THERMAL SCIENCE

International Scientific Journal

Thermal Science - Online First

Authors of this Paper

External Links

online first only

Aero-engine exhaust gas temperature prediction based on LightGBM optimized by improved bat algorithm

ABSTRACT
In this paper, an aero-engine exhaust gas temperature (EGT) prediction model based on LightGBM optimized by the chaotic rate bat algorithm (CRBA) is proposed to monitor aero-engine performance effectively. By introducing chaotic rate, the convergence speed and precision of bat algorithm are im-proved, which CRBA is obtained. LightGBM is optimized by CRBA and it is used to predict EGT. Taking a type of aero-engine for example, some relevant performance parameters from the flight data measured by airborne sensors were selected as input variables and EGT as output variables. The data set is divided into training and test sets, and the CRBA-LightGBM model is trained and tested, and compared with ensemble algorithms such as RF, XGBoost, GBDT, LightGBM and BA-LightGBM. The results show that the mean absolute error (MAE) of this method in the prediction of EGT (after normalization) is 0.0065, the mean absolute percentage error (MAPE) is 0.77% and goodness of fit R2 has reached to 0.9469. The prediction effect of CRBA-LightGBM is better than other comparison algorithms and it is suitable for aero-engine condition monitoring.
KEYWORDS
PAPER SUBMITTED: 2020-05-20
PAPER REVISED: 2020-06-27
PAPER ACCEPTED: 2020-07-08
PUBLISHED ONLINE: 2020-09-12
DOI REFERENCE: https://doi.org/10.2298/TSCI200520246L
REFERENCES
  1. Zolghadri, A., et al., Fault Diagnosis and Fault-Tolerant Control and Guidance for Aerospace Vehicles: From Theory to Application., Springer, 2013.
  2. Yilmaz, O., et al., A Repair and Overhaul Methodology for Aeroengine Components., Robotics and Computer-Integrated Manufacturing, 26(2010), 2, pp. 190-201.
  3. Ilbas, M., & Mahmut T., Estimation of exhaust gas temperature using artificial neural network in turbofan engines, 0 Isı bilimi ve tekniği dergisi = Journal of Thermal Sciences and Technology, 32(2012), 2, pp. 11-18.
  4. Zhong, S., Lei, D., & Ding, G., Convolution sum discrete process neural network and its application in aeroengine exhausted gas temperature prediction, Acta Aeronautica et Astronautica Sinica, 33(2012), 3, pp. 438-445.
  5. Ding, G., et al., Prediction of aeroengine exhaust gas temperature using process neural network, Journal of Aerospace Power, 24(2009), 5, pp.1035-1039.
  6. Kumar, A., et al. Exhaust Gas Temperature Data Prediction by Autoregressive Models. 2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE), Nova scotia, Canada, 2015, pp. 976-981.
  7. Jun, P., et al., Aero-engine exhaust gas temperature prediction model based on IFOA-GRNN, Journal of Aerospace Power, 34(2019), 1, pp.8-17, 2019.
  8. Maragoudakis, M., & Loukis E., Using Ensemble Random Forests for the extraction and exploitation of knowledge on gas turbine blading faults identification, Or Insight, 25(2012), pp. 80-104.
  9. Pan, B., Application of XGBoost algorithm in hourly PM2.5 concentration prediction, IOP Conference Series: Earth and Environmental Science, 113(2012), 1, p. 012127.
  10. Huang, Q., et al., A prediction method for aero-engine health management based on nonlinear time series analysis, ieee international conference on prognostics and health management, 2016, pp. 1-8.
  11. Zhou, Y., et al., Research on Aero-Engine Maintenance Level Decision Based on Improved Artificial Fish-Swarm Optimization Random Forest Algorithm, 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC), Xi'an, China, 2018, pp. 606-610.
  12. Ke, G. et al., LightGBM: a highly efficient gradient boosting decision tree, the Neural Information Processing Systems, 2017, pp.3146-3154.
  13. Wang, D., et al., LightGBM: An Effective miRNA Classification Method in Breast Cancer Patients, Proceedings of the 2017 International Conference on Computational Biology and Bioinformatics, 2017, pp. 7-11.
  14. Ma. X, et al., Study on A Prediction of P2P Network Loan Default Based on the Machine Learning LightGBM and XGboost Algorithms according to Different High Dimensional Data Cleaning, Electronic Commerce Research & Applications, 31(2018), pp. 24-39.
  15. Ustuner, M., & Sanli, F., Polarimetric Target Decompositions and Light Gradient Boosting Ma-chine for Crop Classification: A Comparative Evaluation, Isprs International Journal of Geo In-formation, 8(2019), 2, no. 2, p. 97.
  16. Ju, Y., et al., A Model Combining Convolutional Neural Network and LightGBM Algorithm for Ultra-Short-Term Wind Power Forecasting, IEEE Access, 7(2019), pp. 28309-28318.
  17. Tan, P.-N., Steinbach, M. M., & Kumar, V. Introduction to Data Mining, Addison Wesley, Boston, 2015.
  18. Elith, J. Leathwick, J., & Hastie T., A working guide to boosted regression trees, Journal of Animal Ecology, 77(2008), 4, pp. 802-813.
  19. Yang, X., A New Metaheuristic Bat-Inspired Algorithm, Computer Knowledge & Technology, 284(2010), pp. 65-74.
  20. Wang, Y., et al., Study on Improved Singular Value Decomposition Denoising Method Applied to UAV Flight Parameter Data, 2019 IEEE 20th International Conference on High Performance Switching and Routing (HPSR), 2019, pp. 1-6.
  21. Yang, X., Nature-inspired metaheuristic algorithms. Luniver press, 2008, pp. 97-104.
  22. Yang, X., Bat Algorithm and Cuckoo Search: A Tutorial. Artificial Intelligence, Evolutionary Computing and Metaheuristics, 2013, pp. 421-434.
  23. Adarsh, B., et al., Economic dispatch using chaotic bat algorithm, Energy, 96(2016), pp. 666-675.
  24. Karri, C., & Jena, U. Fast vector quantization using a Bat algorithm for image compression, Engi-neering Science & Technology An International Journal, 19(2015), 2, pp. 769-781.
  25. Rahimi, A., et al., The online parameter identification of chaotic behaviour in permanent magnet synchronous motor by Self-Adaptive Learning Bat-inspired algorithm," International Journal of Electrical Power & Energy Systems, 78(2016), pp. 285-291.
  26. Dinh, B., et al., Bat optimal algorithm combined uniform mutation with Gaussian mutation, Control & Decision, 32(2017), pp. 1775-1781.
  27. Ye. C., Bat Algorithm with Chaotic Search Strategy and Analysis of Its Property, computer simu-lation, 25(2013), 1, pp. 1183-1188.
  28. Hamidzadeh, J., et al., Weighted support vector data description based on chaotic bat algorithm, applied soft computing, 60(2017), pp. 540-551.