Page 36 - IJAMD-1-3

International Journal of AI for
Materials and Design
Prediction of wall geometry for wire arc additive manufacturing

To address this, knowledge formalization using artificial Funding
intelligence to correlate geometry and WAAM parameters
is essential. None.

5. Conclusion Conflict of interest
This study underscores the critical importance of precise The authors declare no competing interests.
parameter control in WAAM, particularly when utilizing Author contributions
the CMT process. Focusing on key welding parameters
– V and TS – this study demonstrated the influence of Conceptualization: Robin Kromer
these factors on weld bead geometries, specifically BH and Investigation: Robin Kromer
BW. Linear regression models exhibited strong predictive Methodology: Robin Kromer
capabilities, evidenced by robust performance metrics, Writing – original draft: All authors
indicating a direct linear relationship between welding Writing – review & editing: All authors
parameters and bead geometries. Ethics approval and consent to participate
The ANOVA results further validated the aforementioned
models, underscoring the statistical significance of V in Not applicable.
determining BW and highlighting the more nuanced role of
TS. The study also employed various optimization metrics, Consent for publication
such as efficiency, harmonic mean, exponential score, Not applicable.
normalized difference, and cost function, to provide a
comprehensive understanding of the trade-offs involved in Availability of data
optimizing BH and BW. These metrics effectively identified Data are available from the corresponding author upon
optimal welding conditions, demonstrating their utility in reasonable request.
fine-tuning the WAAM process.
For multibead wall production, polynomial regression References
models outperformed linear models, particularly in 1. Ding D, Pan Z, Cuiuri D, Li H. Wire-feed additive
predicting wall height and W, with significant non-linear manufacturing of metal components: Technologies,
terms indicating their substantial influence. This nuanced developments and future interests. Int J Adv Manuf Technol.
understanding is crucial for optimizing multilayer builds, 2015;81:465-481.
ensuring structural integrity, and minimizing defects. Our doi: 10.1007/s00170-015-7077-3
evaluation using various metrics consistently identified
optimal conditions, achieving the desired balance between 2. Le VT, Paris H. On the use of gas-metal-arc-welding
height and W. additive manufacturing for repurposing of low-carbon steel
components: microstructures and mechanical properties.
In addition, Dt values were optimized to achieve a Weld World. 2021;65:157-166.
linear incremental height profile while minimizing W doi: 10.1007/s40194-020-01005-y
in WAAM. A response surface visualization illustrated
the variation in incremental height with Dt and layer 3. Frostevarg J, Kaplan AFH, Lamas J. Comparison of CMT
number, facilitating the selection of optimal Dt values with other arc modes for laser-arc hybrid welding of steel.
Weld World. 2014;58:649-660.
for consistent, high-quality builds. Overall, this study
provides a robust framework for optimizing WAAM doi: 10.1007/s40194-014-0146-7
processes through precise parameter control and advanced 4. Cong B, Ding J, Williams S. Effect of arc mode in cold metal
predictive modeling. The integration of machine learning transfer process on porosity of additively manufactured
models and statistical analysis techniques offers powerful Al-6.3%Cu alloy. Int J Adv Manuf Technol. 2015;76:1593-1606.
tools for manufacturers, enabling them to achieve desired doi: 10.1007/s00170-014-6346-x
part geometries with greater efficiency and reliability.
Our findings enhance the viability and competitiveness 5. Ali Y, Henckell P, Hildebrand J, Reimann J, Bergmann JP,
of WAAM in large-scale manufacturing applications Barnikol-Oettler S. Wire arc additive manufacturing of hot
involving extensive parameters. work tool steel with CMT process. J Mater Process Technol.
2019;269:109-116
Acknowledgments doi: 10.1016/j.jmatprotec.2019.01.034
None. 6. Youheng F, Guilan W, Haiou Z, Liye L. Optimization of

Volume 1 Issue 3 (2024) 30 doi: 10.36922/ijamd.4285