Advanced signal processing for misfire detection in automotive engines

Authors:

Abstract
The paper presents an application of artificial neural networks to the reliable detection of misfires in automotive engines. By government regulations, automobiles an required to be equipped with instrumentation to detect engine misfires and to alert the driver whenever the misfire rate has the potential to affect the health of emission control systems. A relevant model for the powertrain dynamics is developed as well as an explanation of the instrumentation. The basis for using a neural network to detect these misfires is explained and experimental system performance data (including error rates) an given. It is shown that the present method has the potential to meet the government mandated requirements.

This publication has 2 references indexed in Scilit: