Distribution & Access For Publication Downloads News About Us Contact Us
Paper Titles
A Review of Laser Doppler Vibrometry for Structural Health Monitoring Applications
p.1
Analysis of Experimental Data in the Context of Safety against Derailment of a Railway Vehicle, Using the Energy Method
p.16
Application of Image Based Methods for Monitoring and Measurements of Structures in Power Stations
p.24
Applications of Self-Organizing Maps in Structural Health Monitoring
p.37
Artificial Neural Network Based Fault Diagnosis of IC Engines
p.47
Assessment of Bonded Patch Bridge Repairs Using Acoustic Emission and Acousto-Ultrasonics
p.57
Condition Monitoring System for Light Rail Vehicle and Track
p.66
Damage Detection in Gearboxes Considering Intermittent Faults and Time-Varying Loads
p.76
Development of Lamb Waves-Based SHM Systems
p.87

Artificial Neural Network Based Fault Diagnosis of IC Engines

Article Preview

Abstract:

Fault diagnosis is important to avoid unforeseen failures of IC engines, but normally requires an expert to interpret analysis results. Artificial Neural Networks are potential tools for the automated fault diagnosis of IC engines, as they can learn the patterns corresponding to various faults. Most engine faults can be classified into two categories: combustion faults and mechanical faults. Misfire is a typical combustion fault; piston slap and big end bearing knock are common mechanical faults. The automated diagnostic system proposed in this paper has three main stages, each stage including three neural networks. The first stage is the fault detection stage, where the neural networks detect whether there are faults in the engine and if so which kind. In the second stage, based on the detection results, the severity of the faults was identified. In the third stage, the neural networks localize which cylinder has a fault. The critical thing for a neural network is its input feature vector, and a previous study had indicated a number of features that should differentiate between the different faults and their location, based on advanced signal processing of the vibration signals measured for different normal and fault conditions. In this study, an advanced feature selection technology was employed to select the significant features as the inputs to networks. The input vectors were separated into two groups, one for training the network, and the other for its validation. Finally it has been demonstrated that the neural network based system can automatically differentiate and diagnose a number of engine faults, including location and severity.

You might also be interested in these eBooks
Structural Health Monitoring II View Preview

Info:

Periodical:

Key Engineering Materials (Volume 518)

Pages:

47-56

DOI:

https://doi.org/10.4028/www.scientific.net/KEM.518.47

Citation:

Cite this paper

Online since:

July 2012

Authors:

Jian Chen, Robert Randall, Bart Peeters, Wim Desmet, Herman Van der Auweraer

Export:

RIS, BibTeX

Price:

Permissions:

Request Permissions

References

[1] Y. Ren, Detection of knocking combustion in diesel engines by inverse filtering of structural vibration signals. PhD Dissertation, the University of New South Wales, Australia, (1999).

Google Scholar

[2] Rizzoni, G., Estimate of indicated torque from crankshaft fluctuations: A model for the dynamics of the internal combustion engine. IEEE Transaction Vehicle Technology, 38(3), 168–179, (1989).

DOI: 10.1109/25.45470

Google Scholar

[3] Zhang, Y., Randall, R.B., The In-Cylinder Pressure Reconstruction and Indicated Torque Estimation Based on Instantaneous Engine Speed and one Measured In-Cylinder Pressure, Comadem Conference, Faro, Portugal, (2007).

DOI: 10.4271/2015-01-1249

Google Scholar

[4] Geng Z., Chen J., Investigation into piston-slap-induced vibration for engine condition simulation and monitoring, Journal of Sound and Vibration 282, 735–751, (2007).

DOI: 10.1016/j.jsv.2004.03.057

Google Scholar

[5] M. Desbazeille, R.B. Randall, F. Guillet, M. El Badaoui, C. Hoisnard. Model-based diagnosis of large diesel engines based on angular speed variations of the crankshaft. Mechanical System and Signal Processing, vol 24, issue 5, pages 1529-1541, (2011).

DOI: 10.1016/j.ymssp.2009.12.004

Google Scholar

[6] R.B. Randall. Training neural networks for bearing diagnostics using simulated feature vectors. AI-MECH Symposium, Gliwice, Poland, 14-16 November (2001).

Google Scholar

[7] Israel E. Alguindigue, Anna Loskiewicz-Buczak, and Robert E. Uhrig, Monitoring and Diagnosis of Rolling Element Bearings Using Artificial Neural Networks, IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, VOL. 40, NO. 2, APRIL (1993).

DOI: 10.1109/41.222642

Google Scholar

[8] B. A. Paya, I. L. Esat and M. N. M. Badi, Artificial neural network based fault diagnostics of rotating machineryusing wavelet transforms as a preprocessor. Mechanical Systems and Signal Processing, Vol 11, 751–765, (1997).

DOI: 10.1006/mssp.1997.0090

Google Scholar

[9] Jian Chen, Robert Randall, Vibration Signal Processing of Piston Slap and Bearing Knock in IC Engines, Surveillance 6, Compiegne, France, 25-26 Oct (2011).

Google Scholar

[10] Jian Chen, Robert Randall, A Vibration Signal Based Simulation Model for the Misfire of Internal Combustion Engines, CM2011 & MFPT2011 Cardiff, UK, 20-22 Jun (2011).

Google Scholar

[11] J. Antoni, R. B. Randall, The spectral kurtosis: application to the vibratory surveillance and diagnostics of rotating machines, Mechanical Systems and Signal Processing (20), 308–331, (2006).

DOI: 10.1016/j.ymssp.2004.09.002

Google Scholar

[12] Isabelle Guyon, Andr´e Elisseeff, An Introduction to Variable and Feature Selection, Journal of Machine Learning Research Vol3 (2003) 1157-1182.

Google Scholar

[13] Oswaldo Ludwig and Urbano Nunes, Novel Maximum-Margin Training Algorithms for Supervised Neural Networks, IEEE Transaction on Neural Networks, Vol 21, No 6 June 972-983, (2010).

DOI: 10.1109/tnn.2010.2046423

Google Scholar

[14] D. E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, Addison Wesley Publishing Company, January (1989).

Google Scholar

[15] Chris Ding, Hanchuan Peng, Minimum Redundancy Feature Selection from Microarray Gene Expression Data. Proceedings of the Computational Systems Bioinformatics, Stanford, CA, 11-14 Aug, (2003).

DOI: 10.1109/csb.2003.1227396

Google Scholar

[16] Hagan, M. T., H. B. Demuth, and M. H. Beale, Neural Network Design, Boston, MA: PWS Publishing, (1996).

Google Scholar

Scientific.Net is a registered brand of Trans Tech Publications Ltd
© 2024 by Trans Tech Publications Ltd. All Rights Reserved