Skip to main content
SpringerLink
Log in

Machine learning approaches for predicting geometric and mechanical characteristics for single P420 laser beads clad onto an AISI 1018 substrate

The International Journal of Advanced Manufacturing Technology Aims and scope Submit manuscript

Cite this article

Abstract

The final mechanical and physical properties should be predicted in tandem with the bead geometry characteristics for effective additive manufacturing (AM) solutions for processes such as directed energy deposition. Experimental approaches to investigate the final geometry and the mechanical properties are costly, and simulation solutions are time-consuming. Alternative artificial intelligent (AI) systems are explored as they are a powerful approach to predict such properties. In the present study, the geometrical properties as well as the mechanical properties (residual stress and hardness) for single bead clads are investigated. Experimental data is used to calibrate multi-physics finite element models, and both data sets are used to seed the AI models. The adaptive neuro-fuzzy inference system (ANFIS) and a feed-forward back-propagation artificial neural network (ANN) system are utilized to explore their effectiveness in the 1D (discrete values), 2D (bead cross-sections), and 3D (complete bead) domains. The prediction results are evaluated using the mean relative error measure. The ANFIS predictions are more precise than those from the ANN for the 1D and 2D domains, but the ANN had less error for the 3D scenario. These models are capable of predicting the geometrical and the mechanical properties values very well, including capturing the mechanical properties in transient regions; however, this research should be extended for multi-bead scenarios before a conclusive “best approach” strategy can be determined.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24
Fig. 25
Fig. 26
Fig. 27
Fig. 28
Fig. 29
Fig. 30
Fig. 31

Similar content being viewed by others

Data and material availability

Not applicable.

Code availability

Not applicable.

References

  1. Srinivas M, Babu BS (2017) A critical review on recent research methodologies in additive manufacturing. Mater Today Proc 4(8):9049–9059. https://doi.org/10.1016/j.matpr.2017.07.258

    Article  Google Scholar 

  2. Emamian A, Corbin SF, Khajepour A (2010) Effect of laser cladding process parameters on clad quality and in-situ formed microstructure of Fe-TiC composite coatings. Surf Coat Technol 205(7):2007–2015. https://doi.org/10.1016/j.surfcoat.2010.08.087

    Article  Google Scholar 

  3. Shi J, Zhu P, Fu G, Shi S (2018) Geometry characteristics modeling and process optimization in coaxial laser inside wire cladding. Opt Laser Technol 101:341–348. https://doi.org/10.1016/j.optlastec.2017.10.035

    Article  Google Scholar 

  4. Alam MK, Urbanic RJ, Nazemi N, Edrisy A (2018) Predictive modeling and the effect of process parameters on the hardness and bead characteristics for laser-cladded stainless steel. Int J Adv Manuf Technol 94(1):397–413. https://doi.org/10.1007/s00170-017-0898-5

    Article  Google Scholar 

  5. Aggarwal K, Urbanic RJ, Saqib SM (2018) Development of predictive models for effective process parameter selection for single and overlapping laser clad bead geometry. Rapid Protot J

  6. Chen T, Wu W, Li W, Liu D (2019) Laser cladding of nanoparticle TiC ceramic powder: effects of process parameters on the quality characteristics of the coatings and its prediction model. Opt Laser Technol 116:345–355. https://doi.org/10.1016/j.optlastec.2019.03.048

    Article  Google Scholar 

  7. Zareh P, Urbanic RJ (2020) Experimental analysis of single layer multi-track deposition of clad beads with variable overlap percentages. Int J Adv Manuf Technol 109(5):1511–1525. https://doi.org/10.1007/s00170-020-05672-5

    Article  Google Scholar 

  8. Zhao Y, Guan C, Chen L, Sun J, Yu T (2020) Effect of process parameters on the cladding track geometry fabricated by laser cladding. Optik 223:165447. https://doi.org/10.1016/j.ijleo.2020.165447

    Article  Google Scholar 

  9. Mirkoohi E, Sievers DE, Garmestani H, Liang SY (2020) Thermo-mechanical modeling of thermal stress in metal additive manufacturing considering elastoplastic hardening. CIRP J Manuf Sci Technol 28:52–67. https://doi.org/10.1016/j.cirpj.2020.01.002

    Article  Google Scholar 

  10. Nazemi N, Urbanic J, Alam M (2017) Hardness and residual stress modeling of powder injection laser cladding of P420 coating on AISI 1018 substrate. Int J Adv Manuf Technol 93(9):3485–3503. https://doi.org/10.1007/s00170-017-0760-9

    Article  Google Scholar 

  11. Denlinger ER, Gouge M, Irwin J, Michaleris P (2017) Thermomechanical model development and in situ experimental validation of the laser powder-bed fusion process. Addit Manuf 16:73–80. https://doi.org/10.1016/j.addma.2017.05.001

    Article  Google Scholar 

  12. Williams RJ, Davies CM, Hooper PA (2018) A pragmatic part scale model for residual stress and distortion prediction in powder bed fusion. Addit Manuf 22:416–425. https://doi.org/10.1016/j.addma.2018.05.038

    Article  Google Scholar 

  13. Kemerling B, Lippold JC, Fancher CM, Bunn J. Residual stress evaluation of components produced via direct metal laser sintering. https://doi.org/10.1007/s40194-018-0572-z

  14. Chowdhury S, Anand S (2016) Artificial neural network based geometric compensation for thermal deformation in additive manufacturing processes

