2013.10.006
Liao, L. and Köttig, F., A hybrid framework combining data-driven and model-based methods for system remaining useful life prediction, Appl. Soft Comput., 2016, vol. 44, pp. 191–199. https://doi.org/10.1016/j.asoc.2016.03.013
Ramasso, E., Rombaut, M., and Zerhouni, A., Joint prediction of continuous and discrete states in time-series based on belief functions, IEEE Trans. Cybern., 2013, vol. 43, no. 1, pp. 37–50. https://doi.org/10.1109/TSMCB.2012.2198882
Lei, Y., Li, N., Guo, L., Li, N., Yan, T., and Lin, J., Machinery health prognostics: A systematic review from data acquisition to RUL prediction, Mech. Syst. Signal Process., 2018, vol. 104, pp. 799–834. https://doi.org/10.1016/j.ymssp.2017.11.016
Liu, J. and Zio, E., Prediction of peak values in time series data for prognostics of critical components in nuclear power plants, IFAC-PapersOnLine, 2016, vol. 49, no. 28, pp. 174–178. https://doi.org/10.1016/j.ifacol.2016.11.030
Hornik, K., Approximation capabilities of multilayer feedforward networks, Neural Networks, 1991, vol. 4, no. 2, pp. 251–257. https://doi.org/10.1016/0893-6080(91)90009-T
Peel, L., Data driven prognostics using a Kalman filter ensemble of neural network models, 2008 Int. Conf. on Prognostics and Health Management, Denver, Colo., 2008, IEEE, 2008, pp. 1–6. https://doi.org/10.1109/PHM.2008.4711423
Tamilselvan, P. and Wang, P., Failure diagnosis using deep belief learning based health state classification, Reliab. Eng. Syst. Saf., 2013, vol. 115, pp. 124–135. https://doi.org/10.1016/j.ress.2013.02.022
Zhang, X., Xiao, L., and Kang, J., Degradation prediction model based on a neural network with dynamic windows, Sensors, 2015, vol. 15, no. 3, pp. 6996–7015. https://doi.org/10.3390/s150306996
Zhao, Z., Liang, B., Wang, X., and Lu, W., Remaining useful life prediction of aircraft engine based on degradation pattern learning, Reliab. Eng. Syst. Saf., 2017, vol. 164, no. 457, pp. 74–83. https://doi.org/10.1016/j.ress.2017.02.007
Ompusunggu, A.P., Papy, J.M., and Vandenplas, S., Kalman-filtering-based prognostics for automatic transmission clutches, IEEE/ASME Trans. Mechatronics, 2016, vol. 21, no. 1, pp. 419–430. https://doi.org/10.1109/TMECH.2015.2440331
Li, X., Ding, Q., and Sun, J.Q., Remaining useful life estimation in prognostics using deep convolution neural networks, Reliab. Eng. Syst. Saf., 2018, vol. 172, pp. 1–11. https://doi.org/10.1016/j.ress.2017.11.021
Khelif, R., Chebel-Morello, B., Malinowski, S., Laajili, E., Fnaiech, F., and Zerhouni, N., Direct remaining useful life estimation based on support vector regression, IEEE Trans. Ind. Electron., 2017, vol. 64, no. 3, pp. 2276–2285. https://doi.org/10.1109/TIE.2016.2623260
Wu, J., Xu, J., and Huang, X., An indirect prediction method of remaining life based on glowworm swarm optimization and extreme learning machine for lithium battery, 36th Chinese Control Conf. (CCC), Dalian, China, 2017, IEEE, 2017, pp. 7259–7264. https://doi.org/10.23919/ChiCC.2017.8028502
Morando, S., Jemei, S., Gouriveau, R., Zerhouni, N., and Hissel, D., Fuel cells remaining useful lifetime forecasting using echo state network, 2014 IEEE Vehicle Power and Propulsion Conf. (VPPC), Coimbra, Portugal, 2014, IEEE, 2014, pp. 1–6. https://doi.org/10.1109/VPPC.2014.7007074
H. Liu, J. Zhou, Y. Zheng, W. Jiang, and Y. Zhang, Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders, ISA Trans., 2018, vol. 77, pp. 167–178. https://doi.org/10.1016/j.isatra.2018.04.005
R. Chandra, Competition and collaboration in cooperative coevolution of elman recurrent neural networks for time-series prediction, IEEE Trans. Neural Networks Learn. Syst., 2015, vol. 26, no. 12, pp. 3123–3136. https://doi.org/10.1109/TNNLS.2015.2404823
Malhi, A. and Gao, R.X., Recurrent neural networks for long-term prediction in machine condition monitoring, Proc. 21st IEEE Instrumentation Measurement Technology Conf., Como, Italy, 2004, IEEE, 2004, pp. 2048–2053. https://doi.org/10.1109/imtc.2004.1351492
Lukoševičius, M. and Jaeger, H., Reservoir computing approaches to recurrent neural network training, Comput. Sci. Rev., 2009, vol. 3, no. 3, pp. 127–149. https://doi.org/10.1016/j.cosrev.2009.03.005
Wu, Y., Yuan, M., Dong, S., Lin, L., and Liu, Y., Remaining useful life estimation of engineered systems using vanilla LSTM neural networks, Neurocomputing, 2018, vol. 275, pp. 167–179. https://doi.org/10.1016/j.neucom.2017.05.063
Likhitha, D.L. and Nagaraja, R., Prediction of remaining useful life of an aircraft engine using LSTM network, 2019, vol. 9, no. 6, pp. 329–334.
