Monitoring tool wear using classifier fusion

Abstract Real time monitoring of manufacturing processes using a single sensor often poses significant challenge. Sensor fusion has thus been extensively investigated in recent years for process monitoring with significant improvement in performance. This paper presents the results for a monitoring system based on the concept of classifier fusion, and class-weighted voting is investigated to further enhance the system performance. Classifier weights are based on the overall performances of individual classifiers, and majority voting is used in decision making. Acoustic emission monitoring of tool wear during the coroning process is used to illustrate the concept. A classification rate of 87.7% was obtained for classifier fusion with unity weighting. When weighting was based on overall performance of the respective classifiers, the classification rate improved to 95.6%. Further using state performance weighting resulted in a 98.5% classification. Finally, the classifier fusion performance further increased to 99.7% when a penalty vote was applied on the weighting factor.

[1]  Leo Volfson.  Visible, Night Vision and IR Sensor Fusion , 2006, 2006 9th International Conference on Information Fusion.

[2]  Jon Atli Benediktsson,et al.  The effect of correlation on the accuracy of the combined classifier in decision level fusion , 2000, IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120).

[3]  David Dornfeld,et al.  Quantitative Relationships for Acoustic Emission from Orthogonal Metal Cutting , 1981 .

[4]  Li Li,et al.  Gear Multi-Faults Diagnosis of a Rotating Machinery Based on Independent Component Analysis and Fuzzy K-Nearest Neighbor , 2010 .

[5]  Debasis Sengupta,et al.  Estimation of tool wear based on adaptive sensor fusion of force and power in face milling , 2009 .

[6]  Krishna R. Pattipati,et al.  Data Visualization, Data Reduction and Classifier Fusion for Intelligent Fault Diagnosis in Gas Turbine Engines , 2008 .

[7]  Sohyung Cho,et al.  achine ensemble approach for simultaneous detection of transient and radual abnormalities in end milling using multisensor fusion , 2009 .

[8]  João Fernando Gomes de Oliveira,et al.  Precision manufacturing process monitoring with acoustic emission , 2006 .

[9]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[10]  A. M. Mutawa,et al.  Decision Fusion for Visual Inspection of Textiles , 2010 .

[11]  Bin Ma,et al.  Sparse Classifier Fusion for Speaker Verification , 2013, IEEE Transactions on Audio, Speech, and Language Processing.

[12]  Thomas Schenk,et al.  Coroning: High Performance Gear Honing Without Dressing , 2003 .

[13]  M. S. Shunmugam,et al.  Tool condition monitoring in honing process using acoustic emission signals , 2008, Int. J. Autom. Control..

[14]  Roberto Teti,et al.  Tool Wear Monitoring Through Acoustic Emission , 1989 .

[15]  Kaspar Althoefer,et al.  Monitoring of self-tapping screw fastenings using artificial neural networks , 2005 .

[16]  Charles E. Kahn,et al.  Accurate Determination of Imaging Modality using an Ensemble of Text- and Image-Based Classifiers , 2012, Journal of Digital Imaging.

[17]  Jianbo Yu.  Online tool wear prediction in drilling operations using selective artificial neural network ensemble model , 2011, Neural Computing and Applications.

[18]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Ming-Chyuan Lu,et al.  Application of backpropagation neural network for spindle vibration-based tool wear monitoring in micro-milling , 2011, The International Journal of Advanced Manufacturing Technology.

[20]  J. Tlusty,et al.  A Critical Review of Sensors for Unmanned Machining , 1983 .

[21]  Igor Grabec,et al.  Acoustic emission of a cutting process , 1977 .

[22]  M. F. DeVries,et al.  Neural Network Sensor Fusion for Tool Condition Monitoring , 1990 .

[23]  Horst Bischof,et al.  Classifier fusion for robust ICAO compliant face analysis , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[24]  Stuart E. Dreyfus,et al.  A Customized Neural Network for Sensor Fusion in On-Line Monitoring of Cutting Tool Wear , 1995 .

[25]  David Dornfeld,et al.  Tool Wear Detection Using Time Series Analysis of Acoustic Emission , 1989 .

[26]  Yung C. Shin,et al.  A Bayesian machine learning method for sensor selection and fusion with application to on-board fault diagnostics , 2010 .

[27]  D. Ruta,et al.  An Overview of Classifier Fusion Methods , 2000 .

[28]  Tae Hyung Kim,et al.  A two-step feature selection method for monitoring tool wear and its application to the coroning process , 2013 .

[29]  Ming-Chyuan Lu,et al.  Model development for tool wear effect on AE signal generation in micromilling , 2013 .

[30]  Elijah Kannatey-Asibu,et al.  Acoustic Emission Condition Monitoring of the Coroning Process , 2009 .

[31]  T. Nicosevici,et al.  A review of sensor fusion techniques for underwater vehicle navigation , 2004, Oceans '04 MTS/IEEE Techno-Ocean '04 (IEEE Cat. No.04CH37600).

[32]  Elijah Kannatey-Asibu,et al.  Monitoring of laser weld penetration using sensor fusion , 2002 .

[33]  Ming-Chyuan Lu,et al.  Applying the self-organization feature map (SOM) algorithm to AE-based tool wear monitoring in micro-cutting , 2013 .

[34]  Krzysztof Jemielniak,et al.  Advanced monitoring of machining operations , 2010 .

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

[36]  Steven Y. Liang,et al.  Analysis of acoustic emission in chatter vibration with tool wear effect in turning , 2000 .

[37]  I. Inasaki,et al.  A Study on Acoustic Emission from the Orthogonal Cutting Process , 1990 .

[38]  Josef Kittler,et al.  Sum Versus Vote Fusion in Multiple Classifier Systems , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[39]  Ibrahim N. Tansel,et al.  Micro-end-milling—III. Wear estimation and tool breakage detection using acoustic emission signals , 1998 .

[40]  S. E. Muldoon,et al.  Vehicle fault diagnostics using a sensor fusion approach , 2002, Proceedings of IEEE Sensors.

[41]  Fabio Roli,et al.  Methods for Designing Multiple Classifier Systems , 2001, Multiple Classifier Systems.

[42]  Zhenbing Zeng,et al.  Multiple classifier integration for the prediction of protein structural classes , 2009, J. Comput. Chem..

[43]  David Dornfeld,et al.  Application of acoustic emission techniques in manufacturing , 1992 .

[44]  Xiaoli Li,et al.  A brief review: acoustic emission method for tool wear monitoring during turning , 2002 .

[45]  David Dornfeld,et al.  A study of tool wear using statistical analysis of metal-cutting acoustic emission , 1982 .

[46]  Ludmila I. Kuncheva,et al.  A Theoretical Study on Six Classifier Fusion Strategies , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[47]  Thomas Lengauer,et al.  Comparison of Classifier Fusion Methods for Predicting Response to Anti HIV-1 Therapy , 2008, PloS one.

[48]  Eyke Hüllermeier,et al.  Combining predictions in pairwise classification: An optimal adaptive voting strategy and its relation to weighted voting , 2010, Pattern Recognit..

[49]  Elijah Kannatey-Asibu,et al.  Hidden Markov model-based tool wear monitoring in turning , 2002 .

[50]  S.S. Rangwala,et al.  Learning and optimization of machining operations using computing abilities of neural networks , 1989, IEEE Trans. Syst. Man Cybern..

[51]  Toshimichi Moriwaki,et al.  Detection for Cutting Tool Fracture by Acoustic Emission Measurement , 1980 .

[52]  Kenneth A. Loparo,et al.  A decision fusion algorithm for tool wear condition monitoring in drilling , 2001 .