Skip to main content
SpringerLink
Log in

Computational adaptive multivariable degradation model for improving the remaining useful life prediction in industrial systems

  • Published:
Computational and Applied Mathematics Aims and scope Submit manuscript

Abstract

Accuracy in predicting the remaining useful life (RUL) of industrial systems is crucial for maintenance tasks. Obtaining models that improve the RUL prediction and that are increasingly adjusting to the reality of the process is an open research problem. This paper proposes an adaptive method for predicting RUL based on modeling the behavior of multiple variables during degradation. The information from each model is weighted to predict the RUL of the system, improving the prediction results significantly. The proposed method is applied to NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset benchmark, showing promising results. Finally, a comparison is made with current prediction techniques present in the scientific literature where it is evidenced that the proposed model has better results.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Similar content being viewed by others

Abbreviations

AE:

Autoencoder

BLSTM:

Bidirectional long short-term memory neural network

C-MAPSS:

Commercial modular aero-propulsion system simulation

DNN:

Deep neural network

EOL:

End of life

RUL:

Remaining useful life

SVDD:

Support vector data description

\(\alpha _{i,t}\) :

Weight of RUL prediction error of system i at time t

\(\mathrm{EOL}_{j,i,t}^*\) :

Predicted EOL with variable j of system i at time t

\(\mathrm{ET}_j\) :

EOL threshold of variable j

\(f_j \) :

Degradation model of variable j

N :

Number of systems

\(\mathbf {p}\) :

vector of parameters of f

\(p_k\) :

parameters k of f

\(\mathbf {p}_L, \mathbf {p}_U\) :

Lower and upper bounds of parameters \( \mathbf {p} \)

\(R_s\) :

Constrained region of the parameter space

RMSE:

Root mean squared error

\(\mathrm{RUL}_{i,t}\) :

True RUL of system i at time t

\(\mathrm{RUL}_{j,i,t}^*\) :

Predicted RUL with variable j of system i at time t

\(\mathrm{RUL}_{i,t}^*\) :

Predicted RUL of system i at time t

\( t_d \) :

Detection time of the degradation process

T :

Number of observations

TWEB:

Timeliness weighted error bias

V :

Number of variables

\(w_j\) :

Weight of variable j

\(y_j\) :

variable j

\( \zeta \) :

Late prediction based penalization function

References

  • Ali JB, Saidi L, Harrath S, Bechhoefer E, Benbouzid M (2018) Online automatic diagnosis of wind turbine bearings progressive degradation under real experimental conditions based on unsupervised machine learning. Appl Acoust 132:167–181

    Article  Google Scholar 

  • Barraza-Barraza D, Tercero-Gómez VG, Beruvides MG, Limón-Robles J (2017) An adaptive arx model to estimate the rul of aluminum plates based on its crack growth. Mech Syst Signal Process 82:519–536

    Article  Google Scholar 

  • Branch MA, Coleman TF, Li Y (1999) A subspace, interior and conjugate gradient method for large-scale bound-constrained minimization problems. SIAM J Sci Comput 21(1):1–23

    Article  MathSciNet  Google Scholar 

  • Bregon A, Daigle MJ (2019) Fundamentals of prognostics. In: Fault diagnosis of dynamic systems, pp. 409–432. Springer

  • Cheng H, Kong X, Chen G, Wang Q, Wang R (2021) Transferable convolutional neural network based remaining useful life prediction of bearing under multiple failure behaviors. Measurement 168:108286

    Article  Google Scholar 

  • Coble JB (2010) Merging data sources to predict remaining useful life: an automated method to identify prognostic parameters. Ph.D. thesis, University of Tennessee

  • Coble J, Hines JW (2009) Identifying optimal prognostic parameters from data: a genetic algorithms approach. In: Annual conference of the prognostics and health management society, vol. 27

