Tool wear monitoring—an intelligent approach

Abstract Tool wear monitoring is one of the most crucial and inevitable processes in present-day manufacturing systems. With the growth of unmanned factories, the need for on-line monitoring systems is well recognized. Artificial intelligence techniques such as artificial neural networks, fuzzy logic and the neuro-fuzzy technique have proved their potential in monitoring the manufacturing processes. In shop-floor control, the condition of the cutting tool is of more concern than the actual tool wear value but, in research activities, the estimation of the actual value of the tool wear occupies a prominent place. The present work is concerned with the assessment of the tool condition and also the estimation of the tool wear value. In the present paper, artificial intelligence techniques are applied to estimate the tool condition and tool wear value on line. Kohonen's self-organizing map is applied in neural networks for estimating the tool condition. Fuzzy logic and the neuro-fuzzy technique are implemented by triangular membership functions. To assess the tool wear value, a back-propagation neural network is applied. In fuzzy logic and neuro-fuzzy techniques, the centroid method of defuzzification is applied to obtain the flank wear value. Experimental data are generated by machining EN-8 steel with a high-speed steel cutting tool. The obtained data are used to train and test the networks. To make the monitoring system user friendly, a user interface is developed using Microsoft Visual Basic 6.0.

[1]  H HoangTien.  Fuzzy systems and fuzzy logic theory in the decision support systems and artificial intelligence , 1992 .

[2]  Min-Yang Yang,et al.  A Study on the Relationships Between Static/Dynamic Cutting Force Components and Tool Wear , 2001 .

[3]  Laura Ignizio Burke,et al.  Automated identification of tool wear states in machining processes: an application of self-organizing neural networks , 1989 .

[4]  F Giusti,et al.  On-Line Sensing of Flank and Crater Wear of Cutting Tools , 1987 .

[5]  S. S. Rangwala,et al.  Machining process characterization and intelligent tool condition monitoring using acoustic emission signal analysis , 1994 .

[6]  R. J. Kuo,et al.  Intelligent tool wear estimation system through artificial neural networks and fuzzy modeling , 1998, Artif. Intell. Eng..

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

[8]  Y. G. Srinivasa,et al.  A back-propagation algorithm applied to tool wear monitoring , 1994 .

[9]  Krzysztof Jemielniak,et al.  Tool condition monitoring using artificial intelligence methods , 2002 .

[10]  N. H. Cook,et al.  Criticism of Radioactive Tool-Life Testing , 1963 .

[11]  Bin. Zhang.  Tool condition monitoring in turning using optical sensors. , 1993 .

[12]  Reza Langari,et al.  A Neuro-Fuzzy System for Tool Condition Monitoring in Metal Cutting , 2001 .

[13]  Derek A. Linkens,et al.  Fuzzy-neural control: principles, algorithms and applications , 1995 .