Fault Detection of Fuel Injectors Based on One-Class Classifiers

Dimitrios Moshou, Athanasios Natsis, Dimitrios Kateris, Xanthoula-Eirini Pantazi, Ioannis Kalimanis, Ioannis Gravalos

Agricultural Engineering Laboratory, Aristotle University of Thessaloniki, Thessaloniki, Greece.
Department of Biosystems Engineering, Technological Educational Institute of Thessaly, Larissa, Greece.
Department of Exploitation of Natural Resources and Agricultural Mechanics, Agricultural University of Athens, Athens, Greece.

DOI: 10.4236/mme.2014.41003                

Abstract

Fuel injectors are considered as an important component of combustion engines. Operational weakness can possibly lead to the complete machine malfunction, decreasing reliability and leading to loss of production. To overcome these circumstances, various condition monitoring techniques can be applied. The application of acoustic signals is common in the field of fault diagnosis of rotating machinery. Advanced signal processing is utilized for the construction of features that are specialized in detecting fuel injector faults. A performance comparison between novelty detection algorithms in the form of one-class classifiers is presented. The one-class classifiers that were tested included One-Class Support Vector Machine (OCSVM) and One-Class Self Organizing Map (OCSOM). The acoustic signals of fuel injectors in different operational conditions were processed for feature extraction. Features from all the signals were used as input to the one-class classifiers. The one-class classifiers were trained only with healthy fuel injector conditions and compared with new experimental data which belonged to different operational conditions that were not included in the training set so as to contribute to generalization. The results present the effectiveness of one-class classifiers for detecting faults in fuel injectors.

Keywords

Fuel Injectors; Fault Detection; Acoustics; Neural Networks; One-Class Classifiers

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	A. Albarbar, F. Gu, A. D. Ball and A. Starr, “Acoustic Monitoring of Engine Fuel Injection Based on Adaptive Filtering Techniques,” Applied Acoustics, Vol. 71, No. 12, 2010, pp. 1132-1141. http://dx.doi.org/10.1016/j.apacoust.2010.07.001
[2]	F. Elamin, F. Gu and A. Ball, “Diesel Engine Injector Faults Detection Using Acoustic Emissions Technique,” Modern Applied Science, Vol. 4, No. 9, 2010, pp. 3-13.
[3]	S. Zahi, J. Ragot and F. Kratz, “Structured Hypothesis Tests Based Diagnosis: Application to a Common Rail Diesel Injection System,” Advances in Vehicle Control and Safety, Genova, 2004.
[4]	T. R. Lin, A. C. C. Tan and J. Mathew, “Condition Monitoring and Diagnosis of Injector Faults in a Diesel Engine Using In-Cylinder Pressure and Acoustic Emission Techniques,” 14th Asia Pacific Vibration Conference APVC 2011, The Hong Kong Polytechnic University, 5-8 December 2011.
[5]	F. Elamin, Y. Fan and F. Gu, “Andrew Ball Detection of Diesel Engine Injector Faults Using Acoustic Emissions,” COMADEM 2010: Advances in Maintenance and Condition Diagnosis Technologies towards Sustainable Society, Nara, 28 June-2 July 2010.
[6]	L. Jianmin, S. Yupeng, Z. Xiaoming, X. Shiyong and D. Lijun, “Fuel Injection System Fault Diagnosis Based on Cylinder Head Vibration Signal,” Procedia Engineering, Vol. 16, 2011, pp. 218-223. http://dx.doi.org/10.1016/j.proeng.2011.08.1075
[7]	A. Albarbar, F. Gu and A. D. Ball, “Diesel Engine Fuel Injection Monitoring Using Acoustic Measurements and Independent Component Analysis,” Measurement, Vol. 43, No. 10, 2010, pp. 1376-1386. http://dx.doi.org/10.1016/j.measurement.2010.08.003
[8]	V. Crupi, E. Guglielmino and G. Millazo, “Neural-Network-Based System for Novel Fault Detection in Rotating Machinery,” Journal of Vibration and Control, Vol. 10, No. 8, 2004, pp. 1137-1150. http://dx.doi.org/10.1177/1077546304043543
[9]	SPM Instrument http://www.spminstrument.se/en/Products/Portable-instruments/BearingChecker/
[10]	Y. Lei, Z. He and Y. Zi, “A New Approach to Intelligent Fault Diagnosis of Rotating Machinery,” Expert Systems with Applications, Vol. 35, 2008, pp. 1593-1600. http://dx.doi.org/10.1016/j.eswa.2007.08.072
[11]	D. Moshou, D. Kateris, I. Gravalos, S. Loutridis, N. Sawalhi, Th. Gialamas, P. Xyradakis and Z. Tsiropoulos, “Determination of Fault Topology in Mechanical Subsystems of Agricultural Machinery Based on Feature Fusion and Neural Networks,” 4th International Conference TAE 2010, Czech University of Life Sciences Prague, 2010, pp. 448-453.
[12]	B. Scholkopf, J. Platt, J. Shawe-Taylor, A. Smola and R. Williamson, “Estimating the Support of a High Dimensional Distribution,” Neural Computation, Vol. 13, No. 7, 2001, pp. 1443-1472. http://dx.doi.org/10.1162/089976601750264965
[13]	A. Ypma, “Learning Methods for Machine Vibration Analysis and Health Monitoring,” Ph.D. Dissertation, Delft University of Technology, Delft, 2001.
[14]	R. Saunders and J. S. Gero, “A Curious Design Agent: A Computational Model of Novelty-Seeking Behaviour in Design,” Proceedings of the 6th Conference on Computer Aided Architectural Design Research in Asia (CAADRIA 2001), Sydney, 19-21 April 2001, pp. 345-350.