  • Coleman TF, Li Y (1996) An interior point trust region approach for nonlinear minimization subject to bounds. SIAM J Optim 6(2):418–445

    Article  MathSciNet  Google Scholar 

  • Coleman TF, Li Y (1996) A reflective newton method for minimizing a quadratic function subject to bounds on some of the variables. SIAM J Optim 6(4):1040–1058

    Article  MathSciNet  Google Scholar 

  • Dong Q, Cui L, Si S (2020) Reliability and availability analysis of stochastic degradation systems based on bivariate wiener processes. Appl Math Model 79:414–433

    Article  MathSciNet  Google Scholar 

  • Ellefsen AL, Bjørlykhaug E, Æsøy V, Ushakov S, Zhang H (2019) Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture. Reliab Eng Syst Saf 183:240–251

    Article  Google Scholar 

  • Hou L, Xu X, Yao Y, Wang D, Tong J (2021) Improved exponential weighted moving average based measurement noise estimation for strapdown inertial navigation system/doppler velocity log integrated system. J Navigat 74(2):467–487

    Article  Google Scholar 

  • Ibrahim M, Steiner NY, Jemei S, Hissel D (2016) Wavelet-based approach for online fuel cell remaining useful lifetime prediction. IEEE Trans Ind Electron 63(8):5057–5068

    Google Scholar 

  • ISO 13381-1:2015 (2015) Condition monitoring and diagnostics of machines—Prognostics—Part 1: General Guidelines

  • Javed K, Gouriveau R, Zerhouni N (2017) State of the art and taxonomy of prognostics approaches, trends of prognostics applications and open issues towards maturity at different technology readiness levels. Mech Syst Signal Process 94:214–236

    Article  Google Scholar 

  • Kim NH, An D, Choi JH (2016) Prognostics and health management of engineering systems: an introduction. Springer

  • Le Son K, Fouladirad M, Barros A, Levrat E, Iung B (2013) Remaining useful life estimation based on stochastic deterioration models: a comparative study. Reliab Eng Syst Saf 112:165–175

    Article  Google Scholar 

  • Lei Y, Li N, Gontarz S, Lin J, Radkowski S, Dybala J (2016) A model-based method for remaining useful life prediction of machinery. IEEE Trans Reliab 65(3):1314–1326

    Article  Google Scholar 

  • Lei Y, Li N, Guo L, Li N, Yan T, Lin J (2018) Machinery health prognostics: a systematic review from data acquisition to rul prediction. Mech Syst Signal Process 104:799–834

    Article  Google Scholar 

  • Li Q, Gao Z, Tang D, Li B (2016) Remaining useful life estimation for deteriorating systems with time-varying operational conditions and condition-specific failure zones. Chin J Aeronaut 29(3):662–674

    Article  Google Scholar 

  • Li X, Ding Q, Sun JQ (2018) Remaining useful life estimation in prognostics using deep convolution neural networks. Reliab Eng Syst Saf 172:1–11

    Article  Google Scholar 

  • Li H, Zhao W, Zhang Y, Zio E (2020) Remaining useful life prediction using multi-scale deep convolution neural network. Appl Soft Comput 89:106–113

    Google Scholar 

  • Liao L, Jin W, Pavel R (2016) Enhanced restricted boltzmann machine with prognosability regularization for prognostics and health assessment. IEEE Trans Ind Electron 63(11):7076–7083

    Article  Google Scholar 

  • Liu K, Gebraeel NZ, Shi J (2013) A data-level fusion model for developing composite health indices for degradation modeling and prognostic analysis. IEEE Trans Automat Sci Eng 10(3):652–664

    Article  Google Scholar 

  • Niu G (2017) Data-driven technology for engineering systems health management. Springer, Berlin

    Book  Google Scholar 

  • Saidi L, Ali JB, Bechhoefer E, Benbouzid M (2017) Wind turbine high-speed shaft bearings health prognosis through a spectral kurtosis-derived indices and svr. Appl Acoust 120:1–8

