Premium
Bayesian and regression approaches to on‐line prediction of residual tool life
Author(s) -
Wiklund Håkan
Publication year - 1998
Publication title -
quality and reliability engineering international
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.913
H-Index - 62
eISSN - 1099-1638
pISSN - 0748-8017
DOI - 10.1002/(sici)1099-1638(199809/10)14:5<303::aid-qre155>3.0.co;2-f
Subject(s) - bayesian probability , residual , computer science , reliability (semiconductor) , regression , bayesian linear regression , process (computing) , machine learning , data mining , line (geometry) , reliability engineering , bayesian inference , engineering , artificial intelligence , statistics , mathematics , algorithm , geometry , power (physics) , physics , quantum mechanics , operating system
In this paper, two statistical approaches to on‐line prediction of cutting tool life are presented and discussed. A Bayesian approach utilizes in‐process information about the cutting tool state and constitutes a valuable basis for improved prediction. A second approach is based on the cutting forces and facilitates a prediction of the tool life with an uncertainty of 15% after 1.5–2.0 cutting minutes. Traditional tool condition monitoring can be improved by increased reliability of tool life predictions, increased utilization of the cutting tools together with reduced need for pre‐process data and calibrating procedures. © 1998 John Wiley & Sons, Ltd.