Search Results

This paper explores the feasibility of using in-cylinder pressure-based variables to predict gaseous exhaust emissions levels from a Navistar T444 direct injection diesel engine through the use of neural networks. The networks were trained using in-cylinder pressure derived variables generated at steady state conditions over a wide speed and load test matrix. The networks were then validated on previously “unseen” real-time data obtained from the Federal Test Procedure cycle through the use of a high speed digital signal processor data acquisition system. Once fully trained, the DSP-based system developed in this work allows the real-time prediction of NOX and CO2 emissions from this engine on a cycle-by-cycle basis without requiring emissions measurement.

The emissions reduction benefits of Fischer-Tropsch (FT) diesel fuel have been shown in several recent published studies in both engine testing and in-use vehicle testing. FT diesel fuel shows significant advantages in reducing regulated engine emissions over conventional diesel fuel primarily to: its zero sulfur specification, implying reduced particulate matter (PM) emissions, its relatively lower aromaticity, and its relatively high cetane rating. However, the actual effect of FT diesel formulation on the in-cylinder combustion characteristics of unmodified modern heavy-duty diesel engines is not well documented. As a result, a Navistar T444E (V8, 7.3 liter) engine, instrumented for in-cylinder pressure measurement, was installed on an engine dynamometer and subjected to steady-state emissions measurement using both conventional Federal low sulfur pump diesel and a natural gas-derived FT fuel.