Application of a Back-Propagation Neural Network to Tool Condition Monitoring in a Metal Turning Process

Artificial Neural Networks (ANN) are robust tools for data classification, modelling and dynamic control. This paper presents the initial results of an investigative study of sensor integration through the application of multiple feed-forward neural networks for the accomplishment of Tool Condition Monitoring (TCM). Progressive wear test studies were conducted on a conventional centre-lathe, with P25 uncoated and P15 coated carbide inserts, and an EN24T work-piece material. The cutting forces and vibration signatures were recorded, together with the nose and flank wear lengths. A signal processing method was employed to calculate the energy contained in the dynamic forces and vibration signals spectra which, together with the static forces, were used as inputs to a neural network. Additionally, the cutting speed, feed rate and depth of cut were incorporated into the input vector sets. Limiting the tool states to either sharp or worn, results obtained from off-line investigations using a 12-20-1 feed-forward Multi-Layer Perceptron (MLP) neural network showed a successful classification rate of between 75–87.5%.

[1]  D. E. Dimla,et al.  Neural network solutions to the tool condition monitoring problem in metal cutting—A critical review of methods , 1997 .

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

[3]  Jeong-Du Kim,et al.  Development of a tool failure detection system using multi-sensors , 1996 .

[4]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[5]  Ren C. Luo,et al.  Multisensor integration and fusion in intelligent systems , 1989, IEEE Trans. Syst. Man Cybern..

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

[7]  R. Krishnamurthy,et al.  Modelling of tool wear based on cutting forces in turning , 1993 .

[8]  Arne Novak,et al.  Reliability Improvement of Tool-Wear Monitoring , 1993 .

[9]  Thomas Jackson,et al.  Neural Computing - An Introduction , 1990 .

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

[11]  L. C. Lee,et al.  A study of noise emission for tool failure prediction , 1986 .

[12]  David J. Spiegelhalter,et al.  Machine Learning, Neural and Statistical Classification , 2009 .

[13]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

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

[15]  D. Guinea,et al.  Multi-sensor integration—An automatic feature selection and state identification methodology for tool wear estimation , 1991 .

[16]  Ole Pedersen,et al.  Fusing sensor systems: promises and problems , 1989 .

[17]  Robert L. Harvey,et al.  Neural network principles , 1994 .