Search Results

Minimizing fuel consumption is emerging as the next major challenge for engine control and calibration, even as the requirements of complying with ever lower transient emissions regulations cannot be underestimated. Meeting these difficult and apparently conflicting emissions and efficiency goals is becoming increasingly onerous as engine and aftertreatment control complexity increases. Conventional engine calibration techniques are by nature time-intensive, ad-hoc and repetitive, resulting in low productivity of test facilities and engineering effort. Steady state engine mapping methods, such as design of experiments, do little to ensure transient emissions compliance or fuel consumption optimization. A new model-based Rapid Transient Calibration system has been developed, tested and validated using a 2007 production-specification Detroit Diesel Series 60 heavy-duty diesel engine.

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.

Speed-time and video data were logged for tractor-trailers performing local deliveries in Akron, OH. and Richmond, VA. in order to develop an emissions test schedule that represented real truck use. The data bank developed using these logging techniques was used to create a Yard cycle, a Freeway cycle and a City-Suburban cycle by the concatenation of microtrips. The City-Suburban driving cycle was converted to a driving route, in which the truck under test would perform at maximum acceleration during certain portions of the test schedule. This new route was used to characterize the emissions of a 1982 Ford tractor with a Cummins 14 liter, 350 hp engine and a 1998 International tractor with a Cummins 14 liter, 435 hp engine. Emissions levels were found to be repeatable with one driver and the driver-to-driver variation of NOx was under 4%, although the driver-to-driver variations of CO and PM were higher.