基于高斯过程的TGDI发动机充气模型试验研究

Experimental Research on Charging Model of A TGDI Engine Based-on Gauss Process

采用高斯过程(Gauss Process,GP)对增压直喷汽油机充气模型开展研究,首先以发动机进气过程物理特性为理论基础,阐述模型控制原理,并基于高斯过程的发动机充气模型,采用稳态和慢动态数据完成模型精度的验证,结果表明:模型精度较高,可作为黑盒模型用于ECU控制算法开发及离线标定功能开发。此外,研究了减少训练数据点和减少输入参数对高斯模型精度的影响。

In this paper,the charging model of Turbocharged Gasoline Direct Injection(TGDI)engine is studied by using Gauss Process(GP).Through the analysis of the physical characteristics of the intake state,the basic principle of the charging model is expounded,and the relative intake mass flow is evaluated by using the Gauss process model.The steady and slow dynamic data are used to verify the accuracy of the model.It can be used as a black box model for the development of ECU control algorithm and offline calibration development.This paper also studies the influence of reducing training data points and input parameters on the accuracy of Gaussian model.