• ISSN 0258-2724
  • CN 51-1277/U
  • EI Compendex
  • Scopus
  • Indexed by Core Journals of China, Chinese S&T Journal Citation Reports
  • Chinese S&T Journal Citation Reports
  • Chinese Science Citation Database
Turn off MathJax
Article Contents
ZHAO Jianhui, LAN Zhongze, LU Xiangdong, YANG Jintao. Injection Quantity Prediction of High-Pressure Common Rail Systems under Multiple Injections Based on Gaussian Process Regression[J]. Journal of Southwest Jiaotong University. doi: 10.3969/j.issn.0258-2724.20240101
Citation: ZHAO Jianhui, LAN Zhongze, LU Xiangdong, YANG Jintao. Injection Quantity Prediction of High-Pressure Common Rail Systems under Multiple Injections Based on Gaussian Process Regression[J]. Journal of Southwest Jiaotong University. doi: 10.3969/j.issn.0258-2724.20240101

Injection Quantity Prediction of High-Pressure Common Rail Systems under Multiple Injections Based on Gaussian Process Regression

doi: 10.3969/j.issn.0258-2724.20240101
  • Received Date: 01 Mar 2024
  • Rev Recd Date: 11 Jun 2024
  • Available Online: 31 Dec 2025
  • In high-pressure common rail systems under multiple injections, the pressure waves induced by the pilot injection cause fluctuations in the main injection quantity, thereby reducing in-cylinder combustion efficiency and increasing pollutant emissions. A data-driven prediction model for the main injection quantity based on Gaussian process regression (GPR) was proposed to achieve the accurate control of injection quantity under multiple injections. First, D-optimal design and a second-order response surface method were employed to build a response surface model for the main injection quantity by utilizing rail pressure, pilot-injection pulse width, pilot-main injection interval, and main-injection pulse width as factors. Analysis of variance indicates that the four operating parameters all have extremely significant effects on the main injection quantity. Then, based on a self-developed multi-physics coupled digital simulation platform, a dataset containing 528 operating conditions was constructed, and the model was trained. On this basis, several combinations of mean functions (zero, constant, linear, and quadratic polynomials) and different kernel functions (Seiso, Rqard, and Matérn) were systematically compared, and the linear mean function combined with the rational quadratic kernel function was identified as the optimal configuration. Results show that in test conditions, the mean absolute percentage error (MAPE) of main injection quantity predicted by the GPR-based model is 0.347% and the coefficient of determination R2 is 0.9996, with predictions at different main-pulse widths and pilot-main intervals clustered closely around the regression line. In non-test conditions, the model can still accurately reproduce the fluctuation law of the main injection quantity with varying pilot-main intervals, and features lower error and higher consistency than BP, GR, and SVR models. The proposed GPR-based data-driven model under multiple injections is proved to have both high prediction accuracy and sound generalization capability, providing model support for the precise control of high-pressure common rail systems under multiple injections.

     

  • loading
  • [1]
    HAN T, SINGH R, LAVOIE G, et al. Multiple injection for improving knock, gaseous and particulate matter emissions in direct injection SI engines[J]. Applied Energy, 2020, 262: 114578. doi: 10.1016/j.apenergy.2020.114578
    [2]
    赵建辉, 徐煜, 杨贵春, 等. 基于喷雾动量法的共轨喷油器喷油稳定性试验研究[J]. 西南交通大学学报, 2025, 60(3): 665-670. doi: 10.3969/j.issn.0258-2724.20230335

    ZHAO Jianhui, XU Yu, YANG Guichun, et al. Experimental study on injection stability of common rail injector based onsSpray momentum method[J]. Journal of Southwest Jiaotong University, 2025, 60(3): 665-670. doi: 10.3969/j.issn.0258-2724.20230335
    [3]
    MORETTO G, SCHNELL N, FREY J, et al. Fast model-based calibration of multiple injections for a CI engine using nonlinear optimal control[J]. Control Engineering Practice, 2024, 145: 105848. doi: 10.1016/j.conengprac.2024.105848
    [4]
    夏天峰, 陶文辉, 王晓艳, 等. 微量柴油引燃高压直喷天然气的碳烟体积分数分布[J]. 内燃机学报, 2025, 43(2): 117-126. doi: 10.16236/j.cnki.nrjxb.202502014

    XIA Tianfeng, TAO Wenhui, WANG Xiaoyan, et al. Distribution of soot volume fraction of high pressure direct injection natural gas ignited by trace diesel[J]. Transactions of CSICE, 2025, 43(2): 117-126 doi: 10.16236/j.cnki.nrjxb.202502014
    [5]
    杨津韬, 张恒, 赵建辉, 等. 多次喷射下喷油器结构参数对喷油量波动影响[J]. 哈尔滨工程大学学报, 2025, 46(2): 276-282. doi: 10.11990/jheu.202307011

