Heat input control and deep learning-based indirect measure of process and deposition stability in Wire Arc Additive Manufacturing

Authors

• Alessandra Caggiano, Roma Tre UniversityFollow
• Giulio Mattera, University of Naples Federico IIFollow
• Yuming Zhang, University of KentuckyFollow
• Roberto Teti, University of Naples Federico II

Abstract

A process qualification-oriented data-driven framework for Wire Arc Additive Manufacturing (WAAM) integrating qualification data, process monitoring and feedback control, is presented. A proportional control strategy regulating heat input by varying the Contact Tip–to–Workpiece Distance (CTWD) is developed to enhance process stability, ensure consistent layer geometry and maintain the qualified heat-input conditions for process qualification. To assess the control strategy stability, deep learning-based CTWD soft sensing from high-frequency welding signals is combined with an uncertainty-aware process quality index. The framework is validated on Invar 36 alloy, but it supports extension to other alloys and arc welding-based additive processes.

Document Type

Article

Publication Date

2026

Notes/Citation Information

0007-8506/© 2026 The Authors. Published by Elsevier Ltd on behalf of CIRP. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/)

Digital Object Identifier (DOI)

https://doi.org/10.1016/j.cirp.2026.04.008

Repository Citation

Caggiano, Alessandra; Mattera, Giulio; Zhang, Yuming; and Teti, Roberto, "Heat input control and deep learning-based indirect measure of process and deposition stability in Wire Arc Additive Manufacturing" (2026). Electrical and Computer Engineering Faculty Publications. 67.
https://uknowledge.uky.edu/ece_facpub/67