Design and Optimization of Neural Networks To Estimate the Chamber Pressure in Internal Combustion Engines by an Indirect Method

详细信息    查看全文

• 作者：Fernando Cruz-Peragó ; n ; Francisco J. Jimé ; nez-Espadafor
• 刊名：Energy & Fuels
• 出版年：2007
• 出版时间：September 2007
• 年：2007
• 卷：21
• 期：5
• 页码：2627 - 2636
• 全文大小：326K
• 年卷期：v.21,no.5(September 2007)
• ISSN：1520-5029

文摘

A particular type of artificial neural network (ANN), with the aim of estimating the indicated pressure intocylinders from instantaneous angular speed measurement, has been developed: radial basis function (RBF).This is the main component of a methodology where input and output curves are parametrized. A modifiedRBF network from its general structure is designed to reduce the size of the network, approaching the hiddenlayer weights by means of polynomial functions. It makes it possible to use it in medium requirement PCs,such as in automobile applications. Results corresponding to different operating conditions of a single-cylinderdiesel engine (DE), a three-cylinder spark ignition engine (SIE), and a 16-cylinder vee power plant DE (V-16DE) are presented. Results show the accuracy and fast response of the network, making it feasible to use inonline diagnostics and control systems in engines, with very low cost (removing the use of piezoelectric sensors).