Novel Extreme Learning Machine Using Kalman Filter for Performance Prediction of Aircraft Engine in Dynamic Behavior
Publication: Journal of Aerospace Engineering
Volume 33, Issue 5
Abstract
In this paper, a novel state-propagation extreme learning machine using a Kalman filter (KF-ELM) is proposed. In comparison with the plain extreme learning machine, the proposed algorithm takes the topological parameters as state variables and minimizes the covariance of state estimates to overcome the state conjunction and transformation dilemma in time series. As a result, its topological stability and prediction accuracy are enhanced, and these merits are further proved theoretically. In addition, the computational effort of KF-ELM is on the same order of magnitude as the plain extreme learning machine, while the former possesses a faster convergent speed. Then, several benchmark datasets are utilized to test the effectiveness and soundness of the proposed algorithm. Finally, it is employed to predict the gas path performance of a turbofan engine. The performance prediction accuracy is better than the plain ELM with different input rules in the dynamic process. Particularly under various flight operation conditions, the proposed algorithm performs well and its stability is sufficiently showcased. In a word, the proposed algorithm provides a candidate technique for predicting aircraft engine performance in dynamic behavior.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
We are grateful for the financial support of the National Nature Science Foundation of China (No. 91960110) and the Fundamental Research Funds for the Central Universities (No. NS2018018). Gratitude is also extended to the China Scholarship Council for supporting the first author to carry out collaborative research in the Department of Mechanical and Industrial Engineering at the University of Toronto.
References
Chang, R. C. 2014. “Performance diagnosis for turbojet engines based on flight data.” J. Aerosp. Eng. 27 (1): 9–15. https://doi.org/10.1061/(ASCE)AS.1943-5525.0000210.
Deo, R. C., P. Samui, and D. Kim. 2016. “Estimation of monthly evaporative loss using relevance vector machine, extreme learning machine and multivariate adaptive regression spline models.” Stochastic Environ. Res. Risk Assess. 30 (6): 1769–1784. https://doi.org/10.1007/s00477-015-1153-y.
Ding, S. F., G. Ma, and Z. Z. Shi. 2014. “A rough RBF neural network based on weighted regularized extreme learning machine.” Neural Process. Lett. 40 (3): 245–260. https://doi.org/10.1007/s11063-013-9326-5.
Dong, G. Q., and Z. H. Zhu. 2016. “Autonomous robotic capture of non-cooperative target by adaptive extended Kalman filter based visual servo.” Acta Astronaut. 122 (May): 209–218. https://doi.org/10.1016/j.actaastro.2016.02.003.
Du, X., X. M. Sun, Z. M. Wang, and A. N. Dai. 2017. “A scheduling scheme of linear model predictive controllers for turbofan engines.” IEEE Access 5 (Oct): 24533–24541. https://doi.org/10.1109/ACCESS.2017.2764076.
Huang, G. B., H. Zhou, and X. Ding. 2012. “Extreme learning machine for regression and multiclass classification.” IEEE Trans. Syst. Man Cybern. Part B Cybern. 42 (2): 513–529. https://doi.org/10.1109/TSMCB.2011.2168604.
Iosifidis, A., V. Mygdalis, A. Tefas, and I. Pitas. 2017. “One-class classification based on extreme learning and geometric class information.” Neural Process. Lett. 45 (3): 577–592. https://doi.org/10.1007/s11063-016-9541-y.
Lei, D., and S. S. Zhong. 2013. “Prediction of aircraft engine health condition parameters based on ensemble ELM.” J. Harbin Inst. Technol. 20 (3): 7–11.
Li, S., L. Goel, and P. Wang. 2016. “An ensemble approach for short-term load forecasting by extreme learning machine.” Appl. Energy 170 (May): 22–29. https://doi.org/10.1016/j.apenergy.2016.02.114.
Li, Y. G. 2015. “Aero gas turbine flight performance estimation using engine gas path measurements.” J. Propul. Power 31 (3): 851–860. https://doi.org/10.2514/1.B35381.
Liu, X. F., Y. Yuan, J. Shi, and L. Zhao. 2014. “Adaptive modeling of aircraft engine performance degradation model based on the equilibrium manifold and expansion form.” Proc. Inst. Mech. Eng. Part G: J. Aerosp. Eng. 228 (8): 1246–1272. https://doi.org/10.1177/0954410013488852.
Lu, F., T. Y. Y. Gao, J. Q. Huang, and X. J. Qiu. 2018. “Nonlinear Kalman filters for aircraft engine gas path health estimation with measurement uncertainty.” Aerosp. Sci. Technol. 76 (May): 126–140. https://doi.org/10.1016/j.ast.2018.01.024.
Lu, F., J. P. Jiang, J. Q. Huang, and X. J. Qiu. 2017. “Dual reduced kernel extreme learning machine for aero-engine fault diagnosis.” Aerosp. Sci. Technol. 71 (Dec): 742–750. https://doi.org/10.1016/j.ast.2017.10.024.
Mohammadil, E., and M. Montazeri-Gh. 2015. “A new approach to the gray-box identification of Wiener models with the application of gas turbine engine modeling.” J. Eng. Gas Turbines Power 137 (7): 071202. https://doi.org/10.1115/1.4029170.
