Physics-Driven AI Applications in Additive Manufacturing and Welding

Dear Colleagues,

Thermal-fluid phenomena are at the heart of arc-based manufacturing processes, including gas metal arc welding (GMAW), gas tungsten arc welding (GTAW), plasma arc welding, and wire arc additive manufacturing (WAAM). From arc plasma generation and droplet transfer to melt pool convection, solidification, and residual stress development, these coupled multi-physics processes collectively determine bead geometry, microstructure, mechanical properties, and structural integrity of fabricated components.

Over the past decades, significant progress has been made through computational fluid dynamics and thermomechanical finite element modeling, complemented by advanced experimental diagnostics such as synchrotron X-ray radiography, high-speed imaging, and infrared thermography. More recently, data-driven and physics-informed machine learning approaches are opening new possibilities for accelerating simulation, reconstructing unmeasurable internal fields from sparse observations, and establishing quantitative process–structure–property relationships.

This Special Issue aims to bring together contributions spanning the full spectrum from fundamental thermal-fluid analysis to emerging intelligent data-driven modeling and monitoring approaches in welding and additive manufacturing. We particularly encourage submissions that leverage machine learning and hybrid physics-data methods to address long-standing challenges in process monitoring, modeling and optimisation. Topics include, but are not limited to:

• melt pool fluid dynamics, heat transfer, and solidification behavior in welding and WAAM;
• arc plasma modeling and droplet/metal transfer phenomena;
• thermomechanical simulation of residual stress, distortion, and thermal management in multi-layer deposition;
• in-situ and operando process characterization (X-ray radiography, high-speed imaging, infrared thermography);
• physics-informed and hybrid data-physics driven models for thermal-fluid field reconstruction;
• deep learning-based surrogate and reduced-order models for process simulation;
• Models for process–structure–property relationship and defect prediction (porosity, hot cracking, lack of fusion);
• machine learning for process monitoring, anomaly detection, and quality assurance;
• shielding gas effects, inter-pass thermal control, and process parameter optimization;
• digital twins for welding and additive manufacturing processes.

Dr. Van Anh Nguyen
Dr. Yue Cao
Dr. Giulio Mattera
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Processes is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• melt pool dynamics
• arc welding
• wire arc additive manufacturing
• thermal-fluid simulation
• residual stress and distortion
• physics-informed machine learning
• process-structure-property relationships
• in-situ characterization
• deep learning for manufacturing
• defect prediction