基于神经网络的汽油HCCI发动机空燃比控制策略  

Air/Fuel Ratio Control of Gasoline HCCI Engine Based on Neural Network

作　　者：周能辉[1] 谢辉[1] 赵华[1] 陈韬[1] 

机构地区：[1]天津大学内燃机燃烧学国家重点实验室,天津300072

出　　处：《农业机械学报》2009年第6期1-5,共5页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家自然科学基金资助项目(50476064);国家重点基础研究发展规划项目(2001CB209204)

摘　　要：均质压缩燃烧(HCCI)在控制上存在难点,其中关键是基于循环的空燃比实时控制。HCCI汽油机没有能直接表征发动机每循环进气量的参数,因此,采用动态递归神经网络(Elman网络)预测HCCI发动机每循环的进气量。通过氧传感器闭环和瞬态工况中的油膜补偿,实现对HCCI发动机的稳态及瞬态工况下空燃比的精确控制。试验表明:汽油HCCI发动机神经网络预测模型及空燃比控制策略能满足HCCI发动机实时控制的需求。Homogeneous charge compression ignition （HCCI） combustion is still confronted with problems in cycle-to-cycle air/fuel ratio control. Because there are no parameters that characterize air inflow in each cycle, dynamic recurrent neural network （Elman） was adopted for forecasting engine＇s air inflow in each cycle. Based on accurate air inflow in each cycle, accurate air/fuel ratio control is achieved in steady and transient operating conditions by oxygen sensor＇s closed loop control and fuel film＇s compensation. The experiment results show that prediction model based on neural network and air/ fuel ratio control strategy can meet the need of real-time control over HCCI operation.

关 键 词：汽油发动机 均质充量压缩燃烧 空燃比 控制 神经网络 

分 类 号：TK411.28[动力工程及工程热物理—动力机械及工程]