Neerukatti, R. K., M. Y. Fard, and A. Chattopadhyay. 2017. “Gaussian process-based particle-filtering approach for real-time damage prediction with application.” J. Aerosp. Eng. 30 (1): 04016080. https://doi.org/10.1061/(ASCE)AS.1943-5525.0000680.
Nobrega, J. P., and A. L. Oliveira. 2015. “Kalman filter-based method for online sequential extreme learning machine for regression problems.” Eng. Appl. Artif. Intell. 44 (C): 101–110. https://doi.org/10.1016/j.engappai.2015.05.010.
Qi, Y. W., W. Bao, and J. T. Chang. 2015. “State-based switching control strategy with application to aeroengine safety protection.” J. Aerosp. Eng. 28 (3): 04014076. https://doi.org/10.1061/(ASCE)AS.1943-5525.0000405.
Safari, N., S. M. Mazhari, B. Khorramdel, and C. Y. Chung. 2019. “Tidal current and level uncertainty prediction via adaptive linear programming.” IEEE Trans. Sustainable Energy 10 (2): 748–758. https://doi.org/10.1109/TSTE.2018.2846661.
Sayehi, I., O. Touali, B. Bouallegue, and R. Tourki. 2015. “A comparative study of two kernel methods: Support vector regression (SVR) and regularization network (RN) and application to a thermal process PT326.” In Proc., Int. Conf. on Sciences and Technique, 849–853. New York: IEEE.
Simon, D. 2008. “A comparison of filtering approaches for aircraft engine health estimation.” Aerosp. Sci. Technol. 12 (4): 276–284. https://doi.org/10.1016/j.ast.2007.06.002.
Song, C. Y., K. B. Liu, and X. Zhang. 2018. “Integration of data-level fusion model and kernel methods for degradation modeling and prognostic analysis.” IEEE Trans. Reliab. 67 (2): 640–650. https://doi.org/10.1109/TR.2017.2715180.
Sulistiawati, I. B., A. Priyadi, O. A. Qudsi, A. Soeprijanto, and N. Yorino. 2016. “Critical clearing time prediction within various loads for transient stability assessment by means of extreme learning machine.” Int. J. Electr. Power Energy Syst. 77 (May): 345–352. https://doi.org/10.1016/j.ijepes.2015.11.034.
Tang, J., C. Deng, and G. B. Huang. 2016. “Extreme learning machine for multilayer perceptron.” IEEE Trans. Neural Networks Learn. Syst. 27 (4): 809. https://doi.org/10.1109/TNNLS.2015.2424995.
Volponi, A. J. 2014. “Gas turbine engine health management: Past, present, and future trends.” J. Eng. Gas Turbines Power 136 (5): 051201. https://doi.org/10.1115/1.4026126.
Wang, X. M., W. Q. Liu, and Z. L. Deng. 2017. “Robust weighted fusion Kalman estimators for systems with multiplicative noises, missing measurements and uncertain-variance linearly correlated white noises.” Aerosp. Sci. Technol. 68 (Sep): 331–344. https://doi.org/10.1016/j.ast.2017.05.023.
You, C. X., J. Q. Huang, and F. Lu. 2016. “Recursive reduced kernel based extreme learning machine for aero-engine fault pattern recognition.” Neurocomputing 214 (Nov): 1038–1045. https://doi.org/10.1016/j.neucom.2016.06.069.
Zaidan, M. A., A. R. Mills, R. F. Harrison, and P. J. Fleming. 2016. “Gas turbine engine prognostics using Bayesian hierarchical models: A variational approach.” Mech. Syst. Sig. Process. 70–71: 120–140. https://doi.org/10.1016/j.ymssp.2015.09.014.
Zhang, S. G., Y. Q. Guo, and X. L. Chen. 2013. “Performance evaluation and simulation validation of fault diagnosis system for aircraft engine.” J. Propul. Technol. 34 (8): 1121–1127.
Zhang, W., M. P. Jia, L. Zhu, and X. A. Yan. 2017. “Comprehensive overview on computational intelligence techniques for machinery condition monitoring and fault diagnosis.” Chin. J. Mech. Eng. 30 (4): 782–795. https://doi.org/10.1007/s10033-017-0150-0.
Zhao, N. B., S. Y. Li, and J. L. Yang. 2016. “A review on nanofluids: Data driven modeling of thermal physical properties and the application in automotive radiator.” Renewable Sustainable Energy Rev. 66 (Dec): 596–616. https://doi.org/10.1016/j.rser.2016.08.029.
Zhou, D. J., Z. Q. Yu, H. S. Zhang, and S. L. Weng. 2016. “A novel grey prognostic model based on Markov process and grey incidence analysis for energy conversion equipment degradation.” Energy 109 (Aug): 420–429. https://doi.org/10.1016/j.energy.2016.05.008.
Zhou, H. W., J. Q. Huang, F. Lu, J. Thiyagalingam, and T. Kirubarajan. 2018. “Echo state kernel recursive least squares algorithm for machine condition prediction.” Mech. Syst. Sig. Process. 111 (Oct): 68–86. https://doi.org/10.1016/j.ymssp.2018.03.047.
Information & Authors
Information
Published In
Copyright
©2020 American Society of Civil Engineers.
History
Received: Oct 24, 2018
Accepted: Mar 9, 2020
Published online: Jun 9, 2020
Published in print: Sep 1, 2020
Discussion open until: Nov 9, 2020
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.