Li, H., Huang, J., Yang, X., Luo, J., Zhang, L., and Pang, Y., Fault diagnosis for rotating machinery using multiscale permutation entropy and convolutional neural networks, Entropy, 2020, vol. 22, no. 8, pp. 101–110. https://doi.org/10.3390/E22080851
Zheng, Sh., Ristovski, K., Farahat, A., and Gupta, Ch., Long short-term memory network for remaining useful life estimation, 2017 IEEE Int. Conf. on Prognonstics and Health Management (ICPHM), Dallas, Texas, 2017, IEEE, 2017, pp. 88–95. https://doi.org/10.1109/ICPHM.2017.7998311
Wu, Ju., Hu, K., Cheng, Yi., Zhu, H., Shao, X., and Wang, Yu., Data-driven remaining useful life prediction via multiple sensor signals and deep long short-term memory neural network, ISA Trans., 2020, vol. 97, pp. 241–250. https://doi.org/10.1016/j.isatra.2019.07.004
Xia, M., Zheng, X., Imran, M., and Shoaib, M., Data-driven prognosis method using hybrid deep recurrent neural network, Appl. Soft Comput., 2020, vol. 93, p. 106351. https://doi.org/10.1016/j.asoc.2020.106351
Hochreiter, S., The vanishing gradient problem during learning recurrent neural nets and problem solutions, Int. J. Uncertainty, Fuzziness Knowl.-Based Syst., 1998, vol. 6, no. 2, pp. 107–116. https://doi.org/10.1142/S0218488598000094
Hochreiter, S. and Schmidhuber, J., Long short-term memory, Neural Comput., 1997, vol. 9, no. 8, pp. 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Gers, F.A., Schmidhuber, J., and Cummins, F., Learning to forget: Continual prediction with LSTM, Neural Comput., 2000, vol. 12, no. 10, pp. 2451–2471. https://doi.org/10.1162/089976600300015015
Tuncel, K.S. and Baydogan, M.G., Autoregressive forests for multivariate time series modeling, Pattern Recognit., 2018, vol. 73, pp. 202–215. https://doi.org/10.1016/j.patcog.2017.08.016
Saxena, A., Goebel, K., Simon, D., and Eklund, N., Damage propagation modeling for aircraft engine run-to-failure simulation, 2008 Int. Conf. on Prognostics and Health Management, Denver, Colo., 2008, IEEE, 2008, pp. 1–9. https://doi.org/10.1109/PHM.2008.4711414
Fawzi, A., Samulowitz, H., Turaga, D., and Frossard, P., Adaptive data augmentation for image classification, 2016 IEEE Int. Conf. on Image Processing (ICIP), Phoenix, Ariz., 2016, IEEE, 2016, pp. 3688–3692. https://doi.org/10.1109/ICIP.2016.7533048
Kingma, D.P. and Ba, J.L., Adam: A method for stochastic optimization, 3rd Int. Conf. Learning Representation, San Diego, Calif., 2015, pp. 1–15.
Heimes, F.O., Recurrent neural networks for remaining useful life estimation, 2008 Int. Conf. on Prognostics and Health Management, Denver, Colo., 2008, IEEE, 2008, pp. 1–6. https://doi.org/10.1109/PHM.2008.4711422
Yuan, M., Wu, Y., and Lin, L., Fault diagnosis and remaining useful life estimation of aero engine using LSTM neural network, AUS 2016—2016 IEEE/CSAA Int. Conf. on Aircraft Utility Systems (AUS), Beijing, 2016, IEEE, 2016, pp. 135–140. https://doi.org/10.1109/AUS.2016.7748035
Sayah, M., Guebli, D., Noureddine, Z., and Al Masry, Z., Deep LSTM enhancement for RUL prediction using Gaussian mixture models, Autom. Control Comput. Sci., 2021, vol. 55, no. 1, pp. 15–25. https://doi.org/10.3103/S014641162
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors declare that they have no conflicts of interest.
About this article
Cite this article
Drici Djalel, Yahia, K., Mohamed, T.M. et al. A New Approach for Remaining Useful Life Estimation Using Deep Learning. Aut. Control Comp. Sci. 57, 93–102 (2023). https://doi.org/10.3103/S0146411623010030
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411623010030