This work attempts to introduce a new intelligent method for condition monitoring of diesel engines. Diesel engine is one of the most important power providers for various industrial applications, including automobiles, ships, agricultures, construction, and electrical machinery. Due to harsh working environment, diesel engines are vulnerable to failures. This article addresses a significant need to improve predictive maintenance activities in diesel engines. A new failure diagnostics approach was proposed based on the manifold learning and swarm intelligence optimized multiclass multi-kernel relevant vector machine. Three manifold learning algorithms were first respectively used to fuse the features that extracted from the original vibration data of the diesel engines into a new nonlinear space. The fused features contain the most distinct health information of the engine by discarding redundant features. Then, the swarm intelligence optimized multiclass multi-kernel relevant vector machine was proposed to identify the failures using the fused features. The contribution of this research is that the dragonfly algorithm is employed to optimize the weights of the multi-kernel functions in the multiclass relevant vector machine. It was also applied to establishing a weighted-sum model by combining the outputs of swarm intelligence optimized multiclass multi-kernel relevant vector machine models with different manifold learning algorithms. Robust failure detection of diesel engines is achieved owing to combined strengths of multiple kernel functions and weighted-sum strategy. The effectiveness of the proposed method is demonstrated by experimental vibration data collected from a commercial diesel engine. The failure detection capability of the proposed manifold learning and swarm intelligence optimized multiclass multi-kernel relevant vector machine method for diesel engines will potentially benefit the machine condition monitoring industry by improving budgeting/forecasting and/or enabling just-in-time maintenance.
LiZGuoZHuCet al. On-line indicated torque estimation for internal combustion engines using discrete observer. Comput Electr Eng2017; 60: 100–115.
2.
LiuYZhangJQinKet al. Diesel engine fault diagnosis using intrinsic time-scale decomposition and multistage Adaboost relevance vector machine. Proc IMechE, Part C: J Mech Eng Sci. Epub ahead of print 6February2017. DOI: 10.1177/0954406217691554.
3.
YangYSMingABZhangYYet al. Discriminative non-negative matrix factorization (DNMF) and its application to the fault diagnosis of diesel engine. Mech Syst Signal Pr2017; 95: 158–171.
4.
KowalskiJKrawczykBWoźniakM.Fault diagnosis of marine 4-stroke diesel engines using a one-vs-one extreme learning ensemble. Eng Appl Artif Intel2017; 57: 134–141.
5.
KrolczykJKrolczykGLegutkoSet al. Material flow optimization—a case study in automotive industry. Teh Vjesn2015; 22(6): 1447–1456.
6.
LiZYanXYuanCet al. Intelligent fault diagnosis method for marine diesel engines using instantaneous angular speed. J Mech Sci Technol2012; 26(8): 2413–2423.
7.
GlowaczAGlowaczZ.Diagnostics of stator faults of the single-phase induction motor using thermal images, MoASoS and selected classifiers. Measurement2016; 93: 86–93.
8.
MarudaRFeldshteinELegutkoSet al. Improving the efficiency of running-in for a bronze–stainless steel friction pair. J Frict Wear2015; 36: 548–553.
9.
LiZJiangYGuoQet al. Multi-dimensional variational mode decomposition for bearing-crack detection in wind turbines with large driving-speed variations. Renew Energ2018; 116: 55–73.
10.
LiZYanXWangXet al. Detection of gear cracks in a complex gearbox of wind turbines using supervised bounded component analysis of vibration signals collected from multi-channel sensors. J Sound Vib2016; 371: 406–433.
11.
LiYPeterWTYangXet al. EMD-based fault diagnosis for abnormal clearance between contacting components in a diesel engine. Mech Syst Signal Pr2010; 24(1): 193–210.
12.
LiYWangYZiYet al. An enhanced data visualization method for diesel engine malfunction classification using multi-sensor signals. Sensors2015; 15(10): 26675–26693.
13.
JiangQJiaMHuJet al. Machinery fault diagnosis using supervised manifold learning. Mech Syst Signal Pr2009; 23(7): 2301–2311.
14.
LiZYanXTianZet al. Blind vibration component separation and nonlinear feature extraction applied to the nonstationary vibration signals for the gearbox multi-fault diagnosis. Measurement2013; 46(1): 259–271.
15.
WangSCuiJ.Sensor-fault detection, diagnosis and estimation for centrifugal chiller systems using principal-component analysis method. Appl Energ2005; 82(3): 197–213.
16.
GoldbergYZakaiAKushnirDet al. Manifold learning: the price of normalization. J Mach Learn Res2008; 9: 1909–1939.
17.
WeinbergerKSaulL.Unsupervised learning of image manifolds by semidefinite programming. Int J Comput Vision2005; 70: 77–90.
18.
RoweisSSaulL.Nonlinear dimensionality reduction by locally linear embedding. Science2000; 290: 2323–2326.
19.
DavidLCarrieG.Hessian eigenmaps: locally linear embedding techniques for high-dimensional data. Proc Natl Acad Sci U S A2003; 100: 5591–5596.
20.
BelkinMNiyogiP.Laplacian Eigenmaps for dimensionality reduction and data representation. Neural Comput2003; 15(6): 1373–1396.
