Rough set models have been widely used as a method for feature selection in fault diagnosis. A neighbourhood rough set model can deal with both nominal and numerical features, but selecting the neighbourhood size for its application may be a challenge. In this article, the authors illustrate that using a common neighbourhood size for all features may overestimate or underestimate a feature's dependency degree. The neighbourhood rough set model is then modified by setting different neighbourhood sizes for different features. The modified model is applied to the fault diagnosis of slurry pump impellers. Results show that the chosen feature subsets generated by the modified neighbourhood rough set model can be physically explained by the corresponding flow patterns and can achieve higher classification accuracy than the raw feature subsets and the feature subsets generated by the original neighbourhood rough set model.
LiuJ.XuH.QiL.LiH., ‘Study on erosive wear and novel wear-resistant materials for centrifugal slurry pumps’ In Proceedings of the ASME Heat Transfer/Fluids Engineering Summer Conference, Charlotte, NC, USA, 2004.
2.
KhalidY. A.SapuanS. M., ‘Wear analysis of centrifugal slurry pump impellers’Ind. Lubr. Tribol.591 (2007): 18–28.
3.
CorneliusS., ‘Pump condition monitoring through vibration analysis’ In Proceedgins of the Pumps: Maintenance, Design and Reliability Conference 2008 – IDC Technology, Johannesburg, South Africa, 2008.
4.
JiangW.SpurgeonS. K.TwiddleJ. A.SchlindweinF. S.FengY.ThanagasundramS., ‘A wavelet cluster-based band-pass filtering and envelope demodulation approach with application to fault diagnosis in a dry vacuum pump’Proc. IMechE, Part C: J. Mechanical Engineering Science221C11 (2007): 1279–1286 DOI: 10.1243/09544062JMES544.
5.
WangL.HopeA. D., ‘Bearing fault diagnosis using multi-layer neural networks’Insight: Non-Destr. Test. Cond. Monit.468 (2004): 451–455.
6.
WangJ.HuH., ‘Vibration-based fault diagnosis of pump using fuzzy technique’Measurement392 (2006): 176–185.
7.
ChudinaM., ‘Noise as an indicator of cavitation in a centrifugal pump’Acoust. Phys.494 (2003): 463–474.
8.
ZuoM. J.WuS. Y.FengZ. G.AulakhA.MiaoC. X., ‘Condition monitoring of slurry pumps for wear assessment’ (2007) Final report, technical report, University of Alberta.
9.
SamantaB.Al BalushiK. R.A1AraimiS. A., ‘Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection’Eng. Appl. Artif. Intell.167–8 (2003): 657–665.
10.
KiraK.RendellL. A., ‘The feature selection problem: Traditional methods and a new algorithm’ In Proceedings of the Tenth National Conference on Artificial intelligence, 1992, pp. 129–134 (MIT Press, Cambridge, MA, USA).
11.
AlmuallimH.DietterichT. G., ‘Learning with many irrelevant features’ In Proceedings of the Ninth National Conference on Artificial intelligence, 1991, pp. 547–552 (MIT Press, Cambridge, MA, USA).
12.
RuizR.AguilarJ.RiquelmeJ., ‘SOAP: Efficient feature selection of numeric attributes’ In Proceedings of the Eighth Ibero-American Conference on AI: Advances in artificial intelligence, Spain, 2002, pp. 233–242.
13.
PawlakZ., Rough sets: Theoretical aspects of reasoning about data (Dordrecht: Kluwer academic publisher1991).
14.
ChingJ. Y.WongA. K. C.ChanK. C. C., ‘Class-dependent discretization for inductive learning from continuous and mixed-mode data’IEEE Trans. Pattern Anal. Mach. Intell.177 (1995): 641–651.
15.
YuD. R.HuQ. H.BaoW., ‘Combining rough set methodology and fuzzy clustering for knowledge discovery from quantitative data’Proc. Chin. Soc. Electr. Eng.246 (2004): 205–210.
YeungD. S.ChenD.TsangE. C. C.LeeJ. W. T.ZhaoW. X., ‘On the generalization of fuzzy rough sets’IEEE Trans. Fuzzy Syst.133 (2005): 343–361.
18.
JinW.TungA. K. H.HanJ.WangW., ‘Ranking outliers using symmetric neighborhood relationship’ In Proceedings of the 2006 Pacific-Asia Conference on Knowledge discovery and data mining (PAKDD06), Singapore, April 2006, pp. 577–593.
19.
ShinH.ChoS., ‘Invariance of neighborhood relation under input space to feature space mapping’Pattern Recognit. Lett.266 (2005): 707–718.
20.
HuQ. H.YuD. R.LiuJ.WuC., ‘Neighborhood rough set based heterogeneous feature subset selection’Inf. Sci.17818 (2008): 3577–3594.
21.
HuQ. H., Rough computation models and algorithms for knowledge discovery from heterogenous data (2008) PhD Thesis.
22.
‘Impeller balancing and pump vibration’Tech. Bull.1 (1991): 3.
23.
ZhengQ.LiuS., ‘Numerical investigation on the formation of jet-wake flow pattern in centrifugal compressor impeller’ In Proceedings of the ASME, International Gas Turbine Institute Turbo Expo (Publication) IGTI, 6 B, 2003 pp. 755–764.
24.
DysonG., ‘Impeller rerate to reduce hydraulically generated vibration’ In Proceedings of the 22nd International Pump Users Symposium, 2005, pp. 10–15.
25.
SchiavelloB.CicatelliG., ‘Vibration field problem resolved with analytical diagnostics approach and innovative impeller design’ In Proceedings of the 24th International Pump Users Symposium, 2007, pp. 39–49.
26.
MajidiK., ‘Numerical study of unsteady flow in a centrifugal pump’J. Turbomach.1272 (2005): 363–371.
27.
HodkiewiczM. R.NortonM. P., ‘The effect of change in flow rate on the vibration of double-suction centrifugal pumps’Proc. IMechE, Part E: J. Process Mechanical Engineering216E1 (2002): 47–58 DOI: 10.1243/095440802760075030.
