A Prototype Similarity-based System for Remaining Useful Life Estimation for Future Industry by Singular Spectrum Analysis-Long Short Term Memory Neural Networks Algorithm


  • Prakit Intachai The Electrical Engineering Graduate Program, Faculty of Engineering, Mahanakorn University of Technology,140 Cheumsamphan Rd., Nong-chok Bangkok 10530, Thailand https://orcid.org/0000-0002-4425-3507
  • Peerapol Yuvapoositanon Mahanakorn Institute of Innovation, Faculty of Engineering, Mahanakorn University of Technology,140 Cheumsamphan Rd., Nong-chok Bangkok 10530, Thailand https://orcid.org/0000-0002-3140-6471




Remaining useful life, Singular spectrum analysis, Long-short term memory, Optimal window length


In this paper, we propose a prototype similarity-based approach of estimating the remaining useful life (RUL) of turbofan engine data using the singular spectrum analysis and the long-short term memory (SSA-LSTM) neural networks algorithm. The algorithm consists of two steps. First, the optimal window length of the trajectory matrix of the dataset is empirically determined from a prototype dataset. Second, the estimation of the RUL of the target datasets is performed using the window length parameter obtained from the first step. The validity of the proposed algorithm is verified by testing with 200 turbofan engine datasets. The results are shown to have a significant improvement in the performance of the RUL estimation over the existing LSTM algorithm.


Download data is not yet available.

Author Biographies

Prakit Intachai, The Electrical Engineering Graduate Program, Faculty of Engineering, Mahanakorn University of Technology,140 Cheumsamphan Rd., Nong-chok Bangkok 10530, Thailand

Prakit Intachai received his bachelor’s and master’s degrees in telecommunication engineering in 2010 and 2012, respectively. Currently, he is pursuing a doctor of engineering degree in electronic engineering with signal processing as the subject of study at the Mahanakorn University of Technology, Bangkok, Thailand. His main research interests include technical analysis and synthesis of time series data and estimation of remaining useful life in industrial systems.

Peerapol Yuvapoositanon, Mahanakorn Institute of Innovation, Faculty of Engineering, Mahanakorn University of Technology,140 Cheumsamphan Rd., Nong-chok Bangkok 10530, Thailand

Peerapol Yuvapoositanon received his B.Eng degree in electronics from the King Mongkut’s Institute of Technology, Ladkrabang, Thailand in 1991 and the M.Sc., degree and DIC in physical science and engineering in medicine in 1995 and Ph.D. degree and DIC in electrical engineering (digital signal processing for wireless communications) in 2002, both from the Imperial College, London, United Kingdom. Since 1992, he has been with the Mahanakorn University of Technology, Bangkok, Thailand where he is now serving as an associate professor in electronic engineering. Throughout the years, he has served as a reviewer and a technical program committee member for multiple international conferences and journals. He has also been involved in the automation industry as a consultant for image and signal processing tasks. His current research interests include signal processing theory for time series analysis in predictive maintenance and machine learning algorithms for industrial applications.


L. Ren, Y. Sun, H. Wang, and L. Zhang. Prediction of bearing remaining useful life with deep convolution neural network. IEEE Access, 6:13041–13049, 2018.

Z. Zhao, B. Liang, X. Wang, and W. Lu. Remaining useful life prediction of aircraft engine based on degradation pattern learning. Reliability Engineering & System Safety, 164:74–83, 2017.

Y. Liu, X. Hu, and W. Zhang. Remaining useful life prediction based on health index similarity. Reliability Engineering & System Safety, 185:502–510, 2019.

X.S. Si, W. Wang, C.H. Hu, D.H. Zhou, and M.G. Pecht. Remaining useful lifeestimation based on a nonlinear diffusion degradation process. IEEE Transactions on Reliability, 61(1):50–67, 2012.

E. Sutrisno, H. Oh, A. S. S. Vasan, and M. Pecht. Estimation of remaining useful life of ball bearings using data driven methodologies. In 3rd IEEE Conference on Prognostics and Health Management, Denver, Colorado, 18-21 June, 2012, pages 1–7, June 2012.

