Search Results

Performance predictions of advanced turbocharged engines are becoming difficult because conventional engine models are built using performance map data of turbochargers with a proportional integral derivative (PID) controller. Improving prediction capabilities under transient test cycles or real driving conditions is a challenging task. This study applies a machine learning technique to predict turbocharger performances with high accuracy under steady-state and transient conditions. The manipulated signals of engine speed and torque created based on Compressed High-Intensity Radiated Pulse (Chirp signal) and Amplitude-modulated Pseudo-Random Binary Signal (APRBS) are used as inputs to the engine testbed. Data from the engine experiments are used as training data for the AI-based turbocharger model. High prediction accuracy of the AI turbocharger model is achieved with the co-efficient of determination in the model, and cross-validation results are higher than 0.8.

For diesel emission control systems containing a Diesel Oxidation Catalyst (DOC) and a Catalyzed Soot Filter (CSF) the DOC is used to oxidize the additional fuel injected into the cylinder and/or the exhaust pipe for the purpose of increasing the CSF inlet temperature during the soot regeneration. Hydrocarbon (HC) oxidation performance of the DOC is affected by HC species as well as a catalyst design, i.e., precious metal species, support materials and additives. How engine-out HC species vary as a function of fuel supply conditions is not well understood. In addition, the relationship between catalyst design and oxidation activity of different hydrocarbon species requires further study. In this study, diesel fuel was supplied by in-cylinder, post injection and exhaust HC species were measured by a gas chromatograph-mass spectrometry (GC-MS) and a gas analyzer. The post injection timing was set to either 73°, 88° or 98° ATDC(after top dead center).

This paper describes the development of a High Speed Calculation Diesel Combustion Model that predicts combustion-related behaviors of diesel engines from passenger cars. Its output is dependent on the engine's operating parameters and on input from on-board pressure and temperature sensors. The model was found to be capable of predicting the engine's in-cylinder pressure, rate of heat release, and NOx emissions with a high degree of accuracy under a wide range of operating conditions at a reasonable computational cost. The construction of this model represents an important preliminary step towards the development of an integrated Model Based Control system for controlling combustion in diesel engines used in passenger cars.