The aim of the present work is to study the applicability of singular spectrum analysis (SSA) to the processing of the sound signal from the cutting zone during a turning process, in order to extract information correlated with the state of the tool. SSA is a novel non-parametric technique of time series analysis that decomposes a given time series into an additive set of independent time series. The correspondence between the singular spectrum obtained using SSA and the frequency spectrum of the signal is the basis of this processing technique. Finally, some of the features extracted from the SSA-processed sound signal were presented to a feedforward back-propagation (FFBP) neural network to determine the tool flank wear. The results showed that the proposed processing technique is well suited to the task of signal processing in the area of tool condition monitoring (TCM).
RavindraH. V.SrinivasaY. G.KrishnamurthyR.Modelling of tool wear based on cutting forces in turning. Wear, 1993, 169, 25–32.
2.
DimlaE.DimlaSnr Sensor signals for tool-wear monitoring in metal cutting operations - a review of methods. Int. J. Mach. Tools Mf., 2000, 40, 1073–1098.
3.
WellerE. J.SchrierH. M.WeichbrodtB.What sound can be expected from a worn tool?Trans. ASME, J. Engng for Industry, 1969, 91(3), 525–534.
4.
SadatA. B.RamanS.Detection of tool flank wear using acoustic signature analysis. Wear, 1987, 115 (3), 265–272.
5.
TrabelsiH.Kannatey-AsibuE.Jr.Pattern-recognition analysis of sound radiation in metal cutting. Int. J. Adv. Mfg Technol., 1991, 6, 220–231.
6.
DelioT.TlustyJ.SmithS.Use of audio signals for chatter detection and control. Trans. ASME, J. Engng for Industry, 1992, 114, 146–157.
7.
SilvaR. G.ReubenR. L.BakerK. J.WilcoxS. J.Tool wear monitoring of turning operations by neural network classification of a feature set generated from multiple sensors. Mech. Syst. Signal Process., 1998, 12, 319–332.
8.
LuM. C.Kannatey-AsibuE.Jr.Analysis of sound characteristics associated with adhesive wear in machining. Trans. NAMRI, 2000, 28, 257–262.
9.
SilvaR. G.BakerK. J.WilcoxS. J.The adaptability of a tool wear monitoring system under changing cutting conditions. Mech. Syst. Signal Process., 2000, 14 (2), 287–298.
10.
KopačJ.ŠaliS.Tool wear monitoring during the turning process. J. Mater. Process. Technol., 2001, 113 (1-3), 312–316.
11.
LuM. C.Kannatey-AsibuE.Jr.Analysis of sound signal generation due to flank wear in turning. Trans. ASME J. Mfg Sci. Engng, 2002, 124 (4), 799–808.
12.
LuM. C.Kannatey-AsibuE.Jr.Flank wear and process characteristic effect on system dynamics in turning. Trans. ASME J. Mfg Sci. Engng, 2004, 126(1), 131–140.
13.
GolyandinaN.NekrutkinV.ZhigljavskyA.Analysis of time series structure - SSA and related techniques, 2001, pp. 13–78 (Chapman & Hall/CRC Press, Boca Raton, Florida).
14.
VautardR.GhilM.Singular spectrum analysis in non-linear dynamics, with applications to paleoclimatic time series. Physica D, 1989, 35, 395–124.
15.
VautardR.YiouP.GhilM.Singular spectrum analysis: A toolkit for short noisy chaotic signals. Physica D, 1992, 58, 95–126.
16.
PasmanterR. A.Variational search of periodic motions in complex dynamical systems. Chaos Solitons Fractals, 1995, 6, 447–154.
17.
WangW. J.ChenJ.WuX. K.The application of some non-linear methods in rotating machinery fault diagnosis. Mech. Syst. Signal Process., 2001, 15, 697–705.
18.
ChoudhuryS. K.JainV. K.Rama RaoCh. V. V.On-line monitoring of tool wear in turning using a neural network. Int. J. Mach. Tools Mf., 1999, 39, 489–504.
19.
Yusuf AltintasQ.On-line monitoring of flank wear in turning with multilayered feed-forward neural network. Int. J. Mach. Tools Mf., 1999, 39, 1945–1959.
20.
DuttaR. K.PaulS.ChattopadhyayA. B.Applicability of the back-propagation algorithm in tool condition monitoring for faster convergence. J. Mater. Process. Technol., 2000, 98, 299–309.
21.
Zawada-TomkiewiczA.Classifying the wear of turning tools with neural networks. J. Mater. Process. Technol., 2001, 109, 300–304.
22.
Niranjan PrasadK.RamamoorthyB.Tool wear evaluation by stereo vision and prediction by artificial neural networks. J. Mater. Process. Technol., 2001, 112, 43–52.
23.
OzelT.NadgirA.Prediction of flank wear by using backpropagation neural network modelling when cutting hardened H-13 steel with chamfered and honed CBN tools. Int. J. Mach. Tools. Mf., 2002, 42, 287–297.
24.
Sch efferC.KratzH.HeynsP. S.KlockeF.Development of a tol wear-monitoring system for hard turning. Int. J. Mach. Tools Mf., 2003, 43 (10), 973–985.
25.
RahmanM.ZhouQ.HongG. S.On-line cutting state recognition in turning using a neural network. Int. J. Adv. Mfg Technol., 1995, 10, 87–92.
26.
QinS. J.RajagopalB.Combining statistics and expert systems with neural networks for empirical process modelling, In Proceedings of International Conference and Exhibition on Instrumentation Control, 1993, Vol. 48, pp. 1711–1720.
