Search Results

Artificial Intelligence is becoming very important and useful in several scientific fields. Machine learning methods, such as neural networks and decision trees, are often proposed in applications for internal combustion engines as virtual sensors, faults diagnosis systems and engine performance optimization. The high pressure of the intake air coupled with the demand of lean conditions, in order to reduce emissions, have often close relationship with the knock events. Fuels autoignition characteristics and flame front speed have a significant impact on knock phenomenon, producing high internal cylinder pressures and engine faults. The limitations in using pressure sensors in the racing field and the challenge to reduce the costs of commercial cars, push the replacement of a hardware redundancy with a software redundancy.

Water injection in highly boosted gasoline direct injection (GDI) engines has become an attractive area over the last few years as a way of increasing efficiency, enhancing performance and reducing emissions. The technology and its effects are not new, but current gasoline engine trends for passenger vehicles have several motivations for adopting this technology today. Water injection enables higher compression ratios, optimal spark timing and elimination of fuel enrichment at high load, and possibly replacement of EGR. Physically, water reduces charge temperature by evaporation, dilutes combustion, and varies the specific heat ratio of the working fluid, with complex effects. Several of these mutually intertwined aspects are investigated in this paper through computational fluid dynamics (CFD) simulations, focusing on a turbo-charged GDI engine with port water injection (PWI). Different strategies for water injection timing, pressure and spray targeting are investigated.