    YANG Jintao, ZHANG Heng, ZHAO Jianhui, et al. Influence of injector structure parameters on fuel injection quantity fluctuation under multiple injections[J]. Journal of Harbin Engineering University, 2025, 46(2): 276-282. doi: 10.11990/jheu.202307011
    [6]
    JIA G H, GAO S, SHU X, et al. Multi-objective optimization of emission parameters of a diesel engine using oxygenated fuel and pilot injection strategy based on RSM-NSGA Ⅲ[J]. Energy, 2024, 293: 130661. doi: 10.1016/j.energy.2024.130661
    [7]
    XUAN T M, LI H J, WANG Y T, et al. A conceptual model of polyoxymethylene dimethyl ether 3 (PODE3) spray combustion under compression ignition engine-like conditions[J]. Combustion and Flame, 2024, 261: 113296. doi: 10.1016/j.combustflame.2024.113296
    [8]
    KIM J, LEE J, KIM K. Numerical study on the effects of fuel viscosity and density on the injection rate performance of a solenoid diesel injector based on AMESim[J]. Fuel, 2019, 256: 115912. doi: 10.1016/j.fuel.2019.115912
    [9]
    XU J, FAN L Y, LI B, et al. Research on pressure wave decoupling method for the nozzle of common rail electronically controlled injector based on water hammer theory[J]. International Journal of Engine Research, 2024, 25(5): 882-895. doi: 10.1177/14680874231210715
    [10]
    ROJAS-REINOSO E V, MORALES-CHAUCA K, LARA-LARA J, et al. Adaptation and validation of injection rate predictive model for solenoid type injectors with different nozzle geometry[J]. Applied Sciences, 2024, 14(8): 3394. doi: 10.3390/app14083394
    [11]
    LI R C, YUAN W T, XU J K, et al. Study of the optimization of rail pressure characteristics in the high-pressure common rail injection system for diesel engines based on the response surface methodology[J]. Processes, 2023, 11(9): 2626. doi: 10.3390/pr11092626
    [12]
    TORRES-JIMENEZ E, DORADO R, KEGL B, et al. One-dimensional modeling and simulation of injection processes of bioethanol-biodiesel and bioethanol-diesel fuel blends[J]. Fuel, 2018, 227: 334-344. doi: 10.1016/j.fuel.2018.04.118
    [13]
    FINESSO R, SPESSA E. A control-oriented approach to estimate the injected fuel mass on the basis of the measured in-cylinder pressure in multiple injection diesel engines[J]. Energy Conversion and Management, 2015, 105: 54-70. doi: 10.1016/j.enconman.2015.07.053
    [14]
    DONG Q, YANG X Y, NI H, et al. An on-line measurement method of injection rate of high pressure common rail system[J]. Measurement, 2021, 170: 108716. doi: 10.1016/j.measurement.2020.108716
    [15]
    FEI H Z, LIU B X, WANG L P, et al. Optimal estimation of injection rate for high-pressure common rail system using the extended Kalman filter[J]. Measurement, 2023, 220: 113385. doi: 10.1016/j.measurement.2023.113385
    [16]
    SILVAGNI G, RAVAGLIOLI V, PONTI F, et al. Development of a predictive pressure waves model for high-pressure common rail injection systems[J]. SAE International Journal of Engines, 2021, 15(5): 719-741. doi: 10.4271/03-15-05-0039
    [17]
    SORIANO J A, MATA C, ARMAS O, et al. A zero-dimensional model to simulate injection rate from first generation common rail diesel injectors under thermodynamic diagnosis[J]. Energy, 2018, 158: 845-858. doi: 10.1016/j.energy.2018.06.054
    [18]
    GAO Z G, LI G X, XU C L, et al. A calculation method and experiment study of high-pressure common rail injection rate with solenoid injectors[J]. Science Progress, 2021, 104(2): 368504211026157.
    [19]
    PLAMONDON E, SEERS P. Development of a simplified dynamic model for a piezoelectric injector using multiple injection strategies with biodiesel/diesel-fuel blends[J]. Applied Energy, 2014, 131: 411-424. doi: 10.1016/j.apenergy.2014.06.039
    [20]
    ATAC O F, LEE S, MOON S. Development of simplified model for injection rate prediction of diesel injectors during transient and steady operation[J]. Fuel, 2022, 324: 124655. doi: 10.1016/j.fuel.2022.124655
    [21]
    ZHANG T T. An estimation method of the fuel mass injected in large injections in common-rail diesel engines based on system identification using artificial neural network[J]. Fuel, 2022, 310: 122404. doi: 10.1016/j.fuel.2021.122404
    [22]
    OH H, HWANG J, PICKETT L M, et al. Machine-learning based prediction of injection rate and solenoid voltage characteristics in GDI injectors[J]. Fuel, 2022, 311: 122569. doi: 10.1016/j.fuel.2021.122569
    [23]
    ZHAO J H, ZIRKA S E, MOROZ Y I. Duality-derived models of high-speed electromagnetic valves[J]. IEEE Transactions on Industrial Electronics, 2021, 68(10): 9876-9884. doi: 10.1109/TIE.2020.3022510
    [24]
    ZHAO J H, ZIRKA S E, MOROZ Y I, et al. Physical Cauer circuits in nonlinear eddy-current modeling[J]. Journal of Magnetism and Magnetic Materials, 2020, 508: 166850. doi: 10.1016/j.jmmm.2020.166850
    [25]
    张付英, 高勇新, 张原浩, 等. 基于响应面法和正交试验的旋转轴唇形密封的可靠性分析[J]. 机械设计, 2024, 41(10): 41-49. doi: 10.13841/j.cnki.jxsj.2024.10.003

    ZHANG Fuying, GAO Yongxin, ZHANG Yuanhao, et al. Reliability analysis of rotary shaft lip seal based on response surface method and orthogonal test[J]. Journal of Machine Design, 2024, 41(10): 41-49. doi: 10.13841/j.cnki.jxsj.2024.10.003
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(5)  / Tables(5)

    Article views(65) PDF downloads(9) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return