Diagnostics and predictive analysis of the wear of a cutting tool when processing on CNC machines

M. Bryniuk Ukrainian Engineering and Pedagogical Academy https://orcid.org/0009-0005-2974-8818
O. Kondratyuk Ukrainian Engineering and Pedagogical Academy https://orcid.org/0000-0002-3263-0483
V. Markov Ukrainian Engineering and Pedagogical Academy https://orcid.org/0000-0002-0625-6934
A. Skorkin Ukrainian Engineering and Pedagogical Academy https://orcid.org/0000-0003-3032-8341

Keywords: technological system, control, diagnostics, manufacturing quality, prediction model, tool resource, efficiency of the cutting process

Abstract

DOI: https://doi.org/10.32820/2079-1747-2023-31-21-32

This article addresses a significant issue in material processing, specifically the forecasting
of cutting blade tool resources and the development of a novel method to diagnose the criticality of
its technical condition. The concept of resource refers to the period of the tool wear before
resharpening, since the duration of the tool operation, which does not require resharpening, is the
easiest to control automatically.
This article presents the outcomes of research aimed at developing a method for forecasting
the resource of a cutting tool by continuously monitoring the sound pressure level during the cutting
process.
The investigation employed system analysis, cutting theory, oscillation theory, and
identification methods through random search. The study focused on analyzing the dynamic
behavior of the metalworking technological system as the cutting tool undergoes wear.
The research resulted in the development of a forecasting method for the cutting tool resource.
This method involves identifying parameters of a forecast model based on continuous monitoring of
the sound pressure level during the cutting process. Moreover, the model is compiled in such a way
that the sought-after resource is included in its mathematical structure, eliminating the need for
statistically unreliable criteria parameters when making forecasts about the limit state of the tool.
This article presents a novel model for forecasting the technical state of technological
systems, enabling estimation of the resource of both the tool and the technological system as a
whole. Knowledge of the system resource facilitates the implementation of adaptive management,
preventing unforeseen interruptions for tool replacement or machine repair, and minimizing the risk
of workpiece omissions. The developed automated predictive and diagnostic complex facilitates the
practical application of the proposed forecasting model across a wide range of material processing
scenarios. This advancement addresses a crucial scientific and practical objective of enhancing
cutting process efficiency.

Downloads

References

Zaloga, VO & Vnukov, JM 2010, Znoshuvannja і stіjkіst' rіzal'nih lezovih іnstrumentіv, [Wear resistance and cutting blade tools], Sums'kij derzhavnij unіversitet, Sumi.

Zaloha, VA & Zinchenko, RN 2008, ‘Doslidzhennia mozhlyvosti zastosuvannia metodu diahnostyky akustychnoi emisii v chystove tochinnia tytanovoho splavu’, [Investigation of the possibility to apply the method of acoustic emission diagnostics in titanium alloy finishing turning], Vesnyk KumDU. Seriia Tekhnichni nauky, no 4, Pp. 118-125.

Rumbeshta, VO 2000, Systemy keruvannia yakistiu vyhotovlennia vyrobiv, [Quality management systems for manufacturing products: a course of lectures], NTUU «KPI», Kiev.

Ribalko, AP, Lyshchenko, NV & Larshyn, VP 2015, ‘Cystemi tekhnolohycheskoi dyahnostyky y adaptyvnoho upravlenyia dlia stankov s ChPU’, [Process diagnostics and adaptive control systems for CNC machines], Vysoki tekhnolohii v mashynobuduvanni, no 1, Pp. 150–161.

Barton, J & Reuben, B 1996, ‘Tool - wear monitoring by optical techniques’, Materials World, no 4 (3), Pp. 131-132.

Chen, JC & Black, JT 1997, ‘A fuzzy-nets in-process (FNIP) system for tool-breakage monitoring in end-milling operations’, International Journal of Machine Tools and Manufacture, no 37, Pp. 783-800.

Chen, JC, Chen, WL 1999, ‘A tool breakage Detection system using an Accelerometer sensor’, Journal of Intelligent Manufacturing, no 10, Pp. 187-197.

Chi, LA & Dornfield, DA 1998, ‘A self-organizing approach to the detection and prediction of tool wear’, ISA Transactions, no 37, Pp. 239-255.

