基于人工神经网络的汽油机稳态排放模型辨识  

Identification of Static Exhaust Emission Model in Gasoline Engine Based on Artificial Neural Network

作　　者：刘玉长[1] 李君[1] 

机构地区：[1]中南大学能源科学与工程学院,湖南长沙410083

出　　处：《现代车用动力》2009年第2期32-35,共4页Modern Vehicle Power

摘　　要：在CF4g18电控汽油机的稳态排放物测量试验的基础上,利用径向基(RBF)神经网络对该发动机进行了污染物的辨识,通过选定该网络的结构和各参数,并对试验数据进行学习,得到了该发动机污染物的辨识模型,该模型输出值与试验值误差较小,可以精确地反映该发动机在不同转速和扭矩下的各污染物排放特性。Based on the experiment results of static exhaust emission measurement in the gasoline engine of model CF4g18,the identification of exhaust emission model of the engine is made by RBF neural network.The identification of the model is carried out after the architecture and parameters in the neural network are determined and training of the model is made according to test data.The error between the output in the model of neutral network and test data is small,and exhaust emission performance of the engine at different speed and torque condition can be precisely obtained in the model.

关 键 词：汽油机 神经网络 辨识 污染物排放 

分 类 号：TK411.5[动力工程及工程热物理—动力机械及工程]