Skip to main content
SpringerLink
Log in

Artificial neural network-based surface reconstruction model of wire-arc additively manufactured surfaces using discrete cosine transform

  • Research Paper
  • Published:
Welding in the World Aims and scope Submit manuscript

Abstract

The arc-based additive manufacturing process offers high deposition rates with a drawback of creating irregular surfaces necessitating post-machining efforts. These post-processing activities use up vital raw materials and considerable energy resources. Developing predictive capabilities for surface topography becomes essential to counter these challenges. Such predictions rely on key process parameters, including wire feed and travel speeds. In this study, we develop a surface topography model that reconstructs surfaces using wire feed speed, travel speed, and interpass temperature as input parameters. The initial phase is to identify the relevant surface features that together describe the surface. From the several features scrutinized, eight representative attributes have been discerned and used in developing the surface reconstruction model, including spatial average roughness, spatial peak height, spatial maximum valley depth, spatial skewness, spatial kurtosis, maximum flatness, and waviness. The surface reconstruction model leverages the discrete cosine transform (DCT) and requires at least 30 DCT parameters for accurate surface reconstruction. Moreover, an ANN model is introduced to predict the DCT parameters based on the wire feed speed, travel speed, and interpass temperature inputs. Validation with the 309L stainless steel test material highlights the model’s commendable accuracy in predicting the DCT parameters, paving the way for precise projections of overall surface topography and machining allowances. This model sets the stage for simulation-based additive-subtractive process design, pinpointing optimal deposition conditions and matching machining parameters. Additionally, it facilitates the seamless integration of realistic surfaces into computational models for additive process simulations, holding immense potential to refine additive manufacturing processes.

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

Similar content being viewed by others

Data availability

The data that support the findings of this study are available from the corresponding author, AS, upon reasonable request.

Abbreviations

AM:

Additive manufacturing

ANN:

Artificial neural network

ANOVA:

Analysis of variance

CTWD:

Contact tip to work distance

DCT:

Direct cosine transform

GMAW:

Gas metal arc welding

IDCT:

Inverse discrete cosine transform

IT:

Interpass temperature

LMD:

Laser metal deposition

MSE:

Mean square error

TS:

Travel speed

WAAM:

Wire and arc additive manufacturing

WFS:

Wire feed speed

References

  1. Nowicki B (1985) Multiparameter representation of surface roughness. Wear 102(3):161–176. https://doi.org/10.1016/0043-1648(85)90216-9

    Article  Google Scholar 

  2. Dong WP, Sullivan PJ, Stout KJ (1992) Comprehensive study of parameters for characterizing three-dimensional surface topography I: some inherent properties of parameter variation. Wear 159(2):161–71. https://doi.org/10.1016/0043-1648(92)90299-N

    Article  Google Scholar 

  3. Dong WP, Sullivan PJ, Stout KJ (1994) Comprehensive study of parameters for characterising three-dimensional surface topography: III: parameters for characterising amplitude and some functional properties. Wear 178(1–2):29–43. https://doi.org/10.1016/0043-1648(94)90127-9

    Article  CAS  Google Scholar 

  4. Suresh N, Shreehari KM, Prasad A, Kruthvik S, Manu R, Lawrence KD (2021) Simulation of surface topography of engineering surfaces with specified roughness for tribological investigations. In AIP Conf Proc 2336:1. https://doi.org/10.1063/5.0045851

    Article  Google Scholar 

  5. Hensel J, Przyklenk A, Mueller J, Koehler M, Dilger K (2022) Surface quality parameters for structural components manufactured by DED-arc processes. Mater Des 215:110438. https://doi.org/10.1016/j.matdes.2022.110438

    Article  CAS  Google Scholar 

  6. Chernovol N, Sharma A, Tjahjowidodo T, Lauwers B, Van Rymenant P (2021) Machinability of wire and arc additive manufactured components. CIRP J Manuf Sci Tech 35:379–389. https://doi.org/10.1016/j.cirpj.2021.06.022

    Article  Google Scholar 

  7. Xia C, Pan Z, Polden J, Li H, Xu Y, Chen S (2022) Modelling and prediction of surface roughness in wire arc additive manufacturing using machine learning. J Intell Manuf 1:1–6. https://doi.org/10.1007/s10845-020-01725-4

    Article  Google Scholar 

  8. Liao D, Shao W, Tang J, Li J (2018) An improved rough surface modeling method based on linear transformation technique. Tribol International 119:786–794. https://doi.org/10.1016/j.triboint.2017.12.008

    Article  Google Scholar 

  9. Ren J, Ren M (2021) Fast surface topography reconstruction method for profilometer measurement based on neural continuous representation. Int Conf on Sens Meas & Data Anal in the era of Artif Intell (ICSMD) 1–6. https://doi.org/10.1109/ICSMD53520.2021.9670780

