Abstract
Drill wear detection and prognosis is one of the most important considerations in reducing the cost of rework and scrap and to optimize tool utilization in hole making industry. This study presents the development and implementation of two supervised vector quantization neural networks for estimating the flank-land wear size of a twist drill. The two algorithms are; the learning vector quantization (LVQ) and the fuzzy learning vector quantization (FLVQ). The input features to the neural networks were extracted from the vibration signals using power spectral analysis and continuous wavelet transform techniques. Training and testing were performed under a variety of speeds and feeds in the dry drilling of steel plates. It was found that the FLVQ is more efficient in assessing the flank wear size than the LVQ. The experimental procedure for acquiring vibration data and extracting features in the time-frequency domain using the wavelet transform is detailed. Experimental results demonstrated that the proposed neural network algorithms were effective in estimating the size of the drill flank wear.
Similar content being viewed by others
References
Kaldor S, Lenz E (1981) Investigation in tool life of twist drill. Ann CIRP 30(1):
El-Wardany I, Gao D, Elbestawi MA (1996) Tool condition monitoring in drilling using vibration signature analysis. Int J Mach Tools Manuf 36(6):687–711
Looney CG (1997) Pattern recognition using neural networks, theory and algorithms for engineers and scientists. Oxford University Press, New York
Li PG, Wu S, Wu M (1994) Monitoring drilling wear states by a fuzzy pattern recognition technique. ASME J Eng Ind 110:297–300
Liu TI, Wu S, Wu M (1990) On-Line detection of drill wear. ASME J Eng Ind 112:299–302
Govekar E, Grabec I (1994) Self-organizing neural network application to drill wear classification. ASME J Eng Ind 116:233–238
Govekar E, Madsen H, Grabec I (1991) Estimation of drill wear from AE signals using a self-organizing neural network. Proceedings of 4th World Meeting on AE and 1st Inf. Conf. on AE in Manufacturing, Boston, pp 65–71
Liu TI, Anantharaman KS (1994) Intelligent classification and measurement of drill wear. ASME J Eng Ind 116:392–397
Lin SC, Ting CJ (1996) Drill wear monitoring using neural networks. Int J Mach Tools Manuf 36(4):465–475
Li X, Dong S, Venuvinod PK (2000) Hybrid learning for tool wear monitoring. Int J Adv Manuf Tech 16:303–307
Liu TI, Chen WY (1998) Intelligent detection of drill wear. Mech Sys Sig Proc 12(6):863–873
Xiaoli Li, Tso SK (1999) Drill wear monitoring based on current signals. Wear 231:172–178
Tansel IN, Mekdeci C, Rodriguez O, Uragun B (1993) Monitoring drill conditions with wavelet based encoding and neural networks. Int J Mach Tool Manuf 33:559–575
Dimla DE, Lister PM, Leighton NJ (1997) Neural network solutions to the tool condition monitoring problem in metal cutting - a critical review of methods. Int J Mach Tools Manuf 37(9):1219–1241
Kohonen T (1986) Learning vector quantization for pattern recognition. Technical Report TKK-F-A601, Helsinki University of Technology
Chung FL, Lee T (1995) Fuzzy competitive learning. Neural Networks 7(3):539–551
MATLAB (2000) Signal processing toolbox user’s guide. The Math Works In, Natick
Marple SL (1987) Chapter 7 In: Digital spectral analysis. Prentice Hall, Englewood Cliffs
Romberg TM, Cassar AG, Harris RW (1984) A comparison of traditional Fourier and maximum entropy spectral method for vibration analysis. ASME J Vib Ac Str Rel Des 106:36–39
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Abu-Mahfouz, I. Drill flank wear estimation using supervised vector quantization neural networks. Neural Comput & Applic 14, 167–175 (2005). https://doi.org/10.1007/s00521-004-0436-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-004-0436-x