Input choices of Particulate Matter Models for Diesel Engines
Diesel engines produce a variety of particles generically classified as diesel particulate matter (PM) mainly due to incomplete combustion. The increasingly stringent emissions regulations require that engine manufacturers must reduce the PM in the engine emission. The prediction of the PM emission is one of the key technologies that could help to reduce the PM. However, choice of the inputs is the most important task for the prediction of PM emission. This paper illustrated the impact of inputs on the accuracy of the PM prediction based on an autoregressive model with exogenous inputs (NLARX). The input parameters are analysed based on the PM formation mechanism, the knowledge of the combustion process and an insight of the underlying physics. The method called as the Principal Component Analysis (PCA) is also used to decide the number of the inputs (torque, speed and their derivatives) on the PM prediction.
Diesel engine Particulate Matter model prediction neural network.
Jiamei Deng Andrzej Ordys Yawei Wang
School ofMechanicall and Automotive Engineering, Kingston University London School of Mechanicall and Automotive Engineering, Kingston University London
国际会议
The 24th Chinese Control and Decision Conference (第24届中国控制与决策学术年会 2012 CCDC)
太原
英文
1980-1985
2012-05-23（万方平台首次上网日期，不代表论文的发表时间）