In this paper, a neural network based system for ‘on-line’ estimation of tool wear in turning operations is introduced. The system monitors the cutting force components and extracts the tool wear information from the changes occurring over the cutting process. A hierarchical structure using multilayered feedforward static and dynamic neural networks is used as a specialized subsystem, for each wear component to be monitored. These subsystems share information about the tool wear components they are monitoring and their error in estimating the cutting force components is used to update the dynamic neural networks. The adaptability property of neural networks ensures that changes in machining parameters can be accommodated. Simulation studies are undertaken using experimental data available from manufacturing literature. The results are promising and show good estimation ability.
El GomayelJ. I.BreggerK. D.On-line tool wear sensing for turning operations. Trans ASME, J. Engng for Industry, 1986, 108, 44–47.
2.
GiustiF.SantochiM.TantussiG.On-line sensing of flank and crater wear of cutting tools. Ann. CIRP, 1987, 36, 41–44.
3.
DuR.ElbestawiM. A.WuS. M.Automated monitoring of manufacturing processes, Part 1 and Part 2. J. Engng for Industry, 1995, 117, 121–141.
4.
WrightP. K.Physical models of tool wear for adaptive control in flexible machining cells. In ASME Winter Annual Meeting, Boston, Massachusetts, 1983, pp. 19–31.
5.
KonigW.LanghammerK.SchemmelH. U.Correlation between cutting force components and tool wear. Ann. CIRP, 1972, 21, 19–20.
6.
MackinnonR.WilsonG. E.WilkinsonA. J.Tool condition monitoring using multi-component force measurements. In Proceedings of the Twenty-sixth International Machine Tool Design and Research Conference, 1986, pp. 317–324.
7.
MichelettiG. F.De FillipiA.IppolitoR.Tool wear and cutting forces in steel turning. Ann. CIRP XVI, 1968, 353–360.
8.
DanL.MathewJ.Tool wear and failure monitoring techniques for turningâ a review. Int. J. Mach. Tools Mfg, 1990, 30(4), 579–598.
9.
DanaiK.UlsoyA. G.A dynamic state model for on-line tool wear estimation in turning. Trans ASME, J. Engng for Industry, 1987, 109, 396–399.
10.
KorenY.LenzE.Mathematical model for the flank wear while turning steel with carbide tools. In Proceedings of the CIRP Seminars on Manufacturing Systems, 1972, Vol. 1(2).
11.
KorenY.MasoryO.Adaptive control with process estimation. Ann. CIRP, 1981, 30(1), 373–376.
12.
SataT.ShimaA.ShiotaY.TakedaK.SatakeK.A newly developed adaptive control of the turning process. In Proceedings of the CIRP Seminars on Manufacturing Systems, 1973, Vol. 2(1), pp. 71–83.
13.
KorenY.KoT. R.DanaiK.UlsoyA. G.Flank wear estimation under varying cutting conditions. Trans. ASME, J. Dynam. Systems, Measmt and Control, 1991, 300–307.
14.
ParkJ. J.UlsoyA. G.On-line flank wear estimation using an adaptive observer and computer vision, Part 1: Theory. Trans. ASME, J. Engng for Industry, 1993, 115, 30–36.
15.
ElanayarS. V. T.ShinY. C.Machining condition monitoring for automation using neural networks. In ASME Winter Annual Meeting, Dallas, Texas, 1990, pp. 85–100.
16.
KhanchustambhamR. G.ZhangG. M.A neural network approach to on-line monitoring of turning process. In International Conference on Neural Networks, Baltimore, Maryland, 1992, pp. 889–894.
17.
ElanayarS. V. T.ShinY. C.Robust tool wear estimation via radial basis function neural networks. In ASME Winter Annual Meeting, Anaheim, California, 1992, pp. 37–51.
18.
PurushothamanS.SrinivasaY. G.A back-propagation algorithm applied to tool wear monitoring. Int. J. Mach. Tools Mfg, 1994, 34(5), 625–631.
19.
TarngY. S.HseihY. W.HwangS. T.Sensing tool breakage in face milling with a neural network. Int. J. Mach. Tools Mfg, 1994, 34(3), 341–350.
20.
ParkJ. J.UlsoyA. G.On-line tool wear estimation using force measurement and a nonlinear observer. In ASME Winter Annual Meeting, San Francisco, California, 1989, pp. 55–63.
21.
HushD. R.HorneB. G.Progress in supervised neural networks. IEEE Signal Processing Mag., 1993, 8–39.
22.
NarendraK. S.ParthasarathyK.Gradient methods for the optimization of dynamical systems containing neural networks. IEEE Trans. on Neural Networks, 1991, 2(2), 252–262.
OrabyS. E.HayhurstD. R.Development of models for tool wear force relationships in metal cutting. Int. J. Mech. Sci., 1991, 33(2), 125–138.
25.
GhasempoorA.MooreT. N.JeswietJ.On-line flank wear estimation using neural networks. In Proceedings of the Advanced Manufacturing Processes, Systems and Technologies Conference, Bradford, UK, 1996, pp. 173–181.
