Topic: Data-Driven Innovations in Additive Manufacturing

Additive Manufacturing (AM) has evolved from a rapid prototyping technique into a mainstream industrial production technology. This Special Issue aims to highlight cutting-edge research on data-driven methodologies that fundamentally transform the AM value chain. The integration of vast and heterogeneous datasets - including in situ process monitoring, multi-physics simulations, material characterization, and materials design - presents unprecedented opportunities for advancing AM. By leveraging artificial intelligence (AI), machine learning (ML), statistical modeling, and digital twin frameworks, new frontiers in AM optimization can be unlocked. This Special Issue welcomes original research articles and reviews focusing on intelligent process control, predictive quality assurance, materials design, and microstructure and property prediction.

We invite contributions addressing, but not limited to, the following themes:

1.  Intelligent Process Monitoring and Control:
● ML-basedreal-time analysis of multimodal sensor data (e.g., thermal, optical, acoustic signals);
● Insitu defect detection (porosity, cracking, lack of fusion) and automated correction;
● Closed-loop control systems for laser powder bed fusion, directed energy deposition, and related AM processes;
● Digital twinframeworks for real-time process simulation and validation.

2.  Data-Enabled Design and Process Planning:
● AI-driven optimization of process parameters;
● Generative design and topology optimization integrated with manufacturability constraints;
● ML approachesfor predicting and optimizing support structures and scan paths.

3.  Microstructure and Property Prediction:
● Establishing process-structure-property (PSP) linkages using data mining and ML;
● Prediction of mechanical performance, fatigue life, and residual stress from process data;
● Microstructural optimization for enhanced material properties.

4.  Data-Driven Materials Design for AM:
● ML-assisted alloy design guided by AM metallurgyprinciples;
● Utilization of materials databasesand large language models (LLMs) for alloy design in AM;
● High-throughput experimentalapproaches for alloy design in AM.

Additive manufacturing, data-driven modeling, artificial intelligence (AI), machine learning (ML), digital twin; process monitoring, process optimization, materials design, microstructural tuning, property prediction