Misfire Detection in IC Engine using Kstar Algorithm

Misfire in an IC Engine continues to be a problem leading to reduced fuel efficiency, increased power loss and emissions containing heavy concentration of 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 from these vibration signals were extracted. Out of these, useful features were identified using the J48 decision tree algorithm and selected features were used for classification using the Kstar algorithm. In this paper performance analysis of Kstar algorithm is presented.

[1]  Yunsong Wang,et al.  Real-time misfire detection via sliding mode observer , 2005 .

[2]  Stephen J. Citron,et al.  Cylinder-by-cylinder engine pressure and pressure torque waveform determination utilizing crankshaft speed fluctuations , 1989 .

[3]  Yaojung Shiao,et al.  Misfire Detection and Cylinder Pressure Reconstruction for SI Engines , 1994 .

[4]  Carlos Guardiola,et al.  A comparison of different methods for fuel delivery unevenness detection in Diesel engines , 2006 .

[5]  Giorgio Rizzoni,et al.  Estimate of indicated torque from crankshaft speed fluctuations: a model for the dynamics of the IC engine , 1989 .

[6]  N. R. Sakthivel,et al.  Use of histogram features for decision tree-based fault diagnosis of monoblock centrifugal pump , 2011, Int. J. Granul. Comput. Rough Sets Intell. Syst..

[7]  V. Sugumaran,et al.  A comparative study of Naïve Bayes classifier and Bayes net classifier for fault diagnosis of monoblock centrifugal pump using wavelet analysis , 2012, Appl. Soft Comput..

[8]  Zhixiong Li,et al.  Intelligent fault diagnosis method for marine diesel engines using instantaneous angular speed , 2012 .

[9]  Giorgio Rizzoni,et al.  Detection of Partial Misfire in IC Engines Using a Measurement of Crankshaft Angular Velocity , 1995 .

[10]  V. Sugumaran,et al.  Misfire identification in a four-stroke four-cylinder petrol engine using decision tree , 2010, Expert Syst. Appl..

[11]  V. Sugumaran,et al.  Effect of number of features on classification of roller bearing faults using SVM and PSVM , 2011, Expert Syst. Appl..

[12]  Wolfgang Wimmer,et al.  Misfire Detection by Evaluating Crankshaft Speed - A Means to Comply with OBDII , 1993 .