A graphic pattern feature-mapping-based data-driven condition monitoring method for diesel engine malfunction identification and classification

Abstract

Effective condition monitoring of diesel engine can ensure the reliability of large-power machines and prevent catastrophic consequences. Cylinder pressure is capable of reflecting the whole combustion process of diesel engine, and hence can help to identify the malfunctions of the diesel engine during operation. In this paper, a graphic pattern feature-mapping method is proposed for graphic pattern feature recognition in data-driven condition monitoring. The graphic feature extraction and recognition are linked by labeled feature-mapping. It is used for identifying the running condition of the diesel engine via analyzing the cylinder pressure signal of the diesel engine. The different types of the malfunctions which are caused by different parts of the diesel engine such as induction system, valve actuating mechanism, fuel system, fuel injection system, etc. can be identified just by cylinder pressure signal. The bench experiment of a large-power diesel engine is performed to validate this graphic pattern recognition method. The results show that it has good accuracy on multi-malfunction identification and classification when the engine operates at one speed and one load.

Keywords

Feature-mapping graphic pattern recognition cylinder pressure signal malfunction identification diesel engine

Get full access to this article

View all access options for this article.

References

Watzenig D, Sommer MS and Steiner G. Model-based condition and state monitoring of large marine diesel engines. In: Bari S (ed.) Diesel engine – combustion, emissions and condition monitoring. London: Intech, 2013, pp. 217–230.

Jones NB and Li YH. A review of condition monitoring and fault diagnosis for diesel engines. Lubracation Science 2000; 6: 267–291.

Geng

Chen

. Investigation into piston-slap-induced vibration for engine condition simulation and monitoring. J Sound Vib 2005; 282: 735–751.

Porteiro

Collazo

Patiño

et al.

Diesel engine condition monitoring using a multi-net neural network system with nonintrusive sensors. Appl Therm Eng 2011; 31: 4097–4105.

Lin TR, Tan ACC, Ma L, et al. Estimating the loading condition of a diesel engine using instantaneous angular speed analysis. In: J Lee et al. (eds) Engineering asset management 2011. London: Springer, 2014, pp. 259–272.

Desbazeille

Randall

Guillet

et al.

Model-based diagnosis of large diesel engines based on angular speed variations of the crankshaft. Mech Syst Signal Process 2010; 24: 1529–1541.

Hargis

Taylor

Gozzo

. Condition monitoring of marine diesel engines through ferrographic oil analysis. Wear 1983; 90: 225–238.

Jiang

Gennish

et al.

Monitoring of diesel engine combustions based on the acoustic source characterisation of the exhaust system. Mech Syst Signal Process 2008; 22: 1465–1480.

Elamin F, Fan Y, Gu F, et al. Detection of diesel engine valve clearance by acoustic emission. In: Computing and engineering annual researchers’ conference 2009: CEARC’09. Huddersfield: University of Huddersfield, pp.7–13.

10.

Lin

Tan

ACC

et al.

Condition monitoring and fault diagnosis of diesel engines using instantaneous angular speed analysis. Proc IMechE, Part C: J Mechanical Engineering Science 2015; 229: 304–315.

11.

Flett

Bone

. Fault detection and diagnosis of diesel engine valve trains. Mech Syst Signal Process 2016; 72–73: 316–327.

12.

Sharkey AJC, Chandroth GO and Sharkey NE. Acoustic emission, cylinder pressure and vibration: a multisensor approach to robust fault diagnosis. In: IJCNN 2000: Proceedings of the IEEE-INNS-ENNS international joint conference on neural networks, Vol. VI (eds SI Amari, CL Giles, M Gori, et al.), IEEE Neural Network Council, International Neural Network Society, European Neural Network Society, Como, Italy, 24–27 July 2000, pp.223–228. USA: IEEE Computer Society.

13.

Lin

Tan

ACC

Mathew

. Condition monitoring and diagnosis of injector faults in a diesel engine using in-cylinder pressure and acoustic emission techniques. Dyn Sustainable Eng 2011; 1: 454–463.

14.

Payri

Broatch

Tormos

et al.

New methodology for in-cylinder pressure analysis in direct injection diesel engines – application to combustion noise. Meas Sci Technol 2005; 16: 540–547.

15.

Watzenig

Sommer

Steiner

. Engine state monitoring and fault diagnosis of large marine diesel engines. Elektrotech Inform 2009; 126: 173–179.

16.

Antory

. Application of a data-driven monitoring technique to diagnose air leaks in an automotive diesel engine: a case study. Mech Syst Signal Process 2007; 21: 795–808.

17.

Ulukaya

Erdem

. Gaussian mixture model based estimation of the neutral face shape for emotion recognition. Digital Signal Process 2014; 32: 11–23.

18.

Yuan

Chu

. Fault diagnosis based on support vector machines with parameter optimisation by artificial immunisation algorithm. Mech Syst Signal Process 2007; 21: 1318–1330.

19.

Huang JS and Zhang PJ. Fault diagnosis for diesel engines based on discrete hidden Markov model. In: ICICTA: 2009 second international conference on intelligent computation technology and automation, vol II, proceedings. Changsha, Peoples Republic of China, 10–11 October 2009, pp.513–516. USA: IEEE Computer Society.

20.

Boutros

Liang

. Detection and diagnosis of bearing and cutting tool faults using hidden Markov models. Mech Syst Signal Process 2011; 25: 2102–2124.

21.

Figueiredo

MAT

Jain

. Unsupervised learning of finite mixture models. IEEE Trans Pattern Anal Mach Intell 2002; 24: 381–396.

22.

et al.

Hidden Markov model-based fault diagnostics method in speed-up and speed-down process for rotating machinery. Mech Syst Signal Process 2005; 19: 329–339.

23.

Rabiner

Juang

. Fundamentals of speech recognition, New Jersey: Prentice Hall, 1993.