A Comprehensive Identification of Tool Failure and Chatter Using a Parallel Multi-ART2 Neural Network

Tool failure and chatter are two major problems during machining. To detect and distinguish the occurrences of these two abnormal conditions, a novel parallel multi-ART2 neural network has been developed. An advantage of this network is more reliable identification of a variety of complex patterns. This is due to the sharing of multi-input feature information by its multiple ART2 subnetworks which allow for finer vigilance thresholds. Using the maximum frequency-band coherence function of two acceleration signals and the relative weighted frequency-band power ratio of an acoustic emission signal as input feature information, the network has been found to identify various tool failure and chatter states in turning operations with a total of 96.4% success rate over a wide range of cutting conditions, compared to that of 80.4% obtainable with the single-ART2 neural network.

[1]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[2]  Kourosh Danai,et al.  Unsupervised Neural Network for Tool Breakage Detection in Turning , 1993 .

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

[4]  S. Y. Liang,et al.  Tool Wear and Chatter Detection in Turning via Time-Series Modeling and Frequency Band Averaging , 1994 .

[5]  D. Dornfeld,et al.  In-Process Tool Fracture Detection , 1984 .

[6]  Igor Grabec,et al.  Self-Organizing Neural Network Application to Drill Wear Classification , 1994 .

[7]  K. F. Eman,et al.  A Feasibility Study of On-Line Identification of Chatter in Turning Operations , 1980 .

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

[9]  Ibrahim N. Tansel.  Identification of the prefailure phase in microdrilling operations using multiple sensors , 1994 .

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

[11]  Ibrahim N. Tansel,et al.  Recognition of chatter with neural networks , 1991 .

[12]  George Chryssolouris,et al.  Sensor Synthesis for Control of Manufacturing Processes , 1992 .

[13]  Y. S. Tarng,et al.  On-line drilling chatter recognition and avoidance using an ART2—A neural network , 1994 .

[14]  S. M. Pandit,et al.  A Data Dependent Systems Strategy of On-Line Tool Wear Sensing , 1982 .

[15]  Ibrahim N. Tansel,et al.  Detection of tool breakage in milling operations—II. The neural network approach , 1993 .

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

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

[18]  Kourosh Danai,et al.  On-line tool breakage detection in turning: a multi-sensor method , 1994 .

[19]  I. E. Minis,et al.  Improved Methods for the Prediction of Chatter in Turning , 1990 .

[20]  Laura I. Burke,et al.  An unsupervised neural network approach to tool wear identification , 1993 .

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

[22]  Julius S. Bendat,et al.  Engineering Applications of Correlation and Spectral Analysis , 1980 .

[23]  Stephen Grossberg,et al.  Art 2: Self-Organization Of Stable Category Recognition Codes For Analog Input Patterns , 1988, Other Conferences.

[24]  P. Toni,et al.  An Approach to On-Line Measurement of Tool Wear by Spectrum Analysis , 1977 .

[25]  W. Dong,et al.  Machine tool chatter monitoring by coherence analysis , 1992 .

[26]  I. Inasaki,et al.  In-Process Detection of Cutting Tool Damage by Acoustic Emission Measurement , 1982 .

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