한국분무공학회지 (Journal of ILASS-Korea)

  • 제27권2호
  • /
  • Pages.57-65
  • /
  • 2022
  • /
  • 1226-2277(pISSN)
  • /
  • 2288-9051(eISSN)
한국분무공학회 (Institute for Liquid Atomization and Spray Systems-Korea)
권호 표지
DOI QR코드

DOI QR Code

머신러닝을 이용한 다공형 GDI 인젝터의 플래시 보일링 분무 예측 모델 개발

Development of Flash Boiling Spray Prediction Model of Multi-hole GDI Injector Using Machine Learning

  • 상몽소 (전남대학교 일반대학원 기계공학과) ;
  • 신달호 (건국대학교 일반대학원 기계공학과) ;
  • ;
  • 박수한 (건국대학교 기계항공공학부)
  • 투고 : 2022.02.21
  • 심사 : 2022.03.14
  • 발행 : 2022.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

The purpose of this study is to use machine learning to build a model capable of predicting the flash boiling spray characteristics. In this study, the flash boiling spray was visualized using Shadowgraph visualization technology, and then the spray image was processed with MATLAB to obtain quantitative data of spray characteristics. The experimental conditions were used as input, and the spray characteristics were used as output to train the machine learning model. For the machine learning model, the XGB (extreme gradient boosting) algorithm was used. Finally, the performance of machine learning model was evaluated using R2 and RMSE (root mean square error). In order to have enough data to train the machine learning model, this study used 12 injectors with different design parameters, and set various fuel temperatures and ambient pressures, resulting in about 12,000 data. By comparing the performance of the model with different amounts of training data, it was found that the number of training data must reach at least 7,000 before the model can show optimal performance. The model showed different prediction performances for different spray characteristics. Compared with the upstream spray angle and the downstream spray angle, the model had the best prediction performance for the spray tip penetration. In addition, the prediction performance of the model showed a relatively poor trend in the initial stage of injection and the final stage of injection. The model performance is expired to be further enhanced by optimizing the hyper-parameters input into the model.

키워드

과제정보

이 연구는 한국연구재단 중견연구자지원사업(2019R1A2C1089494)과 한-인도 해외협력기반조성사업(2020K1A3A1A19088692)의 지원으로 수행되었습니다. 지원기관에 감사드립니다.

