Multilevel Classification of Milling Tool Wear with Confidence Estimation

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]  C. S. Leem.  A practical monitoring strategy for machining process control , 1997 .

[2]  Gary D. Bernard,et al.  Advances in Real-Time Monitoring of Acoustic Emissions , 1997 .

[3]  Ruxu Du,et al.  Automated Monitoring of Manufacturing Processes, Part 2: Applications , 1995 .

[4]  Li Dan,et al.  Tool wear and failure monitoring techniques for turning—A review , 1990 .

[5]  S. Li,et al.  Tool Condition Monitoring in Machining by Fuzzy Neural Networks , 1996 .

[6]  Larry P. Heck,et al.  Mechanical system monitoring using hidden Markov models , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[7]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[8]  Guy Littlefair,et al.  Fusion of integrated multisensor data for tool wear monitoring , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[9]  Les E. Atlas,et al.  Hidden Markov models for monitoring machining tool-wear , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[10]  David Dornfeld,et al.  Sensor Integration Using Neural Networks for Intelligent Tool Condition Monitoring , 1990 .

[11]  Yuan Zhejun,et al.  Tool wear monitoring with wavelet packet transform—fuzzy clustering method , 1998 .

[12]  Elijah Kannatey-Asibu,et al.  Tool Failure Monitoring in Turning by Pattern Recognition Analysis of AE Signals , 1988 .

[13]  Geok Soon Hong,et al.  Multi-Category Classification of Tool Conditions Using Wavelet Packets and ART2 Network , 1998 .

[14]  Ruxu Du,et al.  Artificial Neural Network Architecture Design Using Similarity Measure With Applications in Engineering Monitoring and Diagnosis , 1996 .

[15]  Paul William Prickett,et al.  An overview of approaches to end milling tool monitoring , 1999 .

[16]  Trevor Hastie,et al.  Statistical Models in S , 1991 .

[17]  Lane M. D. Owsley,et al.  Self-organizing feature maps and hidden Markov models for machine-tool monitoring , 1997, IEEE Trans. Signal Process..

[18]  Steve Young,et al.  The HTK book , 1995 .

[19]  Barney E. Klamecki,et al.  Milling Cutter Wear Monitoring Using Spindle Shaft Vibration , 1990 .

[20]  Andrew Y. C. Nee,et al.  A Comprehensive Identification of Tool Failure and Chatter Using a Parallel Multi-ART2 Neural Network , 1998 .

[21]  Herbert Gish,et al.  Evaluation of word confidence for speech recognition systems , 1999, Comput. Speech Lang..

[22]  William J. Byrne,et al.  Discounted likelihood linear regression for rapid speaker adaptation , 2001, Comput. Speech Lang..