In-Cylinder Pressure based Modeling for Injection Parameters by PCA with Feature Correlation Analysis Johannes Kepler University Linz

Format:

Conference/Event

Author/Creator:

Stadlbauer, Stadlbauer, author.

Contributor:

Del Re, Luigi

Waschl, Harald

Conference Name:

11th International Conference on Engines & Vehicles (2013-09-15 : Capri, Italy)

Language:

English

Physical Description:

1 online resource

Place of Publication:

Warrendale, PA SAE International 2013

Summary:

Modern Diesel engines have become complex systems with a high number of available sensor information and degrees of freedom in control. Due to recent developments in production type in-cylinder pressure sensors, there is again an upcoming interest for in-cylinder pressure based applications. Besides the standard approaches, like to use it for closed loop combustion control, also estimation and on-board diagnostics have become important topics. Not surprising in general the trend is to utilize those sensors for as many tasks as possible.Consequently this work focuses on the estimation of the injection parameters based on the indicated pressure signal information which can be seen as first step of a combustion control based on desirable indicated pressure characteristics which may be utilized for e.g. the minimization of NOx emissions.Currently the acquisition of the cylinder pressure traces can be done in real-time by fast FPGA (Field Programmable Gate Array) based systems. However, a crucial part of such cylinder pressure based approaches is to extract the information of the cylinder pressure traces since the raw pressure signals are often available with a resolution of 0.5 CAD and thus per engine cycle 1440 data points are recorded. To post process this information different data reduction techniques are available. Whichever technique used, two differing tasks have to be concerned, on one hand the number of inputs should be as low as possible to keep the model structure simple, but still the significant information should be preserved. However, the number of necessary quantities, e.g. in the case of principle component analysis (PCA) the so called features, cannot be straightforward determined and may depend on the modeled quantity or model type.To this end in this work a PCA reduction approach is extended to tackle three different issues: First, the optimal amount of features for the start of the main injection and the main injection amount are determined by data analysis. And second it is analyzed, whether an identical number of features and amount of parameters is applicable for both injection parameter models. The last issue considers if a direct relation between a certain feature and the injection parameters are detectable

Notes:

Vendor supplied data

Publisher Number:

2013-24-0148

Access Restriction:

Restricted for use by site license