F. Liu, B. He, Y. Liu, S. Lu, Y. Zhao, and J. Zhao. Phase space similarity as a signature for rolling bearing fault diagnosis and remaining useful life estimation. Shock and Vibration, 2016(5341970):1–12, 2016.

Q. Zhang, P. W.T. Tse, X. Wan, and G. Xu. Remaining useful life estimation for mechanical systems based on similarity of phase space trajectory. Expert Systems with Applications, 42(5):2353–2360, 2015.

L. Zeming, G. Jianmin, J. Hongquan, G. Xu, G. Zhiyong, and W. Rongxi. A similaritybased method for remaining useful life prediction based on operational reliability. Applied Intelligence, 48(9):2983–2995, 2018.

P. Bonizzion and J.M.H. Karel. Singular spectrum decomposition: A new method for time series decomposition. Advances in Adaptive Data Analysis, 6(4):1450011, 2014.

N. Golyandina and A. Zhigljavsky. Singular Spectrum Analysis for time series. Springer Science & Business Media, 2013.

N. Golyandina and A. Korobeynikov. Basic singular spectrum analysis and forecasting with r. Computational Statistics & Data Analysis, 71:934–954, 2014.

J.B. Elsner and A.A. Tsonis. Singular spectrum analysis: a new tool in time series analysis. Springer Science & Business Media, 2013.

M. Atikur Rahman Khan and D.S. Poskitt. A note on window length selection in singular spectrum analysis. Australian & New Zealand Journal of Statistics, 55(2):87–108, 2013.

M.A.R. Khan and D. Poskitt. Window length selection and signal-noise separation and reconstruction in singular spectrum analysis. Monash Econometrics and Business Statistics Working Papers, 23(11):2011-23, 2011.

M.A.R. Khan and D. Poskitt. Moment tests for window length selection in singular spectrum analysis of short-and long-memory processes. Journal of Time Series Analysis, 34(2):141–155, 2013.

W. Mao, J. He, J. Tang, and Y. Li. Predicting remaining useful life of rolling bearings based on deep feature representation and long short-term memory neural network. Advances in Mechanical Engineering, 10(12):1687814018817184, 2018.

J. Liu, Q. Li, W. Chen, Y. Yan, Y. Qiu, and T. Cao. Remaining useful life prediction of pemfc based on long short-term memory recurrent neural networks. International Journal of Hydrogen Energy, 44(11): 5470–5480, 2019.

NASA. Prognostics Center of Excellence Data Repository: Turbo-fan engine degradation simulation data set. https://ti.arc.nasa.gov/tech /dash/groups/pcoe/prognostic-data-repository/, last accessed on May 2020.

F.J. Harris. On the use of windows for harmonic analysis with the discrete fourier transform. IEEE, 66:51–83, 1978.

A. Miranian, M. Abdollahzade, and H. Hassani. Day-ahead electricity price analysis and forecasting by singular spectrum analysis. IET Generation, Transmission & Distribution, 7(4):337–346, 2013.

C. Yu, Y. Li, and M. Zhang. Comparative study on three new hybrid models using elman neural network and empirical mode decomposition based technologies improved by singular spectrum analysis for hour-ahead wind speed forecasting. Energy Conversion and Management, 147:75–85, 2017.

C. Lima, V.L. de Oliveira Castellani, J.F.M. Pessanha, and A. Soares. A model to forecast wind speed through singular spectrum analysis and artificial neural networks. In Proceedings on the International Conference on Artificial Intelligence (ICAI), The Steering Committee of The 2017 World Congress in Computer Science, Computer Engineering and Applied Computing, Las Vegas, Nevada, USA, 17-20 July, 2017, pages 235–240, July 2017.

P. Intachai and P. Yuvapoositanon. A singular spectrum analysis pre-coded deep learning architecture for forecasting currency time series. In 6th International Electrical Engineering Congress (iEECON), Krabi, Thailand, 7-9 March, 2018, pages 1–4. IEEE, Mar 2018.

The Mathworks Inc.. Sequence-to-sequence regression using deep learning. https://www.mathworks.com/help/deeplearning/ug/sequence-to-sequence-regression-using-deep-learning.html, last accessed on May 2020.






Smart Innovative Technology for Future Industry and Multimedia Applications