21.
TippingM.Sparse Bayesian learning and the relevance vector machine. J Mach Learn Res2001; 1: 211–244.
22.
LiNLiuCHeCet al. Gear fault detection based on adaptive wavelet packet feature extraction and relevance vector machine. Proc IMechE, Part C: J Mech Eng Sci2011; 225(11): 2727–2738.
23.
MakwanaYBhaljaB.Islanding detection technique based on relevance vector machine. IET Renew Power Gen2016; 10(10): 1607–1615.
24.
WidodoAYangB.Application of relevance vector machine and survival probability to machine degradation assessment. Expert Syst Appl2011; 38(3): 2592–2599.
25.
VongCWongPIpWet al. Simultaneous-fault diagnosis of automotive engine ignition systems using prior domain knowledge and relevance vector machine. Math Probl Eng2013; 2013: 974862-1–974862-19.
26.
LiuYZhangJBoFet al. A fault diagnosis approach for diesel engine valve train based on improved ITD and SDAG-RVM. Meas Sci Technol2015; 26(2): 025003.
27.
LiuYZhangJMaL.A fault diagnosis approach for diesel engines based on self-adaptive WVD, improved FCBF and PECOC-RVM. Neurocomputing2016; 177: 600–611.
28.
FredericSDavidM. Using kernel basis with relevance vector machine. In: AplippiCPolycarpouMPanayiotouCet al. (eds) Artificial neural networks—ICANN 2009 (Part II). Berlin: Springer, pp. 255–264.
29.
HeCLiuCLiYet al. Intelligent fault diagnosis of rotating machinery based on multiple relevance vector machines with variance radial basis function kernel. Proc IMechE, Part C: J Mech Eng Sci2011; 225(7): 1718–1729.
30.
FeiSHeY.Fault diagnosis of bearing based on Cauchy kernel relevance vector machine classifier with SIWPSO. Shock Vib2015; 2015: 129361.
31.
GönenM.A Bayesian multiple kernel learning framework for single and multiple output regression. In: Proceedings of the 20th European conference on artificial intelligence, Montpellier, 27–31 August 2012, pp. 354–359. New York: ACM.
32.
FeiSHeY.A multiple-kernel relevance vector machine with nonlinear decreasing inertia weight PSO for state prediction of bearing. Shock Vib2015; 2015: 685979.
33.
TzikasDLikasAGalatsanosN. Large scale multikernel RVM for object detection. In: AntoniouGPotamiasGSpyropoulosCet al. (eds) Advances in artificial intelligence. Berlin: Springer, pp. 389–399.
34.
PsorakisIDamoulasTGirolamiMA.Multiclass relevance vector machines: sparsity and accuracy. IEEE T Neural Networ2010; 21(10): 1588–1598.
35.
ThayananthanA.Relevance vector machine based mixture of experts. Technical Report, Department of Engineering, University of Cambridge, Cambridge, September2005.
36.
DamoulasTGirolamiMYingYet al. Inferring sparse kernel combinations and relevance vectors: an application to subcellular localization of proteins. In: Proceedings of the machine learning and applications, San Diego, CA, 11–13 December 2008, pp. 577–582. New York: IEEE.
37.
YuanYYanXWangKet al. A new remote intelligent diagnosis system for marine diesel engines based on an improved multi-kernel algorithm. Proc IMechE, Part O: J Risk and Reliability2015; 229(6): 604–611.
38.
MirjaliliS.Dragonfly algorithm: a new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems. Neural Comput Appl2016; 27(4): 1053–1073.
39.
BlekasKLikasA. The mixture of multi-kernel relevance vector machines model. In: Proceedings of the IEEE 12th international conference on data mining, Brussels, 10–13 December 2012, pp. 111–120. New York: IEEE.
40.
SejdićEDjurovićIJiangJ.Time-frequency feature representation using energy concentration: an overview of recent advances. Digit Signal Process2009; 19(1): 153–183.
41.
WuJDLiuCH.An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network. Expert Syst Appl2009; 36(3): 4278–4286.
42.
LiYPeterWTYangXet al. EMD-based fault diagnosis for abnormal clearance between contacting components in a diesel engine. Mech Syst Signal Pr2010; 24(1): 193–210.
43.
LimaCLallUJebaraTet al. Machine learning methods for ENSO analysis and prediction. In: LakshmananVGillelandEMcGovernAet al. (eds) Machine learning and data mining approaches to climate science. Cham: Springer, 2015; 13–21.
ChinTSuterD.Out-of-sample extrapolation of learned manifolds. IEEE T Pattern Anal2008; 30(9): 1547–1556.
46.
JonesNLiY.A review of condition monitoring and fault diagnosis for diesel engines. Lubr Sci2000; 6(3): 267–297.
47.
NocedalJWrightSJ.Numerical optimization. New York: Springer-Verlag, 1999.
48.
AndrzejMSreckoKMarudaRet al. Taguchi design of experiment versus dynamic programming approach in the optimization of turning process. Appl Mech Mater2015; 808: 66–71.
49.
GlowaczAGlowaczZ.Diagnosis of stator faults of the single-phase induction motor using acoustic signals. Appl Acoust2017; 117: 20–27.
