Search Results

Recent advances in Variable Valve Actuation (VVA) methods have led to development of optimized valve timing strategies for a broad range of engine operating conditions. This study focuses on the cold-start period, which begins at engine cranking and lasts for approximately 1 minute thereafter. Cold-start is characterized by poor mixture preparation due to low component temperatures, aggravated by fixed valve timing which has historically been compromised to give optimal warm engine operation. In this study, intake cam phasing was varied to explore the potential benefit in hydrocarbon emissions and driveability obtainable for cold-start. A simple experimental approach was used to investigate the potential emissions benefits realizable through intake cam phasing. High speed cylinder pressure and Fast Flame Ionization Detector (FFID) engine-out hydrocarbon (HC) measurements were made to characterize instantaneous cold-start emissions and driveability.

Tremendous amount of useful information can be extracted from the cylinder pressure signal for engine combustion control. However, the physical cylinder pressure sensors are undesirably expensive and their health need to be monitored for fault diagnostic purpose as well. This paper presents the results of the development of a virtual cylinder pressure sensor (VCPS) with individual variable-oriented independent estimators. Two neural network-based independent cylinder pressure related variable estimators were developed and verified at steady state. The results show that these models can predict the variables correctly compared with the extracted variables from the measured physical cylinder pressure sensor signal. Good generalization capabilities of the developed models are observed in the sense that the models work well not only for the training data set but also for the new inputs that they have never been exposed to before.