Neuro-Fuzzy Modeling of Automotive SI-Engine Characteristics

Abstract In automotive technology, the behaviour of SI-combustion engines is often characterised by the dependency of the engine torque on the engine speed and the throttle angle. Especially for control and simulation purposes it is important to provide an easy possibility to extract a formal description of an engine characteristic map from data measured on an engine test stand. This paper describes a way to replace the conventionally used look-up-tables by neural network or fuzzy logic representations and to adapt them on-line to measured signals. In addition to that, a neuro-fuzzy approach is discussed as well.