Journal bearing bushing wear and shaft misalignment are the common defects observed in rotating systems. Both defects influence their dynamic behaviour, stability and life time and their detection is a very important task. This article introduces a defect diagnosis approach that uses artificial neural networks. Reynolds equation is solved by finite element method and wear/misalignment data are provided. Then, the proposed model uses values of journal bearing performance characteristics, such as eccentricity, attitude angle and film thickness, and it trains an artificial neural network so that reliable defect identification is performed. The accuracy of the proposed model is demonstrated – for different misalignment angles, wear depths and L/D ratios – for a worn/misaligned journal bearing. The potential use of the artificial neural networks-based model for a real-time condition monitoring system is also discussed. The outcome of this study is to obtain an efficient engineering tool that would be capable of detecting wear and misalignment of journal bearings for different operating conditions using artificial neural networks.
ZhangJ.KorstenM.RegtienP. P. L.A vision system for online wear detection. InProceedings of the XVII IMEKO World Congress on Metrology in the 3rd Millennium, Dubrovnik, Croatia, 22–27 June 20031960–1964.
6.
ZhangJ.RegtienP. P. L.KorstenM. J.Monitoring of dry sliding wear using fractal analysis. Metrol. Meas. Syst., 2005, XII(2), 110–120.
7.
BouyerJ.FillonM.Influence of wear on a two-lobe hydrodynamic journal bearing subjected to numerous start-ups and stops. ASME J. Tribol., 2007, 129(1), 205–208.
8.
DufraneK. F.KannelJ. W.McCloskeyT. H.Wear of steam turbine journal bearings at low operating speeds. J. Lubr. Technol., 1983, 105(3), 313–317.
9.
FillonM.BouyerJ.Thermohydrodynamic analysis of a worn plain journal bearing. Tribol. Int., 2004, 37(2), 129–136.
10.
VaidyanathanT. G.KeithJ. R.Performance characteristics of elliptical journal bearings in the turbulent flow regime. Tribol. Trans., 1991, 34(1), 35–41.
11.
HasimotoH.WadaS.NojimaK.Performance characteristics of worn journal bearings in both laminar and turbulent regimes. Part II: dynamic characteristics. ASLE Trans., 1986, 29(4), 572–577.
12.
KumarA.MishraS. S.Stability of a rigid rotor in turbulent hydrodynamic worn journal bearings. Wear, 1996, 193, 95–30.
13.
HashimotoH.WadaS.NojimaK.Performance characteristics of worn journal bearings in both laminar and turbulent regimes. Part I: steady-state characteristics. ASLE Trans., 2007, 29(4), 565–571.
14.
BouyerJ.FillonM.An experimental analysis of misalignment effects on hydrodynamic plain journal bearing performances. J. Tribol., 2002, 124(2), 313–319.
15.
PierreI.BouyerJ.FillonThermoM.hydrodynamic behavior of misaligned plain journal bearings: theoretical and experimental approaches. Tribol. Trans., 2004, 47(4), 594–604.
16.
BoedoS.BookerJ. F.Classical bearing misalignment and edge loading. Numerical study of limiting cases. J. Tribol., 2004, 126(3), 535–541.
17.
SunJ.GuiC.LiZ.An experimental study of journal bearing lubrication effected by journal misalignment as a result of shaft deformation under load. J. Tribol., 2005, 127(4), 813–819.
GoenkaP. K.Dynamically loaded journal bearings: finite element method analysis. ASME J. Tribol., 1984, 106(4), 429–439.
20.
BouyerJ.FillonM.Improvement of the THD performance of a misaligned plain journal bearing. ASME J. Tribol., 2003, 125(2), 334–342.
21.
NikolakopoulosP. G.PapadopoulosC. A.Wear model evaluation in misaligned journal bearings. In Proceedings of the 3rd International Conference on Power transmissions ’09, Kallithea, Chalkidiki, Greece, 1–2 October 2009447–447.
22.
ZahariT.KhusnunW.Artificial neural network for bearing defect detection based on acoustic emission. Int. J. Adv. Manuf. Technol., 2010, 50, 289–296.
23.
TianZ.LornaW.NimaS.A neural network approach for remaining useful life prediction utilizing both failure and suspension histories. Mech. Syst. Sig. Process., 2010, 24(5), 1542–1555.
24.
SinanogluC.Investigation of load carriage capacity of journal bearings by surface texturing. Ind. Lubr. Tribol., 2009, 61(5), 261–270.
25.
KalkatM.YildirimŞ.Uzmayİ.Design of artificial neural networks for rotor dynamics analysis of rotating machine systems. Mechatronics, 2005, 15, 573–588.
26.
TianZ.An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring. J. Intell. Manuf., 2009. DOI 10.1007/s10845-009-0356-9.
27.
NayakR.JainL.TingB.Artificial neural networks in biomedical engineering: a review. Proceedings of the Asia–Pacific Conference on Advance computational mechanics (Eds ValliappanS.KhaliliN.), Sydney, Australia, 20–23 November 2001, pp. 887–892.
28.
BoseN. K.LiangP.Neural network fundamentals with graphs, algorithms and applications, 1996 (McGraw-Hill, Singapore).
29.
KasabovK. N.Foundation of neural networks, fuzzy systems and knowledge engineering, 1996 (MIT Press, Massachusetts).
Sadik ÜnlüB.DurmuşH.MeriçC.Determination of friction coefficient at journal bearings by experimental and by means of artificial neural networks method. Math. Comput. Appl., 2004, 9(3), 399–408.
32.
KalkatM.YildirimŞUzmayİRotor dynamics analysis of rotating machine systems using artificial neural networks. Int. J. Rotating Mach., 2003, 9, 255–262.
33.
SaridakisK. M.ChasalevrisA. C.DentsorasA. J.PapadopoulosC. A.Applying neural networks, genetic algorithms and fuzzy logic for the identification of cracks in shafts by using coupled response measurements. Comput. Struct., 2008, 86, 1318–1338.
34.
Saridakis, K. M., Nikolakopoulos, P. G., Papadopoulos, C. A., and Dentsoras, A. J. Fault diagnosis on journal bearings based on artificial neural networks and measurements on bearing performance characteristics. In Proceedings of the 9th International Conference on Computational structures technology (Eds B. H. V. Topping, M. Papadrakakis, et al.) Athens, Greece, 2008.
35.
NikolakopoulosP. G.PapadopoulosC. A.A study of friction in worn misaligned journal bearings under severe hydrodynamic lubrication. Tribol. Int., 2008, 41(6), 461–472–461–472.
