Search Results

West Virginia University evaluated diesel oxidation catalysts (DOC) and lean-NOX catalysts as part of Diesel Emissions Control-Sulfur Effects (DECSE) project. In order to perform thermal aging of the DOC and lean-NOX catalysts simultaneously and economically, each catalyst was sized to accommodate half of the engine exhaust flow. Simultaneous catalyst aging was then achieved by splitting the engine exhaust into two streams such that approximately half of the total exhaust flowed through the DOC and half through the lean-NOX catalyst. This necessitated splitting the engine exhaust into two streams during emissions measurements. Throttling valves installed in each branch of the split exhaust were adjusted so that approximately half the engine exhaust passed though the active catalyst under evaluation and into a full flow dilution tunnel for emissions measurement.

A Saturn 1.9 liter engine has been converted for operation on either compressed natural gas or gasoline. A bi-fuel controller (BFC) that uses closed-loop control methods for both fuel delivery and spark advance has been developed. The performance and emissions during operation on each fuel have been investigated with the BFC, as well as the performance and emissions with the stock original equipment manufacturer (OEM) controller using gasoline. In-cylinder pressure was measured at a rate of 1024 points per revolution with piezoelectric pressure transducers flush-mounted in the cylinder head. The in-cylinder pressure was used in real time for ignition timing control purposes, and was stored by a data acquisition system for the investigation of engine stability and differences in the combustion properties of the fuels.

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.