CNC spindle signal investigation for the prediction of cutting tool health

The deterioration of cutting tools plays a significant role in the progression of subtractive manufacturing and substantially affects the quality of machined parts. Recognising this most organisations have implemented conventional methods for tool management. These reduce the economic loss associated with time-dependent and stochastic tool wear, and limit the damage arising from tools at end-of life. However, significant costs still remain to be addressed and more development towards tool and process prognostics is desirable. In response, this work investigates process deterioration through the acquisition and processing of selected machine signals. This utilises the internal processor of a CNC Vertical Machining Centre and considers the possible applications of such an approach for the prediction of tool and process health. This paper considers the prediction of tool and process condition with a discussion of the assumptions, benefits, and limitations of such approaches. Furthermore, the efficacy of the approach is tested using the correlation between an offline measurement of part accuracy and an active measure of process variation.

[1]  Sankalita Saha,et al.  Metrics for Offline Evaluation of Prognostic Performance , 2021, International Journal of Prognostics and Health Management.

[2]  Shital S. Chiddarwar,et al.  Tool Condition Monitoring In Various Machining Operations & Use of Acoustic Signature Analysis , 2013 .

[3]  Scott Poll,et al.  A Survey of Health Management User Objectives in Aerospace Systems Related to Diagnostic and Prognostic Metrics , 2021 .

[4]  San Juan Capistrano.  From Vibration Measurements to Condition Based Maintenance Seventy Years of Continuous Progress , 2022 .

[5]  A. F. Adams,et al.  The Survey , 2021, Dyslexia in Higher Education.

[6]  Z.M. Li,et al.  Incremental learning for online tool condition monitoring using Ellipsoid ARTMAP network model , 2015, Appl. Soft Comput..

[7]  Chen Zhang,et al.  A New Method of Tool Wear Measurement , 2010, 2010 International Conference on Electrical and Control Engineering.

[8]  Håkan Wiklund,et al.  Bayesian and regression approaches to on-line prediction of residual tool life , 1998 .

[9]  J. Jones,et al.  Surface finish parameters as diagnostics of tool wear in face milling , 1997 .

[10]  H. Metin Ertunc,et al.  Tool wear condition monitoring using a sensor fusion model based on fuzzy inference system , 2009 .

[11]  Paul W. Prickett,et al.  The difficulties of the assessment of tool life in CNC milling , 2016, 2016 International Conference for Students on Applied Engineering (ICSAE).

[12]  Enrico Zio,et al.  Echo State Network for the Remaining Useful Life Prediction of a Turbofan Engine , 2016, PHM Society European Conference.

[13]  S. Bouallègue,et al.  A New Method , 2021, Black Power and the American Myth.

[14]  Amit Kumar Jain and Bhupesh Kumar Lad.  Data Driven Models for Prognostics of High Speed Milling Cutters , 2016 .

[15]  Vishal Wayal,et al.  Tool Condition Monitoring System: A Review , 2015 .

[16]  Alaa Mohamed Riad,et al.  Prognostics: a literature review , 2016, Complex & Intelligent Systems.

[17]  János Kundrák,et al.  Application of general tool-life function under changing cutting conditions , 2014 .

[18]  Paul William Prickett,et al.  Assessing uneven milling cutting tool wear using component measurement , 2017 .

[19]  Roger Ivor Grosvenor,et al.  A discussion of the prognostics and health management aspects of embedded condition monitoring systems , 2011 .

[20]  N.S. Clements,et al.  Prognostics usefulness criteria , 2006, 2006 IEEE Aerospace Conference.

[21]  Dan Zhang,et al.  Methods and Research for Multi-Component Cutting Force Sensing Devices and Approaches in Machining , 2016, Sensors.

[22]  Stephen J. Engel,et al.  Prognostics, the real issues involved with predicting life remaining , 2000, 2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).

[23]  Lovekesh Vig,et al.  Predicting Remaining Useful Life using Time Series Embeddings based on Recurrent Neural Networks , 2017, International Journal of Prognostics and Health Management.

[24]  Paul William Prickett,et al.  An overview of approaches to end milling tool monitoring , 1999 .

[25]  F. W. Taylor.  The Art of Cutting Metals , 1907 .

[26]  Laishui Zhou,et al.  Modeling of tool wear for ball end milling cutter based on shape mapping , 2013 .

[27]  Guofeng Wang,et al.  Tool wear and hole quality investigation in dry helical milling of Ti-6Al-4V alloy , 2014 .

[28]  Paul E. Utgoff,et al.  Incremental Learning , 2017, Encyclopedia of Machine Learning and Data Mining.