  10. So MS, Seo GJ, Kim DB, Shin JH (2022) Prediction of metal additively manufactured surface roughness using deep neural network. Sensors 22(20):7955. https://doi.org/10.3390/s22207955

    Article  PubMed  PubMed Central  Google Scholar 

  11. Xiong J, Li YJ, Yin ZQ, Chen H (2018) Determination of surface roughness in wire and arc additive manufacturing based on laser vision sensing. Chinese J Mech Eng 31:1–7. https://doi.org/10.1186/s10033-018-0276-8

    Article  Google Scholar 

  12. Batu T, Lemu HG, Shimels H (2023) Application of artificial intelligence for surface roughness prediction of additively manufactured components. Materials 16(18):6266. https://doi.org/10.3390/ma16186266

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Huang J, Yuan W, Yu S, Zhang L, Yu X, Fan D (2020) Droplet transfer behavior in bypass-coupled wire arc additive manufacturing. J Manuf Process 49:397–412. https://doi.org/10.1016/j.jmapro.2019.12.002

    Article  Google Scholar 

  14. Cai Y, Xiong J, Chen H, Zhang G (2023) A review of in-situ monitoring and process control system in metal-based laser additive manufacturing. J Manuf Sys 70:309–326. https://doi.org/10.1016/j.jmsy.2023.07.018

    Article  Google Scholar 

  15. Bhattacharya A, Paul SK, Sharma A (2023) Unraveling the failure mechanism of wire arc additive manufactured low carbon steel under tensile and high cycle fatigue loading. Eng Fail Anal 150:107347. https://doi.org/10.1016/j.engfailanal.2023.107347

    Article  CAS  Google Scholar 

  16. Xiong J, Li Y, Li R, Yin Z (2018) Influences of process parameters on surface roughness of multi-layer single-pass thin-walled parts in GMAW-based additive manufacturing. J Mater Process Tech 252:128–136. https://doi.org/10.1016/j.jmatprotec.2017.09.020

    Article  Google Scholar 

  17. Marefat F, Kapil A, Banaee SA, Van Rymenant P, Sharma A (2023) Evaluating shielding gas-filler wire interaction in bi-metallic wire arc additive manufacturing (WAAM) of creep resistant steel-stainless steel for improved process stability and build quality. J Manuf Process 88:110–124. https://doi.org/10.1016/j.jmapro.2023.01.046

    Article  Google Scholar 

  18. Banaee SA, Kapil A, Marefat F, Sharma A (2023) Generalised overlapping model for multi-material wire arc additive manufacturing (WAAM). Virtual Phys Prototyp 18(1):e2210541. https://doi.org/10.1080/17452759.2023.2210541

    Article  Google Scholar 

  19. Dong WP, Sullivan PJ, Stout KJ (1994) Comprehensive study of parameters for characterising three-dimensional surface topography: IV: parameters for characterising spatial and hybrid properties. Wear 178(1–2):45–60. https://doi.org/10.1016/0043-1648(94)90128-7

    Article  CAS  Google Scholar 

  20. Kumermanis M, Rudzitis J, Mozga N, Ancans A, Grislis A (2014) Investigation into the accuracy of 3D surface roughness characteristics. Latv J Phys Tech Sci 51(2):55–59. https://doi.org/10.2478/lpts-2014-0013

Download references

Acknowledgements

The authors acknowledge the help of the research group member, Ozan Can Ozaner, in conducting some experiments.

Funding

Support for this work comes from the project “Advanced Processing of Additively Manufactured Parts II (Ad-Proc-Add II)” (HBC.2021.0278) funded by Agentschap Innoveren en Ondernemen.

Author information

Authors and Affiliations

  1. Department of Materials Engineering, Faculty of Engineering Technology, KU Leuven, Campus De Nayer, 2860, Sint-Katelijne Waver, Belgium

    Seyed Aref Banaee & Abhay Sharma

Authors
  1. Seyed Aref Banaee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Abhay Sharma
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

SAB: writing—original draft, software, investigation, formal analysis, visualization. AS: Conceptualization, funding acquisition, supervision, writing—review and editing.

Corresponding author

Correspondence to Abhay Sharma.

Ethics declarations

Competing interests

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.

Recommended for publication by Commission I - Additive Manufacturing, Surfacing, and Thermal Cutting

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Banaee, S.A., Sharma, A. Artificial neural network-based surface reconstruction model of wire-arc additively manufactured surfaces using discrete cosine transform. Weld World 68, 731–741 (2024). https://doi.org/10.1007/s40194-023-01625-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40194-023-01625-0

Keywords

Search

Navigation