    Article  Google Scholar 

  • Saxena A, Goebel K, Simon D, Eklund N (2008) Damage propagation modeling for aircraft engine run-to-failure simulation. In: 2008 International Conference on Prognostics and Health Management, pp. 1–9. IEEE

  • Song C, Liu K (2018) Statistical degradation modeling and prognostics of multiple sensor signals via data fusion: a composite health index approach. IISE Trans 50(10):853–867

    Article  Google Scholar 

  • Song Y, Shi G, Chen L, Huang X, Xia T (2018) Remaining useful life prediction of turbofan engine using hybrid model based on autoencoder and bidirectional long short-term memory. J Shang Jiatong Univ. (Sci.) 23(1):85–94

    Article  Google Scholar 

  • Tax DM, Dui RP (2004) Support vector data description. Mach Learn 54(1):45–66

    Article  Google Scholar 

  • Wang D, Tsui KL (2017) Statistical modeling of bearing degradation signals. IEEE Trans Reliab 66(4):1331–1344

    Article  Google Scholar 

  • Wang G, Xiang J (2021) Remaining useful life prediction of rolling bearings based on exponential model optimized by gradient method. Measurement 176:109161

    Article  Google Scholar 

  • Wang T, Yu J, Siegel D, Lee J (2008) A similarity-based prognostics approach for remaining useful life estimation of engineered systems. In: 2008 international conference on prognostics and health management, pp. 1–6. IEEE

  • Yan M, Wang X, Wang B, Chang M, Muhammad I (2020) Bearing remaining useful life prediction using support vector machine and hybrid degradation tracking model. ISA Trans 98:471–482

    Article  Google Scholar 

  • Zeng Z, Di Maio F, Zio E, Kang R (2017) A hierarchical decision-making framework for the assessment of the prediction capability of prognostic methods. Proceedings of the Institution of Mechanical Engineers Part 0. Journal of Risk and Reliability 231(1): 36–52

  • Zhang H, Chen M, Xi X, Zhou D (2017) Remaining useful life prediction for degradation processes with long-range dependence. IEEE Trans Reliab 66(4):1368–1379

    Article  Google Scholar 

  • Zhu J, Chen N, Peng W (2018) Estimation of bearing remaining useful life based on multiscale convolutional neural network. IEEE Trans Ind Electron 66(4):3208–3216

    Article  Google Scholar 

Download references

Acknowledgements

The authors Adriana Villalón-Falcón, Alberto Prieto-Moreno y Orestes Llanes-Santiago acknowledge the financial support provided by the National Research Program Automatica, Robotics and Artificial Intelligence (ARIA) of the Ministry of Science, Technology and Environment (CITMA) from Cuba and Universidad Tecnológica de La Habana José Antonio Echeverría, CUJAE.

Author information

Authors and Affiliations

  1. Universidad Tecnológica de La Habana José Antonio Echeverría, CUJAE, Calle 114 No. 11901, Marianao, La Habana, Cuba

    Adriana Villalón-Falcón, Alberto Prieto-Moreno & Orestes Llanes-Santiago

  2. Vanderbit University, Nashville, TN, 37209, USA

    Marcos Quiñones-Grueiro

Authors
  1. Adriana Villalón-Falcón
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Alberto Prieto-Moreno
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Marcos Quiñones-Grueiro
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Orestes Llanes-Santiago
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Orestes Llanes-Santiago.

Additional information

Communicated by Antonio José Silva Neto.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Villalón-Falcón, A., Prieto-Moreno, A., Quiñones-Grueiro, M. et al. Computational adaptive multivariable degradation model for improving the remaining useful life prediction in industrial systems. Comp. Appl. Math. 41, 48 (2022). https://doi.org/10.1007/s40314-021-01752-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s40314-021-01752-8

Keywords

Mathematics Subject Classification

Search

Navigation