Search Results

This paper describes the applicable and capability of neural network as an artificial intelligence tool to determine the performance and emissions in a compressed natural gas direct injection (CNG-DI) engine. A feed-forward back-propagation artificial neural network (BPANN) approach is explored to predict the combustion performance in the term of indicated power and emissions in the appearance of CO and NO emissions level. A series of numerical computations by mean of computational fluid dynamics (CFD) code were carried out based on the statistics-based design of experiment method. The data for combustion process under various engine operating parameters at the fixed speed at 1000 rpm were obtained to train the developed artificial neural network (ANN).

Compressed natural gas (CNG) has been widely used as alternatives to gasoline and diesel in automotive engines. It is a very promising alternative fuel due to many reasons including adaptability to those engines, low in cost, and low emission levels. Unfortunately, when converting to CNG, engines usually suffer from reduced power and limited engine speed. These are due to volumetric loss and slower flame speed. Direct injection (DI) can mitigate these problems by injecting CNG after the intake valve closes, thus increasing volumetric efficiency. In addition, the high pressure gas jet can enhance the turbulence in the cylinder which is beneficial to the mixing and burning. However, conversion to direct fuel injection (DFI) requires a costly modification to the cylinder head to accommodate the direct injector and also can involve piston crown adjustment. This paper discusses a new alternative to converting to DFI using a device called Spark Plug Fuel Injector (SPFI).