Tool wear monitoring is the most difficult task in the area of tool condition monitoring for metal-cutting manufacturing processes. The main objective is to improve the process reliability, but the production costs need to be reduced as well. This article summarises a new approach for online and indirect tool wear estimation or classification in turning using neural networks. This technique uses a physical process model describing the influence of cutting conditions (such as the feed rate) on measured process parameters (here: cutting force signals) in order to separate signal changes caused by variable cutting conditions from signal changes caused by tool wear. Features extracted from the normalised process parameters are taken as inputs of a dynamic, but nonrecurrent neural network that estimates the current state of the tool. It is shown that the estimation error can be reduced significantly with this combination of a hard computing and a soft computing technique. The article represents an extended summary of the author's investigations and publications in the area of online and indirect tool wear monitoring in turning by means of artificial neural networks.
References
1.
AdamW.SuwalskiI.KruegerJ.: Werkzeugueberwachungfuer CNC-Drehmaschinen mit Fuzzy-Logik; Final report of a DFG research project; Fraunhofer Institut fuer Produktionsanlagen und Konstruktionstechnik (IPK), Berlin, February 1996.
2.
BrooksR. R.IyengarS. S.: Multi-Sensor Fusion — Fundamentals and Applications with Software;Prentice Hall PRT, Upper Saddle River, 1998.
3.
BishopC. M.: Neural Networks for Pattern Recognition;Clarendon Press, Oxford, 1995.
4.
BoothroydG.KnightW. A.: Fundamentals of Machining and Machine Tools; 2nd edn.; Marcel Dekker, New York, Basel, 1989.
5.
BukkapatnamS. T. S.KumaraS. R. T.LakhtakiaA.: Fractal Estimation of Flank Wear in Turning Using Time-Delay Neural Networks in: Intelligent Engineering Systems through Artificial Neural Networks (eds. DagliC. H.FernandezB.GhoshJ.KumaraR. T. S.); vol. 4; pp. 975–980; ASME Press, New York, 1994; (Proceedings of the 4th Artificial Neural Networks in Engineering Conference (ANNIE ′94), St. Louis).
6.
BurkeL. I.RangwalaS.: Tool Condition Monitoring in Metal Cutting: A Neural Network Approach; in: Journal of Intelligent Manufacturing; vol. 2; pp. 269–280, October 1991.
7.
DimlaD. E.ListerP. M.LeightonN. J.: Automatic Tool State Identification in a Metal Turning Operation Using MLP Neural Networks and Multivariate Process Parameters; in: International Journal of Machine Tools and Manufacture; vol. 38 (4); pp. 343–352, 1998.
8.
DornfeldD. A.: Neural Network Sensor Fusion for Tool Condition Monitoring; in: Annals of the CIRP, vol. 39 (1); pp. 101–105, 1990.
9.
GhasempoorA.MooreT. N.JeswietJ.: Tool Wear Prediction in Turning in Proceedings of the 13th International Congress and Exhibition on Condition Monitoring and Diagnostic Engineering Management (COMADEM 2000), Houston; 2000.
10.
GolzH.-U.SchilloE.WolfA.KaufeldM.SprengelP.JohannsenP.HeinekD.: Bewertung von Werkzeugueberwachungssystemen aus Sicht der Anwender; in: Ueberwachung von Zerspan- und Umformprozessen (ed. VDl-Gesellschaft Produktionstechnik (ADB)); pp. 309–317; VDI-Verlag, Duesseldorf, 1995; (Proceedings of the CIRP/VDI conference, Duesseldorf; VDI Berichte number 1179).
11.
HaykinS.: Neural Networks — A Comprehensive Foundation; Macmillan College Publishing Company, New York, 1994.
12.
KuoR. J.CohenP. H.: Multi-Sensor Integration for On-Line Tool Wear Estimation Through Radial Basis Function Networks and Fuzzy Neural Network; in: Neural Networks;vol. 12 (3); pp. 355–370, 1999.
13.
KamarthiS. V.KumaraS. R. T.: A New Neural Network Architecture for Continuous Estimation of Flank Wear in Turning in Proceedings of the First World Congress on Intelligent Manufacturing Processes and Systems, Puerto Rico; vol. 2; pp. 1145–1156, 1995.
14.
LeemC. S.DornfeldD. A.DreyfusS. E.: A Customized Neural Network for Sensor Fusion in On-Line Monitoring of Cutting Tool Wear in Journal of Engineering for Industry (Transactions of the ASME); vol. 117; pp. 152–159, May 1995.
