Hostname: page-component-78c5997874-lj6df Total loading time: 0 Render date: 2024-11-15T19:21:47.794Z Has data issue: false hasContentIssue false
  • English
  • Français

Analyse spectrale singulière des signaux vibratoires et Machine Learning pour la surveillance d'usure d'outils

Published online by Cambridge University Press:  17 May 2008

Bovic Kilundu  and
Pierre Dehombreux
Bovic Kilundu
Affiliation:
Service de génie mécanique, Faculté Polytechnique de Mons, 53 rue du Joncquois, 7000 Mons, Belgique
Pierre Dehombreux
Affiliation:
Service de génie mécanique, Faculté Polytechnique de Mons, 53 rue du Joncquois, 7000 Mons, Belgique
Get access

Abstract

Cette étude explore l'utilisation des techniques de Machine Learning pour la classification de l'état d'outils en usinage. Une analyse spectrale singulière (ASS) pseudo-locale des signaux vibratoires relevés sur le porte-outil, couplée à un filtrage passe-bande a permis la définition et la mise en évidence d'indicateurs très sensibles à l'évolution de l'état de l'outil. Ces indicateurs sont définis à partir des sommes des raies spectrales des signaux reconstruits par ASS et de leurs résidus, dans des gammes de fréquence judicieusement choisies. Les taux de reconnaissance de l'usure sont très bons et dépassent les 80 %. Cette étude met en évidence deux aspects importants : la forte richesse en information des composantes hautes fréquences des signaux vibratoires et la possibilité de s'affranchir du bruit inutile par la combinaison de l'ASS et d'un filtrage passe-bande.

Keywords

Machine Learningvibration signalsingular spectrum analysistool condition monitoringMachine Learningsignaux vibratoiresanalyse spectrale singulièresurveillance de l'usure d'outils
Type
Research Article
Information
Mechanics & Industry , Volume 9 , Issue 1 , January 2008 , pp. 1 - 8
Copyright
© AFM, EDP Sciences, 2008

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

E. Jantunen, Indirect multisignal monitoring and diagnosis of drill wear, Ph.D. Thesis, Helsinki University of technology, 2006
Lee, C.S., Dornfeld, D.A., Design and implementation of sensor-based tool-wear monitoring systems, Mechanical Systems and Signal Processing 10 (1996) 328–347 CrossRef
Ravindra, H.V., Srinisvasa, Y.G., Krishnamurthy, R., Modeling of tool wear based on cutting forces in turning, Wear 169 (1993) 25–32 CrossRef
Abu-Mahfouz, I., Drilling wear detection and classification using vibration signals and artificial neural network, Int. J. Machine Tools Manufacture 43 (2003) 707–720 CrossRef
Obikawa, T., Shinozuka, J., Monitoring of flank wear of coated tools in high speed machining with a neural network art2, Int. J. Machine Tools Manufacture 44 (2004) 1311–1318 CrossRef
Dimla E. Dimla Snr, Sensor signals for tool-wear monitoring in metal cutting operations, a review of methods, Int. J. Machine Tools Manufacture 40 (200) 1073–1098
Dimla Snr, D.E., Lister, P.M., On-line metal cutting tool condition monitoring I: force and vibration analyses, Int. J. Machine Tools Manufacture 40 (2000) 739–768 CrossRef
El-Wardany, T.I., Gao, D., Elbestawi, M.A., Tool condition monitoring in drilling using vibration signature analysis, Int. J. Machine Tools Manufacture 36 (1996) 687–711 CrossRef
Jiang, C.Y., Zhang, Y.Z., In-process, H.J. Xu monitoring of tool wear stage by the frequency band-energy method, Annals of the CIRP 36 (1997) 45–48 CrossRef
Haber, R.E., Jiménez, J.E., Peres, C.R., Alique, J.R., An investigation of tool-wear monitoring in a high-speed machining process, Sensors and Actuators A 16 (2004) 539–545 CrossRef
Li, X., Dong, S., Venuvinod, P.K., Hybrid learning for tool wear monitoring, Int. J. Adv. Manuacturing Techn. 16 (2000) 303–307 CrossRef
D. Shi, N.N. Gindy, Tool wear predictive model based on least squares support vector machines, Mechanical Systems and Signal Processing (2006) doi:10.1016/j.ymssp.2006.07.016 CrossRef
O'Donnel, G., Young, P., Kelly, K., Byrne, G., Towards the improvement of tool condition monitoring systems in the manufacturing environment, J. Mat. Processing Tech. 119 (2001) 133–139 CrossRef
Ghil, M., Allen, M.R., Dettinger, M.D., Ide, K., Kondrashov, D., Mann, M.E., Robertson, A.W., Saunders, A., Tian, Y., Varadi, F., Yiou, P., Advanced spectral methods for climatic time series, Rev. Geophys. 40 (2002) 1.1–1.41 CrossRef
Salgado, D.R., Alonso, F.J., Tool wear detection in turning operations using singular spectrum analysis, J. Materials Processing Tech. 171 (2006) 451–458 CrossRef
Aldrich, C., Barkhuizen, M., Process system identification strategies based on the use of singular spectrum analysis, Minerals engineering 16 (2003) 815–826 CrossRef
Jemwa, G.T., Aldrich, C., Classification of process dynamics with Monte Carlo singular spectrum analysis, Computers and Chemical Eng. 30 (2006) 816–831 CrossRef
Broomhead, D.S., King, G., Extracting qualitative dynamics from experimental data, Phys. D 20 (1986) 217–236 CrossRef
N. Golyandina, V. Nekrutkin, A. Zhigljavsky, Analysis of Time Series Structure- SSA and related techniques, Chapman & Hall, CRC, 2001
P. Yiou, D. Sornette, M. Ghil, Data-adaptive wavelets and multi-scale singular spectrum analysis, Phys. D 142 (200) 254–290
I.H. Witten, E. Frank, Data mining: Practical machine learning tools and techniques, Morgan Kaufmann, San Francisco, 2005
R. Kohavi, A study of cross-validation and bootstrap for accuracy estimation and model selection, in: Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, Morgan Kaufmann, 1995, pp. 1137–1143