A Data-Driven Approach for Thermal Modelling of Wire Arc Additive Manufacturing: Combining the Finite Element Method and Machine Learning

DOI

10.2991/978-94-6239-813-9_17How to use a DOI?

Keywords

Wire arc additive manufacturing; Finite element analysis; Machine learning

ABSTRACT

During the fabrication of large components using Wire Arc Additive Manufacturing (WAAM), the process involves a unique thermal cycle that results in significant heat accumulation in the deposited layers. This research proposes a data-driven technique that combines finite element analysis (FEA) and Machine learning for predicting the temperature history layer by layer in the WAAM process. Four machine learning algorithms were employed to train the dataset derived from the FEA results, thereby developing the surrogate models. The models predicted the thermal profile with minimal error, with an RMSE of 5.49 ℃ and an MSE of 4.17 ℃, and achieved a higher computational speed than the FEA simulation.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Dharmendar Kumar Mahato
AU  - Mukesh Chandra
AU  - Sagar Nikam
PY  - 2026
DA  - 2026/10/29
TI  - A Data-Driven Approach for Thermal Modelling of Wire Arc Additive Manufacturing: Combining the Finite Element Method and Machine Learning
BT  - Proceedings of the  Global Symposium on Adaptive Manufacturing (GSAM 2026)
PB  - Atlantis Press
SP  - 49
EP  - 51
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-813-9_17
DO  - 10.2991/978-94-6239-813-9_17
ID  - Mahato2026
ER  -