This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Multilevel Classification of Milling Tool Wear with Confidence Estimation
January 2003 (vol. 25 no. 1)
pp. 75-85

Abstract—An important problem during industrial machining operations is the detection and classification of tool wear. Past research in this area has demonstrated the effectiveness of various feature sets and binary classifiers. Here, the goal is to develop a classifier which makes use of the dynamic characteristics of tool wear in a metal milling application and which replaces the standard binary classification result with two outputs: a prediction of the wear level (quantized) and a gradient measure that is the posterior probability (or confidence) that the tool is worn given the observed feature sequence. The classifier tracks the dynamics of sensor data within a single cutting pass as well as the evolution of wear from sharp to dull. Different alternatives to parameter estimation with sparsely-labeled training data are proposed and evaluated. We achieve high accuracy across changing cutting conditions, even with a limited feature set drawn from a single sensor.

[1] Technical Editorial Dept. Sandvik Coromant, Modern Metal Cutting—A Practical Handbook, Fair Lawn, N.J.: Sandvik Coromant, 1996.
[2] L. Dan and J. Mathew, “Tool Wear and Failure Monitoring Techniques for Turning–A Review,” Int'l J. Machine Tools Manufacturing, vol. 30, pp. 579-598, 1990.
[3] S. Kim and B.E. Klamecki, “Milling Cutter Wear Monitoring Using Spindle Shaft Vibration,” ASME J. Manufacturing Science and Eng., vol. 119, pp. 118-119, Feb. 1997.
[4] R. Du, M.A. Elbestawi, and S.M. Wu, “Automated Monitoring of Manufacturing Processes, Part 2: Applications,” ASME J. Manufacturing Science and Eng., vol. 117, pp. 133-141, May 1995.
[5] X.Q. Li, Y.S. Wong, and A.Y.C. Nee, “A Comprehensive Identification of Tool Failure and Chatter Using a Parallel Multi-ART 2 Neural Network,” ASME J. Manufacturing Science and Eng., vol. 120, pp. 433-442, May 1998.
[6] S. Rangwala and D. Dornfeld, “Sensor Integration Using Neural Networks for Intelligent Tool Condition Monitoring,” ASME J. Manufacturing Science and Eng., vol. 112, pp. 219-228, Aug. 1990.
[7] E. Emel and E. Kannatey-Asibu, Jr., “Tool Failure Monitoring in Turning by Pattern Recognition Analysis of AE Signals,” ASME J. Eng. for Industry, vol. 110, pp. 137-145, May 1988.
[8] Y.M. Niu, Y.S. Wong, G.S. Hong, and T.I. Liu, “Multi-Category Classification of Tool Conditions Using Wavelet Packets and ART2 Network,” ASME J. Manufacturing Science and Eng., vol. 120, pp. 807-816, Nov. 1998.
[9] L.P. Heck and J.H. McClellan, “Mechanical System Monitoring Using Hidden Markov Models,” Proc. Int'l Conf. Acoustics, Speech, and Signal Processing, vol. 3, pp. 1697-1700, 1991.
[10] J.-C. Fabre, Y. Deswarte, and B. Randell, “Designing Secure and Reliable Applications Using Fragmentation-Redundancy-Scattering: An Object-Oriented Approach,” Proc. First European Dependable Computing Conf., pp. 21-38, Oct. 1994.
[11] J. McLaughlin, L. Owsley, L.E. Atlas, and G.D. Bernard, “Advances in Real-Time Monitoring of Acoustic Emissions,” Proc. SAE Aerospace Meeting, 1997.
[12] L. Atlas, M. Ostendorf, and G. Bernard, “Hidden Markov Models for Monitoring Machining Tool-Wear,” Proc. Int'l Conf. Acoustics, Speech, and Signal Processing, vol. 6, pp. 3887-3890, 2000.
[13] L.R. Rabiner and B.H. Juang, Fundamentals of Speech Recognition, Prentice Hall, Upper Saddle River, N.J., 1993.
[14] D.A. Anderson, “Tool Sensing for Milling,” Proc. Soc. Manufacturing Eng. (SME) Conf. Machine Monitoring Sensors Clinic, vol. MS89-460, 1989.
[15] J. Odell, D. Ollason, V. Valtchev, and P. Woodland, The HTK Book. Cambridge Univ., 1997.
[16] J.M. Chambers and T.J. Hastie, Statistical Models in S.New York: Wadsworth, 1992.
[17] M. Siu and H. Gish, “Evaluation of Word Confidence for Speech Recognition Systems,” Computer Speech and Language, vol. 13, pp. 299-319, 1999.
[18] P. W. Prickett and C. Johns, “An Overview of Approach to End Milling Tool Monitoring,” Int'l J. Machine Tool and Manufacturing, vol. 39, pp. 105-122, 1999.
[19] X. Li and Z. Yuan, “Tool Wear Monitoring with Wavelet Parket Transform-Fuzzy Clustering Method,” Wear, vol. 219, pp. 145-154, 1998.
[20] G. Littlefair, M.A. Javed, and G.T. Smith, “Fusion of Integrated Multisensor Data for Tool Wear Monitoring,” Proc. IEEE Int'l Conf. Neural Networks, pp. 734-737, 1995.
[21] S. Li and M.A. Elbestawi, “Tool Condition Monitoring in Machining by Fuzzy Neural Networks,” J. Dynamic Systems, Measurement, and Control (Trans. ASME), vol. 118, pp. 665-672, 1996.
[22] Y. Chen and R. Du, “Artificial Neural Network Architecture Design Using Similarity Measure with Applications in Engineering Monitoring and Diagnosis,” J. Dynamic Systems, Measurement, and Control (Trans. ASME), vol. 118, pp. 635-639, 1996.
[23] C.S. Leem, “A Practical Monitoring Strategy for Machining Process Control,” Int'l J. Production Research, vol. 35, no. 4, pp. 1051-1066, 1997.
[24] A. Gunawardana and W. Byrne, “Discounted Likelihood Linear Regression for Rapid Speaker Adaptation,” Computer Speech and Language, vol. 15, no. 1, pp. 15-38, Jan. 2001.
[25] R. Fish, M. Ostendorf, G. Bernard, D. Castanon, and H. Shivakumar, “Modeling the Progressive Nature of Milling Tool Wear,” Proc. ASME, Manufacturing Eng. Division, vol. 11, pp. 111-117, 2000.

Index Terms:
Tool wear, confidence, normalized cross entropy, HMM, sparsely-labeled training, machining, milling.
Citation:
Randall K. Fish, Mari Ostendorf, Gary D. Bernard, David A. Castanon, "Multilevel Classification of Milling Tool Wear with Confidence Estimation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 1, pp. 75-85, Jan. 2003, doi:10.1109/TPAMI.2003.1159947
Usage of this product signifies your acceptance of the Terms of Use.