15.
MaydlW.SickB.: Recurrent and Non-Recurrent Dynamic Network Paradigms: A Case Study; in: International Joint Conference on Neural Networks (IJCNN 2000), Como; vol. 6; pp. 73–78, 2000.
PittnerS.KamarthiS. V.GaoQ.: Wavelet Networks for Sensor Signal Interpretation in Flank Wear Assessment; in: Proceedings of the Second World Congress on Intelligent Manufacturing Processes and Systems, Budapest; pp. 82–87, 1997.
18.
RiedmillerM.: RPROP — Description and Implementation Details; Technical report; Universitaet Karlsruhe, Institut fuer Logik, Komplexitaet und Deduktionssysteme, 1994.
19.
RojasR.: Neural Networks-A Systematic Introduction; Springer-Verlag, Berlin, Heidelberg, New York, 1996.
20.
RahmanM.ZhouQ.HongG. S.: Application of Kohonen Neural Network for Tool Condition Monitoring; in: Proceedings of SPIE; vol. 2620; pp. 422–428, 1995.
21.
SickB.GrassW.DonnerK.: Techniken der Sensorfusion beider Verarbeitung mikrosystembasierter Signale; in: Informationstechnik und Technische Informatik; vol. 41 (4); pp. 14–19, 1999.
22.
ShawM. C.: Metal Cutting Principles;Clarendon Press, Oxford, 1984.
23.
SickB.: Wear Estimation for Turning Tools with Process-Specific Preprocessing for Time-Delay Neural Networks; in: Intelligent Engineering Systems through Artificial Neural Networks (eds. DagliC. H.AkayM.ErsoyO.FernandezB. R.SmithA.); vol. 7; pp. 791–796; ASME Press, New York, 1997; (Proceedings of the 7th Artificial Neural Networks in Engineering Conference (ANNIE ′97), St. Louis).
24.
SickB.: Chances and Risks of Sensor Fusion with Neural Networks: An Application Example; in: Proceedings of the 8th International Conference on Artificial Neural Networks (ICANN ′98), Skoevde (eds. NiklassonL.BodenM.ZiemkeT.); vol. 2; pp. 713–718; Springer Verlag, London, 1998.
25.
SickB.: On-Line Tool Wear Classification in Turning with Time-Delay Neural Networks and Process-Specific Pre-Processing; in: International Joint Conference on Neural Networks (IJCNN ′98), Anchorage; pp. 84–89, 1998.
26.
SickB.: On-Line Tool Wear Monitoring in Turning Using Neural Networks; in: Neural Computing & Applications; vol. 7 (4); pp.356–366, 1998.
27.
SickB.: Signalinterpretation mit Neuronalen Netzen unter Nutzungvon modellbasiertem Nebenwissen am Beispiel der Verschleissueberwachungvon Werkzeugen in CNC-Drehmaschinen; VDI-Verlag, Duesseldorf, 2000;(Fortschritt-Berichte VDI (Reihe 10: Informatik/Kommunikationstechnik) Nr.629).
28.
SickB.: Online and Indirect Tool Wear Monitoring in Turning with Artificial Neural Networks: A Review of More Than a Decade of Research in Mechanical Systems and Signal Processing, 2001; (under review).
29.
SilvaR. G.ReubenR. L.BakerK. J.WilcoxS. J.: Tool Wear Monitoring of Turning Operations by Neural Network and Expert System Classification of a Feature Set Generated from Multiple Sensors; in: Mechanical Systems and Signal Processing; vol. 12 (2); pp. 319–332, 1998.
30.
SickB.SichenederA.LindingerH.-J.: A Comparative Evaluation of Different Neural Network Paradigms for Tool Wear Classification in Turning; in: 3rd International Workshop Neural Networks in Applications (NN ′98), Magdeburg (eds. NauckD.KrellG.KruseR.MichaelisB.);pp. 139–146, 1998.
31.
WanE. A.: Finite Impulse Response Neural Networks with Applications in Time Series Prediction; Ph.D. thesis; Stanford University, Department of Electrical Engineering, 1993.
32.
WaibelA.HanazawaT.HintonG.ShikanoK.LangK. J.: Phoneme Recognition Using Time-Delay Neural Networks; in: IEEE Transactions on Acoustics, Speech, and Signal Processing’, vol. 37 (3); pp.328–339, 1989.
