The ability to automate and implement active prediction of a degradation process and potential failures of critical machine components is a pressing concern in modern manufacturing. The increasing prediction reliability and significant cost savings potential have stimulated the introduction of numerous artificial intelligence techniques into the manufacturing arena. The need to explore and understand the capacities of these new methods is extremely important to define their suitable application. This paper explores use of a classifier based on rough sets theory (RST). The results show very good performance over several criteria in a cutting tool wear monitoring application.
LabibW.World class maintenance using a computerised maintenance management system. J. Qual. in Maintenance Engng (JQME), 1998, 4(1), 66–75.
2.
BakshiB. R.Wave-nets: Novel learning techniques, and the induction of physically interpretable models. Proc. SPIE, Orlando, 1994, 2242, 637–648.
3.
WangL.MehrabiM. G.Kannatey-AsibuE.Jr.Tool wear monitoring in reconfigurable machining systems through wavelet analysis. In Proceedings of NAMRI, 2001, Vol. 29, pp. 399–406.
4.
LetourneauS.FamiliF.MatwinS.Data mining for prediction of aircraft component replacement. IEEE Intelligent Systems, Special Issue on Data Mining, 1999, 59–66.
5.
RoemerM. J.Kacprzy?skiG. J.Advanced diagnostics and prognostics for gas turbine engine risk assessment. In Proceedings of IEEE Aerospace Conference, Big Sky, 2000, Vol. 6, pp. 345–353.
6.
ZackJ.StefanowskiJ.Determining maintenance activities of motor vehicles using rough sets approach. In Proceedings of Euromaintenance, Amsterdam, 1994, pp. 39–42.
7.
PawlakZ.Rough sets. Int. J. Computer and Infn. Sci., 1982, 11(5), 341–356.
8.
S?owi?skiK.Rough classification of HSV patients. In Intelligent decision support (Ed. Slowi?skiR.) 1992, pp. 363–372 (Kluwer Academic Publishers, Dordrecht).
9.
DimitrasI.S?owi?skiR.SusmagaR.ZopounidisC.Business failure prediction using rough sets. Eur. J. Opl. Res., 1999, 114, 263–280.
10.
NowickiR.S?owi?skiR.StefanowskiJ.Evaluation of vibroacoustic diagnostic symptoms by means of the rough set theory. J. Computers in Ind., 1992, 20, 141–152.
11.
S?owi?skiR.StefanowskiJ.SusmagaR.Rough set analysis of attribute dependencies in technical diagnosis. In Proceedings of Fourth Workshop on Rough sets, fuzzy sets and machine discovery, Tokyo, 1996, pp. 284–291.
12.
WójcikZ. M.Intelligent image filtering using rough sets. In Proceedings of International Workshop on Rough sets and knowledge discovery, Banff, 1993, pp. 377–386.
13.
ØhrnJ.KomorowskiJ.ROSETTA: A rough set toolkit for analysis of data. In Proceedings of Third International Joint Conference on Information Sciences, Fifth International Workshop on Rough sets and soft computing (RSSC'97), Durham, 1997, 3, 403–407.
14.
HanleyJ. A.McNeilB. J.A method for comparing the areas under receiver operating characteristics curves derived from the same cases. Radiology, 1983, 148(3), 839–843.
15.
WangL.MehrabiM. G.Kannatey-AsibuE.Jr.Hidden markov model-based tool wear monitoring in machining. Trans. ASME, J. Mfg Sci. and Engng, 2002, 124, 651–658.
16.
AssouadP.LiuJ.PasekZ. J.Performance assessment of two classification schemes for cutting tool degradation monitoring. IEEE Systems, Man, Cybernetics 2003 Conference, October 2003, Washington, DC.