  15. Caiazzo F, Caggiano A (2018) Laser direct metal deposition of 2024 Al alloy: trace geometry prediction via machine learning. Materials 11(3):444

    Article  Google Scholar 

  16. Ren K, Chew Y, Zhang YF, Fuh JYH, Bi GJ (2020) Thermal field prediction for laser scanning paths in laser aided additive manufacturing by physics-based machine learning. Comput Methods Appl Mech Eng 362:112734

    Article  Google Scholar 

  17. Sood AK, Ohdar RK, Mahapatra SS (2012) Experimental investigation and empirical modelling of FDM process for compressive strength improvement. J Adv Res 3(1):81–90. https://doi.org/10.1016/j.jare.2011.05.001

    Article  Google Scholar 

  18. Singh RP. Analysis of depth of penetration and impact strength during shielded metal arc welding under magnetic field using artificial neural networks

  19. Wu Q, Mukherjee T, De A, DebRoy T (2020) Residual stresses in wire-arc additive manufacturing – hierarchy of influential variables. Addit Manuf 35:101355. https://doi.org/10.1016/j.addma.2020.101355

    Article  Google Scholar 

  20. Mathew J, Griffin J, Alamaniotis M, Kanarachos S, Fitzpatrick ME (2018) Prediction of welding residual stresses using machine learning: comparison between neural networks and neuro-fuzzy systems. Appl Soft Comput J 70:131–146. https://doi.org/10.1016/j.asoc.2018.05.017

    Article  Google Scholar 

  21. Alam MK, Edrisy A, Urbanic J (2019) Microstructural analysis of the laser-cladded AISI 420 martensitic stainless steel. Metall Mater Trans A 50(5):2495–2506

    Article  Google Scholar 

  22. Denai MA, Palis F, Zeghbib A (2004) ANFIS based modelling and control of non-linear systems: a tutorial. In 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No. 04CH37583), 2004, vol. 4, pp. 3433–3438

  23. Rezaei E, Karami A, Yousefi T, Mahmoudinezhad S (2012) Modeling the free convection heat transfer in a partitioned cavity using ANFIS. Int Commun Heat Mass Transfer 39(3):470–475. https://doi.org/10.1016/j.icheatmasstransfer.2011.12.006

    Article  Google Scholar 

  24. Hayati M, Rashidi AM, Rezaei A (2011) Prediction of grain size of nanocrystalline nickel coatings using adaptive neuro-fuzzy inference system. Solid State Sci 13(1):163–167. https://doi.org/10.1016/j.solidstatesciences.2010.11.007

    Article  Google Scholar 

  25. Pedrycz W (1994) Why triangular membership functions? Fuzzy Sets Syst 64(1):21–30

    Article  MathSciNet  Google Scholar 

  26. Mohajernia B, Urbanic RJ, Nazemi N (2019) Predictive modelling of residual stresses for single bead P420 laser cladding onto an AISI 1018 substrate. IFAC-PapersOnLine 52(10):236–241

    Article  Google Scholar 

Download references

Acknowledgements

The support provided by MITACs, CAMufacturing Solutions, Inc., and Lincoln Laser Inc. is gratefully acknowledged.

Funding

This research was funded by Mitacs Accelerate (award number, IT18391, IT16398; grant recipients, Dr. Jill Urbanic, Dr. Ofelia Jianu) and also the NSERC grant (award number, RGPIN/04842–2018; grant recipients, Dr. Jill Urbanic).

Author information

Authors and Affiliations

  1. Department of Mechanical, Automotive, and Materials Engineering, University of Windsor, Windsor, ON, N9B 3P4, Canada

    Bita Mohajernia, Seyedeh Elnaz Mirazimzadeh, Alireza Pasha & R. Jill Urbanic

Authors
  1. Bita Mohajernia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Seyedeh Elnaz Mirazimzadeh
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Alireza Pasha
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. R. Jill Urbanic
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

BM: simulation model setup, data collection, analysis, developing mathematical model, and paper write up. SEM: developing mathematical model and paper write up. AP: developing mathematical model and paper write up. RJU: experimental data collection and analysis, simulation data analysis, research paper writing and editing, and project funding.

Corresponding author

Correspondence to R. Jill Urbanic.

Ethics declarations

Ethics approval

The manuscript is not submitted to any other journal simultaneously. The manuscript will not be submitted elsewhere until the editorial process is completed. The submitted work is original. A single study “Machine learning approaches for predicting geometric and mechanical characteristics for single P420 laser beads clad onto an AISI 1018 substrate” has not been split up into several parts to increase the quantity of submissions. There is no any content being translated from other journals in other languages. Results are presented clearly, honestly, and without fabrication, falsification, or inappropriate data manipulation. No data, text, or theories by others are presented as if they were the author’s own (“plagiarism”). The authors have permission to use the applied software. This research has not been applied to pose a threat to public health or national security.

Consent to participate

Not applicable.

Consent for publication

All authors consent to publish the paper in the current order. The authors transfer to Springer the non-exclusive publication rights.

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mohajernia, B., Mirazimzadeh, S.E., Pasha, A. et al. Machine learning approaches for predicting geometric and mechanical characteristics for single P420 laser beads clad onto an AISI 1018 substrate. Int J Adv Manuf Technol 118, 3691–3710 (2022). https://doi.org/10.1007/s00170-021-08155-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00170-021-08155-3

Keywords

search

Navigation