Abstract
The objective of this work is the fault diagnosis in diesel engines to assist the predictive maintenance, through the analysis of the variation of the pressure curves inside the cylinders and the torsional vibration response of the crankshaft. Hence a fault simulation model based on a zero-dimensional thermodynamic model was developed. The adopted feature vectors were chosen from the thermodynamic model and obtained from processing signals as pressure and temperature inside the cylinder, as well as, torsional vibration of the engines flywheel. These vectors are used as input of the machine learning technique in order to discriminate among several machine conditions, such as normal, pressure reduction in the intake manifold, compression ratio and amount of fuel injected reduction into the cylinders. The machine learning techniques for classification adopted in this work were the multilayer perceptron (MLP) and random forest (RF).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hoffman, A.J., van der Merwe, N.T.: The application of neural networks to vibrational diagnostics for multiple fault conditions. J. Comput. Stand. Interfaces 24, 139–149 (2002)
Haykin, S.: Neural Networks: A Comprehensive Foundation, Prenctice-Hall, Upper Saddle River (1999)
Gutirrez, R.H.R.: Simulação e identificação de falhas de motores diesel, 128p. D.Sc. Thesis-Universidade Federal do Rio de Janeiro (UFRJ) (2016)
Yang, B.S., Di, X., Han, T.: Random forests classifier for machine fault diagnosis. J. Mech. Sci. Technol. 22, 1716–1725 (2008)
de Lima, A.A., Prego, T.M., Netto, S.L., da Silva, E.A.B., Gutierrez, R.H.R., Monteiro, U.A., Troyman, A.C.R., Silveira, F.J.C., Vaz, L.: On fault classification in rotating machines using fourier domain features and neural networks. In: Proceedings of the IEEE Latin American Symposium on Circuits and Systems (LASCAS), Cusco, Peru, p. 1–4, March 2013
Pestana-Viana, D., Zambrano-Lopez, R., de Lima, A.A., Prego, T.D.M., Netto, S.L., da Silva, E.A.B.: The influence of feature vector on the classification of mechanical faults using neural networks. In: Proceedings of the IEEE Seven Latin American Symposium on Circuits and Systems (LASCAS), Pará, Brazil, p. 115–118, March 2016
Mendes, A.S.: Development and validation of a methodology for torsional vibrations analysis in internal combustion engines, 135p. M.Sc. Dissertation–Universidade Estadual de Campinas (UEC) (2005)
Monteiro, U.: Thermodynamic simulation of gas turbines for fault diagnosis. D.Sc. Thesis–Universidade Federal do Rio de Janeiro (UFRJ) (2010)
Heywood, J.: Internal Combustion Engine Fundamentals. Mechanical Engineering. McGraw-Hill, New York (1988)
Stone, R.: Introduction to Internal Combustion Engines, 2nd edn. Macmillan, Basingstoke (1992)
Mendes, A.S.: Development and validation of a methodology for torsional vibrations analysis in internal combustion engines (2005)
Inman, D.J.: Engineering Vibrations, 4th edn. Pearson, London (2014)
Rao, S.S.: Mechanical Vibrations, 5th edn. Pearson, London (2010). Recherche
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Pestana-Viana, D. et al. (2019). Application of Machine Learning in Diesel Engines Fault Identification. In: Cavalca, K., Weber, H. (eds) Proceedings of the 10th International Conference on Rotor Dynamics – IFToMM . IFToMM 2018. Mechanisms and Machine Science, vol 61. Springer, Cham. https://doi.org/10.1007/978-3-319-99268-6_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-99268-6_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-99267-9
Online ISBN: 978-3-319-99268-6
eBook Packages: EngineeringEngineering (R0)