Paper Titles
Potential of Cutting Fluid Application in Gear Hobbing of High-Strength Materials
p.49
Influence of the Crystal Structure of AlCrN on Tool Coating Properties and Wear in Dry Gear Hobbing
p.61
Scaling Methodology for Large Boring Bars with Tuned Mass Dampers
p.71
Experimental and Analytical Study of Cutting Force and Temperature in Drilling of CF/PEEK Composite
p.83
Static Finite Element Modeling of Milling in Flexible Composite Plates
p.93
Laser Surface Texturing of Cylindrical Ejector Pins for Functionalization of Injection Molding Systems: A Preliminary Study
p.103
Drilling of Fiber Metal Laminates for Aerospace Applications: Experimental Evaluation of Surface Treatment Effects on Adhesive Strength and Hole Quality
p.111
Classification of Cutting Tool Wear Evolution in CNC Turning Using Convolutional Neural Networks
p.119
Towards Solid-State Recycling of Ti6Al4V: Defining a Sustainable Machining Process Window for Low-Oxidation Chips
p.127

Classification of Cutting Tool Wear Evolution in CNC Turning Using Convolutional Neural Networks

Article Preview
View Pdf By email

Abstract:

This study proposes an automated framework for online cutting tool wear classification in CNC turning using low-cost optical equipment and Convolutional Neural Networks (CNNs). Longitudinal turning experiments were performed on CK45 medium carbon steel using a HAAS TL1 lathe under dry machining conditions. Tool wear evolution was monitored via a lathe-mounted digital microscope, with images classified into three distinct stages: Low (Vb<160 μm), Medium (160≤Vb≤200 μm), and Critical (Vb>200 μm). A shallow CNN architecture, consisting of three convolutional blocks and a Softmax output layer, was developed to balance model complexity with computational efficiency for potential edge deployment. To enhance robustness against positional changes, data augmentation techniques including random translations and rotations were applied. The results demonstrate good performance, with the model achieving 94.7% accuracy and a weighted F1-score of 95.4% on the testing subset. While the model showed exceptional performance in identifying Low and Medium wear, data scarcity in the Critical wear class remained a limiting factor for recall. Overall, the study confirms that shallow CNNs can accurately capture spatial hierarchies for image-based wear assessment.

You have full access to the following eBook
Machining, Cutting and Severe Plastic Deformation Processes Read eBook

Info:

Periodical:

Defect and Diffusion Forum (Volume 450)

Pages:

119-126

DOI:

https://doi.org/10.4028/p-Ni0KLa

Citation:

Cite this paper

Online since:

April 2026

Authors:

Dimitrios Apollon Gartzonikas, Nikolaos E. Karkalos, Angelos P. Markopoulos, Panorios Benardos*

Keywords:

Flank Wear, Machine Learning, Machine Vision, Tool Wear Classification

Export:

RIS, BibTeX

Permissions:

Creative Commons CC BY 4.0

Share:

Citation:

* - Corresponding Author

References

[1] B.T. Saatci, M. Ulas, T. Gurgenc, Hybrid AI Systems for Tool Wear Monitoring in Manufacturing: A Systematic Review, Appl. Sci. 16(1) (2026) 208

DOI: 10.3390/app16010208

Google Scholar

[2] Y. Jiang, J. Huang, K. Liu, D. Zhao, H. Liu, Y. Wang, Intelligent machining technology for online monitoring and control of tool condition: A review, Front. Mech. Eng. 20 (2025) 50

DOI: 10.1007/s11465-025-0866-y

Google Scholar

[3] S. Li, M. Li, Y. Gao, Deep Learning Tool Wear State Identification Method Based on Cutting Force Signal, Sensors. 25(3) (2025) 662

DOI: 10.3390/s25030662

Google Scholar

[4] K. Wang, A. Wang, L. Wu, G. Xie, Machine Tool Wear Prediction Technology Based on Multi-Sensor Information Fusion, Sensors. 24(8) (2024) 2652

DOI: 10.3390/s24082652

Google Scholar

[5] A.D. Patange, R. Jegadeeshwaran, N.C. Dhobale, Milling cutter condition monitoring using machine learning approach, IOP Conf. Ser.: Mater. Sci. Eng. 624 (2019) 012030

DOI: 10.1088/1757-899X/624/1/012030

Google Scholar

[6] P. Unal, B.U. Deveci, A.M. Ozbayoglu, A Review: Sensors Used in Tool Wear Monitoring and Prediction, In: Awan, I., Younas, M., Poniszewska-Marańda, A. (eds) Mobile Web and Intelligent Information Systems. MobiWIS 2022. LNCS 13475 (2022). Springer, Cham

DOI: 10.1007/978-3-031-14391-5_15

Google Scholar

[7] K. Jemielniak, Contemporary challenges in tool condition monitoring, Journal of Machine Engineering, 19(1) (2019) 48–61.

Google Scholar

[8] F. Ramzan, D. Reforgiato Recupero, A Literature Review on Enhancing Predictive Maintenance in Smart Manufacturing Industries: Fostering Human-Technology Collaboration and Overcoming Data Scarcity Limitations with Advanced AI Models, Oper. Res. Forum 6 (2025) 181

DOI: 10.1007/s43069-025-00584-0

Google Scholar

[9] A.S. Kumar, A. Agarwal, V.G. Jansari, K.A. Desai, C. Chattopadhyay, L. Mears, Realizing on-machine tool wear monitoring through integration of vision-based system with CNC milling machine, J. Manuf. Syst. 78 (2025) 283-293

DOI: 10.1016/j.jmsy.2024.12.004

Google Scholar

[10] B.J. Sujay, S. A. Singh, A. Agarwal, K.A. Desai, L. Mears, Identifying tool wear stages in turning process through machined surface image analysis using convolutional neural network, Manuf. Lett. 44 (2025) 678–686

DOI: 10.1016/j.mfglet.2025.06.079

Google Scholar

[11] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016

DOI: 10.1007/s10710-017-9314-z

Google Scholar