Tool Wear Monitoring Based on Milling Acoustic Spectrum LPCC

Abstract:

Cutting sound signal are acquisited in the vertical machining center using electret microphone, and would be applied to monitor tool wear. Linear Predictive Cepstrum Coefficient (LPCC) of milling sound signal within audibility threshold would be extracted as acoustic spectrum characteristic parameters, and the relativity between LPCC each order component and tools radial wear was analyzed. The experiments and analysis results conclude that there are characteristic components associated with tool wear in characteristic parameters LPCC of milling sound signal; the characteristic components associated with tool wear are mainly concentrated in the 6th, 7th and 8th order components LPCC; the method by characteristic parameters LPCC monitoring tool wear is feasible.

• Periodical: Key Engineering Materials (Volume 499)
• Pages: 353-358
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.499.353
• Online since: January 2012
• Authors: Chang Sheng Ai, Y.J. Sun, G.W. He
• Keywords: Cutting Sound Signal, LPCC, Tool Condition Monitoring, Tool Radial Wear

References

[1] S.M. Ji, L.B. Zhang, J.L. Yuan. Method of monitoring wearing and breakage states of cutting tools based on Mahalanobis distance features. Journal of Materials Processing Technology Vol. 129 (2002), pp.114-117.

DOI: 10.1016/s0924-0136(02)00587-3

[2] H. Shao, H. l. Wang, X.M. Zhao. A cutting power model for tool wear monitoring in milling. International Journal of Machine Tool &Manufacture Vol. 44(2004), pp.1503-1509.

DOI: 10.1016/j.ijmachtools.2004.05.003

[3] Weiguo Gong, Weihong Li, T. Shiraksshi. An active method of monitoring tool wear states by impact diagnostic excitation. International Journal of Machine Tool &Manufacture Vol. 44 (2004), pp.847-854.

DOI: 10.1016/j.ijmachtools.2004.01.007

[4] Y.B. Guo, S.C. Ammula. Real-time acoustic emission monitoring for surface damage in hard machining. International Journal of Machine Tools & Manufacture Vol. 45 (2005), pp.1622-1627.

DOI: 10.1016/j.ijmachtools.2005.02.007

[5] J. Kopac, S. Sali. Tool wear monitoring during the turning process. Journal of Materials Processing Technology Vol. 113(2001), pp.312-316.

DOI: 10.1016/s0924-0136(01)00621-5

[6] Zafer Tekiner, Sezgin. Investigation of the cutting parameters depending on process sound during turning of AISI 304 austenitic stainless steel. Materials & Design Vol. 25(6) (2004), pp.507-513.

DOI: 10.1016/j.matdes.2003.12.011

[7] Ming-Chyuan Lu, Elijah Kannatey-Asibu, Jr. Analysis of Sound Signal Generation Due to Flank Wear in Turning. ASME Vol. 124(2002), pp.799-808.

DOI: 10.1115/1.1511177

[8] D.R. Salgado, F.J. Alonso. An approach based on current and sound signals for in-process tool wear monitoring. International Journal of Machine Tools&Manufacture Vol. 47(14) (2007), pp.2140-2152.

DOI: 10.1016/j.ijmachtools.2007.04.013

[9] F.J. Alonso, D.R. Salgado. Application of singular spectrum analysis of tool wear detection using sound signals. Journal of engineering manufacture Vol. 219(9) (2005), pp.703-710.

DOI: 10.1243/095440505x32634

[10] Ching-Han CHEN, Chia-Te CHU. A High Efficiency Feature Extraction Based Wavelet Transform for Speaker Recognition. Computer Symposium Vol. (2004), pp.15-17.

[11] Wang He ping, Pan Hong xia. The Application of Fusion Technology for Speaker Recognition. International Journal of Computer Science and Network Security Vol. 7(12) (2007), pp.300-303.

[12] Brett.R. Wildermoth, Kuldip k. Paliwal. USE OF VOICING AND PITCH INFORMATION FOR SPEAKER RECOGNITION. Speech Science and Technology Vol. (2000), pp.324-328.

[13] ZHAO Li. The speech signal processing. Mechanical industry press, Beijing. 2003. 4.

[14] YAN Hui, LI Ren-fa. Modeling and Simulation of Extract Cepstrum Features of Speech Signal. Journal Of System Simulation Vol. 17(7) (2005), pp.1774-1778.

[15] WANG Bin-xi, QU Dan, PENG Xuan. The basis of practical speech recognition. National Defense Industry Press, Beijing. (2005).