Choudhury, SK, Jain, VK & Rama Rao ChVV 1999, ‘On-line monitoring of tool wear in turning using a neural network’, International Journal of Machine Tools and Manufacture, no 39, Pp. 489-504.

Dimla, DE 1999, ‘Application of perceptron neural networks to tool state classification in a metal-turning operation"’, Engineering Applications of Artificial Intelligence, no 12, Pp. 471-477.

Govekar, E, Gradisek, J & Grabec, I 2000, ‘Analysis of acoustic emission signals and monitoring of machining processes’, Ultrasonics, no 38, Pp. 598-603.

Huang, PT & Chen, JC 1998 ‘Fuzzy logic-base tool breakage detecting system in end milling operations’, Computers and Industrial Engineering, no 35, Pp. 37-40.

Li, X 2002, ‘A brief review: acoustic emission method for tool wear monitoring during turning’, International Journal of Machine Tools and Manufacture, no 42, Pp. 157-165.

Li, X, Djordjevich, A & Venuvinod, PK 2000, ‘Current-sensor-based feed cutting force intelligent estimation and tool wear conditioning monitoring’, IEEE Transactions on Industrial Electronics, no 47(3), Pp. 697-702.

McBride, R, Carolan, TA, Barton, JS., Wilcox, SJ, Borthwick, WKD & Jones, JDC 1993, ‘Detection of acoustic emission in cutting processes by fibre optic interferometry’, Measurement Science and Technology, no 4(10), Pp. 1122-1128.

Owsley, LM., Atlas, LE & Bernard, GD 1997, ‘Self-Organizing Feature Maps and Hidden Markov Models for Machine-Tool Monitoring’, IEEE Transactions on Signals Processing, no 45 (11), P. 2787-2798.

Atlas, L, Ostendorf, M & Bernard, GD 2000, ‘Hidden Markov Models for Machining Tool-Wear’, IEEE, Pp. 3887-3890.

Quan, Y, Zhou, M & Luo, Z 1998, ‘On-line robust identification of tool-wear via multi-sensor neural-network fusion’, Engineering Applications of Artificial Intelligence, no 11, Pp. 717-722.

Saglam, H & Unuvar, A 2003, ‘Tool Condition Monitoring in Milling based on Cutting Forces by a Neural Network’, International Journal of Production Research, no 41, Pp. 1519-1532.

Sick, B 2002, ‘Fusion of hard and soft computing techniques in indirect, online tool wear monitoring’, IEEE Transactions of Systems, Man, and Cybernetics, no 32 (2), Pp. 80-91.

Dey, S & Stori, JA 2004, ‘A Bayesian Network Approach to Root Cause Diagnosis of Process Variations’, International Journal of Machine Tools & Manufacture, no 45, Pp. 75-91.

Haber, RE 2003, ‘Alique A. Intelligent Process Supervision for Predicting Tool Wear in Machining Processes’, Mechatronics, no 13, Pp. 825-849.

Young, HT 1996, ‘Cutting temperature responses to flank wear’, Wear, T. 201, Pp. 117-120.

Vallejo, AJ, Nolazco-Flores, JA, Morales-Menéndez, R, Sucar, LE & Rodríguez, CA 2005, ‘Tool-wear Monitoring based on Continuous Hidden Markov Models’, LNCS, T. 3773, Рp. 880-890.

Vallejo, AJ, Nolazco-Flores, JA, Morales-Menéndez, R, Sucar, LE & Rodríguez, CA 2006, ‘Diagnosis of a Cutting Tool in a Machining Center’, IEEE International Joint Conference on Neural Networks, Рp. 7097-7101.

Vallejo, AJ, Morales-Menéndez, R, Garza-Castañon, LE & Alique, JR 2007, ‘Pattern Recognition Approaches for Diagnosis of Cutting Tool Wear Condition’, Transactions of the North American Manufacturing of Research Institution of SME, no 35, Рp. 81-88.

Tan, Y. et al 2015, ‘Advance in Swarm and Computational Intelligence’, 6th International Conference, ICSI 2015, Part 3, Pp. 115-126.