This paper evaluates the use of fuzzy unordered rule induction algorithm (FURIA) with correlation based feature selection (CFS) embedded feature subset selection as a tool for misfire detection. The vibration data of the automobile engine contains the engine performance data along with multitudes of other information. The decoding of engine misfire condition was achieved by processing the statistical features of the signals. The quantum of information available at a given instant is enormous and hence suitable techniques are adopted to reduce the computational load due to excess information. The effect of recursive entropy discretiser as feature size reduction tool and CFS based feature subset selection is analysed for performance improvement in the FURIA model. The FURIA based model is found to have a consistent high classification accuracy of around 88% when designed as a multi class problem and approaches 100% when the system is modeled as a two-class problem. From the results obtained the authors conclude that the combination of statistical features and FURIA algorithm is suitable for detection of misfire in spark ignition engines. © 2011 by IJAI.
cited By (since 1996)4
B. S. Devasenapati and Ramachandran, K. I., “Hybrid fuzzy model based expert system for misfire detection in automobile engines”, International Journal of Artificial Intelligence, vol. 7, pp. 47-62, 2011.