Title :
A robust algorithm for identifying different types of engine misfires
Author :
Alkhateeb, Abedulah M. ; Das, Manohar
Author_Institution :
Dept. of Electr. & Syst. Eng., Oakland Univ., Rochester, MI, USA
Abstract :
This paper introduces a robust algorithm for engine misfire detection that can detect and identify different kinds of engine misfires under various speed and load conditions. The overall algorithm consists of two main steps. First, it employs a frequency domain pattern classifier to detect and identify the type of misfire, and then it utilizes a generalized likelihood test to locate the misfire instances. This paper is primarily focused on the first task only. Results of extensive tests on a six-cylinder engine are presented.
Keywords :
frequency-domain analysis; identification; internal combustion engines; pattern classification; road vehicles; engine misfire detection; engine misfire identification; frequency domain pattern classifier; generalized likelihood test; load conditions; misfire type; normalization; robust identification algorithm; six-cylinder engine tests; speed conditions; Costs; Engines; Event detection; Fluctuations; Frequency domain analysis; Gears; Pattern classification; Roads; Robustness; Testing;
Conference_Titel :
Circuits and Systems, 2002. MWSCAS-2002. The 2002 45th Midwest Symposium on
Print_ISBN :
0-7803-7523-8
DOI :
10.1109/MWSCAS.2002.1187074