참고문헌

  1. E. Sher, T. Bar-Kohany and A. Rashkovan, "Flashboiling atomization", Progress in Energy and Combustion Science, Vol. 34, No. 4, 2008, pp. 417~439. https://doi.org/10.1016/j.pecs.2007.05.001
  2. R. Brown and J. L. York, "Sprays formed by flashing liquid jets", AIChE Journal, Vol. 8, No. 2, 1962, pp. 149~153. https://doi.org/10.1002/aic.690080204
  3. A. Montanaro and L. Allocca, Flash Boiling Evidences of a Multi-Hole GDI Spray under Engine Conditions by Mie-Scattering Measurements. SAE International 2015.
  4. M. Kramer, E. Kull and M. Wensing, "Flashboiling-induced targeting changes in gasoline direct injection sprays", International Journal of Engine Research, Vol. 17, No. 1, 2016, pp. 97~107. https://doi.org/10.1177/1468087415604763
  5. H. Guo, X. Ma, Y. Li, S. Liang, Z. Wang, H. Xu and J. Wang, "Effect of flash boiling on microscopic and macroscopic spray characteristics in optical GDI engine", Fuel, Vol. 190, 2017, pp. 79~89. https://doi.org/10.1016/j.fuel.2016.11.043
  6. C. Jiang, M. C. Parker, D. Butcher, A. Spencer, C. P. Garner and J. Helie, "Comparison of flash boiling resistance of two injector designs and the consequences on downsized gasoline engine emissions", Applied Energy, Vol. 254, 2019, 113735. https://doi.org/10.1016/j.apenergy.2019.113735
  7. W. Zeng, M. Xu, G. Zhang, Y. Zhang and D. J. Cleary, "Atomization and vaporization for flash-boiling multihole sprays with alcohol fuels", Fuel, Vol. 95, 2012, pp. 287~297. https://doi.org/10.1016/j.fuel.2011.08.048
  8. D. Kim and S. Park, "Effects of nozzle hole configuration of a multi-hole type gasoline direct injector on spray development under flash boiling conditions", International Journal of Engine Research, Vol. 22, No. 9, 2021, pp. 2997-3012. https://doi.org/10.1177/1468087420960026
  9. T. Kim and S. Park. "Modeling flash boiling breakup phenomena of fuel spray from multi-hole type direct-injection spark-ignition injector for various fuel components", Energy Conversion and Management, Vol. 160, 2018, pp. 165~175. https://doi.org/10.1016/j.enconman.2018.01.042
  10. T. Kim, D. Kim and S. Park, "Numerical approach to analyze propane flash boiling spray using modified gas-jet model", Applied Thermal Engineering, Vol. 162, 2019, 114255.
  11. C. Price, A. Hamzehloo, P. Aleiferis and D. Richardson, "Numerical modelling of droplet breakup for flashboiling fuel spray predictions", International Journal of Multiphase Flow, Vol. 125, 2020, 103183. https://doi.org/10.1016/j.ijmultiphaseflow.2019.103183
  12. C. Price, A. Hamzehloo, P. Aleiferis and D. Richardson, "Numerical modelling of fuel spray formation and collapse from multi-hole injectors under flash-boiling conditions", Fuel, Vol. 221, 2018, pp. 518~541. https://doi.org/10.1016/j.fuel.2018.01.088
  13. C. Price, A. Hamzehloo, P. Aleiferis and D. Richardson, Aspects of Numerical Modelling of Flash-Boiling Fuel Sprays. SAE International 2015.
  14. J. Tian, Y. Liu, H. Bi, F. Li, L. Bao, K. Han, W. Zhou, Z. Ni and Q. Lin, "Experimental study on the spray characteristics of octanol diesel and prediction of spray tip penetration by ANN model", Energy, Vol. 239, 2022, 121920. https://doi.org/10.1016/j.energy.2021.121920
  15. H. Taghavifar, S. Khalilarya and S. Jafarmadar, "Diesel engine spray characteristics prediction with hybridized artificial neural network optimized by genetic algorithm", Energy, Vol. 71, 2014, pp. 656~664. https://doi.org/10.1016/j.energy.2014.05.006
  16. J. Liu, Q. Huang, C. Ulishney and C. E. Dumitrescu, "Machine learning assisted prediction of exhaust gas temperature of a heavy-duty natural gas spark ignition engine", Applied Energy, Vol. 300, 2021, 117413. https://doi.org/10.1016/j.apenergy.2021.117413
  17. J. Hwang, P. Lee, S. Mun, I. K. Karathanassis, P. Koukouvinis, L. M. Pickett and M. Gavaises, "Machine-learning enabled prediction of 3D spray under engine combustion network spray G conditions", Fuel, Vol. 293, 2021, 120444. https://doi.org/10.1016/j.fuel.2021.120444
  18. H. Oh, J. Hwang, L. M. Pickett and D. Han, "Machine-learning based prediction of injection rate and solenoid voltage characteristics in GDI injectors", Fuel, Vol. 311, 2022, 122569. https://doi.org/10.1016/j.fuel.2021.122569
  19. K. C. Opacich, J. S. Heyne, E. Peiffer and S. D. Stouffer, "Analyzing the Relative Impact of Spray and Volatile Fuel Properties on Gas Turbine Combustor Ignition in Multiple Rig Geometries", AIAA Scitech 2019 Forum, 2019.
  20. M. Botticelli, R. Hellmann, P. Jochmann, K. Georg Stapf and E. Schunemann, "Application of Machine Learning to Gasoline Direct Injection Systems: Towards a Data-Driven Development", 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA), 2020, pp. 805~810.
  21. T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System", Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785~794.