Advertisement

MaLTESE: Large-Scale Simulation-Driven Machine Learning for Transient Driving Cycles

  • Shashi M. Aithal
  • Prasanna BalaprakashEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11501)

Abstract

Optimal engine operation during a transient driving cycle is the key to achieving greater fuel economy, engine efficiency, and reduced emissions. In order to achieve continuously optimal engine operation, engine calibration methods use a combination of static correlations obtained from dynamometer tests for steady-state operating points and road and/or track performance data. As the parameter space of control variables, design variable constraints, and objective functions increases, the cost and duration for optimal calibration become prohibitively large. In order to reduce the number of dynamometer tests required for calibrating modern engines, a large-scale simulation-driven machine learning approach is presented in this work. A parallel, fast, robust, physics-based reduced-order engine simulator is used to obtain performance and emission characteristics of engines over a wide range of control parameters under various transient driving conditions (drive cycles). We scale the simulation up to 3,906 nodes of the Theta supercomputer at the Argonne Leadership Computing Facility to generate data required to train a machine learning model. The trained model is then used to predict various engine parameters of interest, and the results are compared with those predicted by the engine simulator. Our results show that a deep-neural-network-based surrogate model achieves high accuracy: Pearson product-moment correlation values larger than 0.99 and mean absolute percentage error within 1.07% for various engine parameters such as exhaust temperature, exhaust pressure, nitric oxide, and engine torque. Once trained, the deep-neural-network-based surrogate model is fast for inference: it requires about 16 \(\upmu \)s for predicting the engine performance and emissions for a single design configuration compared with about 0.5 s per configuration with the engine simulator. Moreover, we demonstrate that transfer learning and retraining can be leveraged to incrementally retrain the surrogate model to cope with new configurations that fall outside the training data space.

Keywords

Transient driving cycle modeling Surrogate modeling Machine learning Deep learning Deep neural networks 

Notes

Acknowledgment

This research used resources of the Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC02-06CH11357. This material was based upon work supported by the U.S. Department of Energy, Office of Science, under Contract DE-AC02-06CH11357.

References

  1. 1.
    Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: OSDI, vol. 16, pp. 265–283 (2016)Google Scholar
  2. 2.
    Aithal, S.M.: Analysis of the current signature in a constant-volume combustion chamber. Combust. Sci. Technol. 185(2), 336–349 (2013).  https://doi.org/10.1080/00102202.2012.718297CrossRefGoogle Scholar
  3. 3.
    Aithal, S.M.: Prediction of voltage signature in a homogeneous charge compression ignition (HCCI) engine fueled with propane and acetylene. Combust. Sci. Technol. 185(8), 1184–1201 (2013).  https://doi.org/10.1080/00102202.2013.781593CrossRefGoogle Scholar
  4. 4.
    Aithal, S.M.: Development of an integrated design tool for real-time analyses of performance and emissions in engines powered by alternative fuels. In: Proceedings of SAE 11th International Conference on Engines & Vehicles. SAE (2013)Google Scholar
  5. 5.
    Aithal, S.M., Wild, S.M.: ACCOLADES: a scalable workflow framework for large-scale simulation and analyses of automotive engines. In: Kunkel, J.M., Ludwig, T. (eds.) ISC High Performance 2015. LNCS, vol. 9137, pp. 87–95. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-20119-1_7CrossRefGoogle Scholar
  6. 6.
    Bishop, C.M.: Pattern Recognition and Machine Learning, vol. 1. Springer, New York (2006).  https://doi.org/10.1007/978-1-4615-7566-5zbMATHCrossRefGoogle Scholar
  7. 7.
    Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)MathSciNetzbMATHGoogle Scholar
  8. 8.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)zbMATHCrossRefGoogle Scholar
  9. 9.
    Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. arXiv preprint arXiv:1603.02754 (2016)
  10. 10.
    Chollet, F., et al.: Keras (2015). https://keras.io
  11. 11.
    Drucker, H.: Improving regressors using boosting techniques. In: ICML, vol. 97, pp. 107–115 (1997)Google Scholar
  12. 12.
    Friedman, J.H.: Stochastic gradient boosting. Comput. Stat. Data Anal. 38(4), 367–378 (2002)MathSciNetzbMATHCrossRefGoogle Scholar
  13. 13.
    Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Mach. Learn. 63(1), 3–42 (2006)zbMATHCrossRefGoogle Scholar
  14. 14.
    Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep Learning, vol. 1. MIT press, Cambridge (2016)zbMATHGoogle Scholar
  15. 15.
    Hashemi, N., Clark, N.: Artificial neural network as a predictive tool for emissions from heavy-duty diesel vehicles in Southern California. Int. J. Eng. Res. 8(4), 321–336 (2007)CrossRefGoogle Scholar
  16. 16.
    Hoerl, A.E., Kennard, R.W.: Ridge regression: biased estimation for nonorthogonal problems. Technometrics 12(1), 55–67 (1970)zbMATHCrossRefGoogle Scholar
  17. 17.
    Krijnsen, H.C., van Kooten, W.E., Calis, H.P.A., Verbeek, R.P., Bleek, C.M.: Prediction of NOx emissions from a transiently operating diesel engine using an artificial neural network. Chem. Eng. Technol. Industr. Chem. Plant Equip. Process Eng. Biotechnol. 22(7), 601–607 (1999)Google Scholar
  18. 18.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  19. 19.
    Loh, W.Y.: Classification and regression trees. Wiley Interdisc. Rev. Data Min. Knowl. Discov. 1(1), 14–23 (2011)CrossRefGoogle Scholar
  20. 20.
    Louppe, G., Geurts, P.: Ensembles on random patches. In: Flach, P.A., De Bie, T., Cristianini, N. (eds.) ECML PKDD 2012. LNCS (LNAI), vol. 7523, pp. 346–361. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33460-3_28CrossRefGoogle Scholar
  21. 21.
    McKay, M., Beckman, R., Conover, W.: Comparison the three methods for selecting values of input variable in the analysis of output from a computer code. Technometrics; (United States).  https://doi.org/10.1080/00401706.1979.10489755MathSciNetzbMATHGoogle Scholar
  22. 22.
    Parlak, A., Islamoglu, Y., Yasar, H., Egrisogut, A.: Application of artificial neural network to predict specific fuel consumption and exhaust temperature for a diesel engine. Appl. Therm. Eng. 26(8–9), 824–828 (2006)CrossRefGoogle Scholar
  23. 23.
    Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  24. 24.
    Shrivastava, N., Khan, Z.M.: Application of soft computing in the field of internal combustion engines: a review. Arch. Comput. Meth. Eng. 25(3), 707–726 (2018)zbMATHCrossRefGoogle Scholar
  25. 25.
    Smola, A.J., Schölkopf, B.: A tutorial on support vector regression. Stat. Comput. 14(3), 199–222 (2004)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Argonne National LaboratoryLemontUSA

Personalised recommendations