Search Results

The use of physical based mathematical models has been the standard when it comes to model development in the powertrain domain. More specifically, substitute models and diagnostic models (also known as virtual sensors) used to identify sensor fault are applied widely in the engine control in order to comply with on-board diagnostic (OBD) requirements. In the early years of calibration, the amount of data was limited: nowadays with extensive and detailed validations demanded by the sector, the vehicles are submitted to a bigger span of tests before reaching the final costumer. It is in this context that a neural network (NN) thermodynamic model of the engine coolant temperature (ECT) of an internal combustion engine (ICE) was created: the main drawback of any machine learning method is the amount of data necessary, but with data not being a problem, the NN can be quickly implemented and generalized to other projects, reducing time of development and costs for them.

To reduce atmospheric CO2 emissions as well as crude oil consumption, several countries have started to increase the ethanol content in gasoline. Brazil is unique in this respect, where pure ethanol fuel (E100) is offered on the market, however the use of pure ethanol as a fuel, significantly affects engine oil dilution. High oil dilution directly affects the injection system, during the fuel evaporation process. The evaporation behaviour is mainly characterized by the chemical composition of the fuel accumulated in the oil, as well as the engine warm-up behaviour. A high proportion of the accumulated hydrocarbons in the engine oil evaporates, as engine oil temperature increases. There can be dramatic effects on systems that are not designed to consider the evaporated hydrocarbons. Effects such as misfire or engine stall are well known phenomena of unconsidered fuel evaporation.