Study on predictions of spray target position of gasoline direct injection injectors with multi-hole using physical model and machine learning

Chang，Mengzhao1; Jeong，Minuk2; Park，Sungwook3; Kim，Hyung Ik4; Park，Jeong Hwan4; Park，Suhan5

2023-08-01

10.1016/j.fuproc.2023.107774

Fuel Processing Technology   影响因子和分区

0378-3820

1873-7188

A lot of effort is being invested in improving the performance of injectors, the core components of gasoline direct injection (GDI) engines, such as injection stability and accuracy. The purpose of this study is to establish models that can predict spray targeting according to the design parameters of GDI injector, to improve the injection accuracy and enhance the engine performance. First, this study used laser sheet beam visualization technology to measure the spray targeting images of injectors with different design parameters in different cross-sections and obtained the spray targeting coordinates through image post-processing. Then, using the experimental data, two different approaches (empirical formula and machine learning), were used to create models for predicting spray targeting, and their applicability was compared. The research results showed that both the physical model and the machine learning model had a prediction accuracy of >0.98 in terms of R, but the physical model had a lower prediction error in terms of the root mean square error (RMSE). Further, the tendency of the target coordinate to change is proportional to 0.2 power of the injection pressure (P), −0.1 power of ratio of hole length to hole diameter ((L/D)), and − 1.5 power of the angle between axes of two holes (θ).

Gasoline direct injection Injector design parameters Machine learning model Physical model Spray targeting

SCI ; EI

英语

第一

Basic Science Research Program[2019R1A2C1089494] ; International Cooperation Program - National Research Foundation of Korea (NRF) under the India-Korea International Cooperation Program[2020K1A3A1A19088692]

Chemistry ; Energy & Fuels ; Engineering

Chemistry, Applied ; Energy & Fuels ; Engineering, Chemical

WOS:000984537800001

ELSEVIER

20231613896758

Direct injection ; Engines ; Forecasting ; Gasoline ; Mean square error

Fuel Combustion and Flame Research:521 ; Liquid Fuels:523 ; Artificial Intelligence:723.4 ; Mathematical Statistics:922.2

CHEMISTRY

2-s2.0-85152580108

Scopus

1.Department of Mechanics and Aerospace Engineering,Southern University of Science and Technology (SUSTech),Shenzhen,518055,China
2.Department of Mechanical Convergence Engineering,Graduate School of Hanyang University,Seoul,222 Wangsimni-ro, Seongdong-gu,04763,South Korea
3.School of Mechanical Engineering,Hanyang University,Seoul,222 Wangsimni-ro, Seongdong-gu,04763,South Korea
4.Product Design Team 2,Hyundai-Kefico,Gunpo-si, Gyeonggi-do,South Korea
5.School of Mechanical and Aerospace Engineering,Konkuk University,Seoul,120 Neungdong-ro, Gwangjin-gu,05029,South Korea

Chang，Mengzhao,Jeong，Minuk,Park，Sungwook,et al. Study on predictions of spray target position of gasoline direct injection injectors with multi-hole using physical model and machine learning[J]. Fuel Processing Technology,2023,247.

Chang，Mengzhao,Jeong，Minuk,Park，Sungwook,Kim，Hyung Ik,Park，Jeong Hwan,&Park，Suhan.(2023).Study on predictions of spray target position of gasoline direct injection injectors with multi-hole using physical model and machine learning.Fuel Processing Technology,247.

Chang，Mengzhao,et al."Study on predictions of spray target position of gasoline direct injection injectors with multi-hole using physical model and machine learning".Fuel Processing Technology 247(2023).