Knowledge & Skills
Materials Engineering, 20th of July 2022, 020005

Detection and prediction of the surface defect in carbide cutting tools treated by laser using artificial intelligence

Kafayat Hazzan , Manuela Pacella

Full access 

on KS-Portal

Share

Wolfson School of Mechanical, Electrical and Manufacturing Engineering, Loughborough University, Loughborough, Leicestershire, LE11 3TU, UK

Associate editor: J. C. Outeiro

*Corresponding author: [email protected]

https://doi.org/10.53229/k.and.s.2021.020005

Creative Commons License

Cite

Abstract

Content

Laser processing applied to cemented carbide cutting tools can induce various thermal and mechanical surface defects including porosity, splatter, cracks, balling, spherical pores, voids, and dissociation, which could be detrimental to the integrity of the tool. To limit and control possible post-processing defects, parametric optimization is needed. In this presentation, Hazzan identifies and classifies surface defects in post laser processed carbides to better understand the relationship between parameters and resultant surface integrity. A region convolutional neural network (R-CNN) was trained to identify and classify these surface defects using scanning electron microscopy images (SEM) as inputs. The R-CNN provided a quantitative analysis of each defect with an average accuracy of 91%. Using the data from the R-CNN matched with the laser parameters, a back propagation neural network (BPNN) was trained to act as a predictive network. The network predicts the number and proportion of defects when the tool grain size, roughness and laser parameters are entered. The predictive network has an accuracy of 96.6%. The effect of individual laser parameters on the surface integrity is estimated by this method, enabling the optimization of laser processing in cutting tools. This approach is the first to predict tool performance based on tool’s surface integrity.

References

Keywords:
Laser Processing,

Cutting Tools,

Tungsten Carbide,

Defects Detection,

Convolutional Neural Networks,

Machine Learning


Duration: 

15 minutes video  


Language:
English    


This presentation was given during the 6th CIRP Conference on Surface Integrity and was runner out for the Best Young Scientist Award

(1) Hazzan, K.E. and Pacella, M., Surface defect detection and prediction in carbide cutting tools treated by lasers. Procedia CIRP, 108, pp.851-856 (2022). https://doi.org/10.1016/j.procir.2022.05.198

(2) Hazzan, K.E., Pacella, M. & See, T.L. Understanding the surface integrity of laser surface engineered tungsten carbide. Int J Adv Manuf Technol 118, 1141–1163 (2022) https://doi.org/10.1007/s00170-021-07885-8.

(3) Hazzan KE, Pacella M, See TL, Laser Processing of hard and ultra-hard materials for micro-machining and surface engineering applications, Micromachines, 12:895 (2021) https://doi.org/10.3390/mi12080895.

(4) Bergs T, Holst C, Gupta P, Augspurger T. Digital image processing with deep learning for automated cutting tool wear detection. Procedia Manufacturing 48:947–58 (2020). https://doi.org/10.1016/j.promfg.2020.05.134.

(5) Zhou X, Liu X, Zhang D, Shen Z, Liu W. Balling phenomena in selective laser melted tungsten. J. Materials Processing Technology 222:33– 42 (2015). https://doi.org/10.1016/j.jmatprotec.2015.02.032.

(6) Hazzan KE, Pacella M., A novel laser machining strategy for cutting tool repair, Manufacturing Letters, 32C:87-91 (2022) https://doi.org/10.1016/j.jmfglet.2022.04.005.

(7) Guimares B, Figueiredo D, Fernandes CM, Silva FS, Miranda G, Carvalho O. Laser machining of WC-Co green compacts for cutting tools manufacturing. Int J Refract Met Hard Mater 2019;81:316–24. https://doi.org/10.1016/j.ijrmhm.2019.03.018.

Full presentation

Citation

K. Hazzan and M. Pacella, 2022, « Detection and prediction of the surface defect in carbide cutting tools treated by laser», Knowledge and Skills, ISSN 2800-2083, Materials Engineering, 020005, https://doi.org/10.53229/k.and.s.2021.020005

Detection and prediction of the surface defect in carbide cutting tools treated by laser using artificial intelligence
presented by Kafayat Hazzan

 

To get full access to this presentation, click on "Full Access" and use your Apprentice account credentials to unlock it. If you don't have yet an Apprentice account on KS-Portal, please create your free account by clicking on "Create account". 

To submit your video to Knowledge and Skills journal for publication via your Talent account inside KS-Portal, click here:

To get an overview to our previous publications inside Knowledge and Skills Journal, click here:

Your opinion is valuable!

As we are adopting the Lean Startup principle, your opinion as a user is very important to us to ameliorate continuously our services and to make KS-Portal respond to your needs. Do not hesitate to give your feedback!

Follow us on social media and join our community on LinkedIn, Facebook and Twitter

OK

Knowledge and Skills uses minimum necessary cookies to optimize the website’s performance. Refusing them may disturb or block your access to some of our services. For further details about this website cookies policy and how to manage them, please see "Cookies Policy" page.