SI Engines Misfire Detection by Using NARX Neural Network

According to OBD II standard, in order to prevent the pollution and mechanical damages of engines, detection of engine’s misfire is one of the most significant rules of this standard. In this paper, a crankshaft speed fluctuation model is used for misfire detection. In this method, a NARX neural network is utilized to model an inverse system from the engine crankshaft speed signal to the firing event signal. The engine misfire detection is based on the output of this inverse system. According to the results that have been obtained in simulations of EF7 engine’s data, the network could detect misfire well.

Keywords:

Misfire detection , NARX neural network , Engine speed fluctuation , Firing events