Fuzzy Pattern Classification Based Detection of Faulty Electronic Fuel Control (EFC) Valves Used in Diesel Engines
by
Umut Tugsal 1 and
Sohel Anwar 2,*
Umut Tugsal 1 and
Sohel Anwar 2,*
1
Cummins, Inc., Columbus, IN 47202, USA
2
Indiana University Purdue University Indianapolis, Indianapolis, IN 46202, USA
*
Author to whom correspondence should be addressed.
Machines 2014, 2(2), 99-119; https://doi.org/10.3390/machines2020099
Received: 19 January 2014 / Revised: 30 March 2014 / Accepted: 15 April 2014 / Published: 7 May 2014
(This article belongs to the Special Issue Advances in Control Engineering)
In this paper, we develop mathematical models of a rotary Electronic Fuel Control (EFC) valve used in a Diesel engine based on dynamic performance test data and system identification methodology in order to detect the faulty EFC valves. The model takes into account the dynamics of the electrical and mechanical portions of the EFC valves. A recursive least squares (RLS) type system identification methodology has been utilized to determine the transfer functions of the different types of EFC valves that were investigated in this study. Both in frequency domain and time domain methods have been utilized for this purpose. Based on the characteristic patterns exhibited by the EFC valves, a fuzzy logic based pattern classification method was utilized to evaluate the residuals and identify faulty EFC valves from good ones. The developed methodology has been shown to provide robust diagnostics for a wide range of EFC valves.
View Full-Text
Keywords:
EFC valve; fuzzy pattern recognition; fault diagnosis
▼
Show Figures
Figure 1
This is an open access article distributed under the Creative Commons Attribution License
MDPI and ACS Style
Tugsal, U.; Anwar, S. Fuzzy Pattern Classification Based Detection of Faulty Electronic Fuel Control (EFC) Valves Used in Diesel Engines. Machines 2014, 2, 99-119.
Show more citation formats
