Bayesian-inference-based neural networks for tool wear estimation

This paper introduces the application of neural networks based on Bayesian inference, the automatic relevance determination algorithm for selecting relevant features and designing neural estimators for tool wear estimation in face-milling processes. Two types of neural networks are studied: Bayesian support vector machines for regression (BSVR) and Bayesian multilayer perceptrons (BMLP). Sixteen well-known features derived from pre-processing of the milling force signal are considered. The force signal samples are collected from 20 milling experiments under various machining conditions. The feature extraction and selection procedure is then applied to the sampled force signal. The feature selection results from the two neural networks are found to be quite similar. The average force has been proven to be the most relevant feature for tool wear estimation in both cases, among a set of six other features in each case, with each set differing by only one feature. The comparison among the generalization capabilities of the entire, selected, and rejected features shows that the selected features are relatively more relevant to tool wear processes in both cases. The comparison between the estimation results from the two neural networks using the corresponding relevant feature set shows that the BSVR method is more accurate in estimating flank wear than BMLP, but at the cost of a higher computing load.

[1]  Y. S. Tarng.  Study of milling cutting force pulsation applied to the detection of tool breakage , 1990 .

[2]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

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

[4]  Zhang Deyuan,et al.  On-line detection of tool breakages using telemetering of cutting forces in milling , 1995 .

[5]  Ibrahim N. Tansel,et al.  Detection of tool breakage in milling operations-I , 1993 .

[6]  Wei Chu,et al.  A Unified Loss Function in Bayesian Framework for Support Vector Regression , 2001, ICML.

[7]  Ian T. Nabney,et al.  Netlab: Algorithms for Pattern Recognition , 2002 .

[8]  Masayoshi Tomizuka,et al.  On-Line Monitoring of Tool and Cutting Conditions in Milling , 1989 .

[9]  Y. S. Tarng,et al.  Sensing tool breakage in face milling with a neural network , 1994 .

[10]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[11]  Wray L. Buntine,et al.  Bayesian Back-Propagation , 1991, Complex Syst..

[12]  Yusuf Altintas,et al.  In-process detection of tool breakages using time series monitoring of cutting forces , 1988 .

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

[14]  Santanu Das,et al.  Force Parameters for On-line Tool Wear Estimation: A Neural Network Approach , 1996, Neural Networks.

[15]  Yusuf Altintas,et al.  In-Process Detection of Tool Failure in Milling Using Cutting Force Models , 1989 .

[16]  Shih-Chieh Lin,et al.  Tool wear monitoring in face milling using force signals , 1996 .

[17]  M. A. Elbestawi,et al.  Process monitoring in milling by pattern recognition , 1989 .

[18]  Michael E. Tipping.  The Relevance Vector Machine , 1999, NIPS.

[19]  T. I. El-Wardany,et al.  A multi-sensor strategy for tool failure detection in milling , 1995 .

[20]  Trevor A. Dean,et al.  Computer modelling of tool loads and press/tool deflections in multistage forging , 1995 .

[21]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[22]  Roger Frost,et al.  International Organization for Standardization (ISO) , 2004 .