Search Results

A real-time approach has been developed and assessed to control BMEP (brake mean effective pressure) and MFB50 (crank angle at which 50% of fuel mass has burnt) in a Euro 6 1.6L GM diesel engine. The approach is based on the use of feed-forward ANNs (artificial neural networks), which have been trained using virtual tests simulated by a previously developed low-throughput physical engine model. The latter is capable of predicting the heat release and the in-cylinder pressure, as well as the related metrics (MFB50, IMEP - indicated mean effective pressure) on the basis of an improved version of the accumulated fuel mass approach. BMEP is obtained from IMEP taking into account friction losses. The low-throughput physical model does not require high calibration effort and is also suitable for control-oriented applications. However, control tasks characterized by stricter demands in terms of computational time may require a modeling approach characterized by a further lower throughput.

A production SI engine originally designed at Fiat Auto to operate with unleaded gasoline was converted to run on natural gas. To that end, in addition to designing and building the CNG fuel plant, it was necessary to replace the multipoint electronic module for injection-duration and ignition-timing control with an ECM designed to obtain multipoint sequential injection. The engine was modified so as to work either with gasoline or natural gas. For the present investigation, however, the engine configuration was not optimized for running on methane, in order to compare the performance of the engine operated by the two different fuels with the same compression ratio. In fact, the engine is also interesting as a dual-fuel engine because of its relatively high compression ratio ≈10.5 that is almost suitable for CNG operation. The engine had the main features of being a multivalve, fast-burn pent-roof chamber engine with a variable intake-system geometry.