Misfire detection in an IC engine using vibration signal and decision tree algorithms

Abstract

Misfire in an IC engine continues to be a problem producing consequences like reduced fuel efficiency, increased power loss and emissions containing heavy concentration of uncombusted hydrocarbons. Misfiring creates a unique vibration pattern attributed to a particular cylinder. Useful features can be extracted from these patterns and can be analyzed to detect misfire. Statistical features of these vibration signals are extracted. Out of these, useful features were identified using the J48 decision tree algorithm and selected features are used with various decision trees. Classification accuracies from J48 algorithm, Best first tree algorithm, random forest tree algorithm, functional tree algorithm and linear model tree algorithm are compared and the best algorithm for such a system is suggested.