Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 58 min ago
PreprintCC BYChemRxiv

From Processing to Programmable Properties: A Review of Artificial Intelligence in Metal Additive Manufacturing

  • Dipayan Sanpui1,2,3,4
  • Sukriti Manna1,2,3,4
  • Subramanian KRS Sankaranarayanan1,2,3,4
4 affiliations
  1. 1Department of Mechanical and Industrial Engineering
  2. 2University of Illinois
  3. 3Center for Nanoscale Materials
  4. 4Argonne National Laboratory
Open at sourceDOICite

Abstract

Machine learning has accelerated process–structure–property (PSP) prediction in metal additive manufacturing (AM), but a predicted optimum is useful only if it can be realized through processing and verified experimentally. This review examines that transition by connecting physics-based simulation, data curation, microstructure representation and reconstruction, and inverse design. We assess the information each stage retains, the assumptions it introduces, and the uncertainty it passes to subsequent decisions. Three tests organize the synthesis: structural fidelity, independently evaluated property performance, and accessibility through a specified processing route. Using these tests, we compare forward and inverse methods in terms of their data requirements, physical constraints, and validation evidence, distinguishing metal-AM demonstrations from transferable approaches developed in adjacent fields. Recurring limitations include simulation–experiment mismatch, incomplete dataset provenance, representation-dependent ambiguity, and insufficient testing outside the training domain. We outline benchmarks and reporting practices that make these limitations visible and connect them to priorities in physics-informed, multifidelity, interpretable, and multimodal learning. The resulting roadmap places experimental feedback at the center of the design workflow and identifies the evidence needed to translate rapid predictions into reproducible control of microstructure and properties.

Related

  1. Influence of Post-Processing by Annealing on Additive Manufacturing Productivity and Mechanical Properties in Three-Point Bending of Additively Manufactured Specimens from PETG and Recycled PETG
    Dragos Gabriel Zisopol, Mihail Minescu, Dragos Valentin Iacob +1
    PolymersPeer-reviewedCC BYFull textMaterials & polymersEurope PMC
  2. Artificial Intelligence for a Circular Solvent Economy: An Environmental Decision-Support Architecture for Sustainable Pharmaceutical Manufacturing
    ISAK RAJJAK SHAIKH
    ChemRxivPreprintCC BYFull textEnvironmental chemistryChemRxiv
  3. Additive manufacturing of a Ni-20 wt%Cr binary alloy by laser powder bed fusion: Impact of the microstructure on the mechanical properties
    Eric Hug, Maxime Lelièvre, Cendrine Folton +3
    Materials Science and Engineering: APeer-reviewedLicence not stated17 citedMaterials & polymersGeneral physicsHAL
  4. Polymeric Materials for Ophthalmic Lenses: A Systematic Review on Structure, Properties, Manufacturing and Sustainability
    Marco Calvi, Elisa Baldini, Matteo Maria Minotto +4
    MoleculesPeer-reviewedCC BY 4.0Full textMaterials & polymersCrossrefEurope PMC
  5. Bismuth-Catalyzed Multifunctional Polydimethylsiloxane (PDMS) Composites with Tunable Thermomechanical Properties for Scalable Manufacturing
    Nadim S. Hmeidat, Steven E. Bullock, Umesh Marathe +2
    ACS OmegaPeer-reviewedCC BY 4.0Full textGeneral chemistryCrossref

Cite

BibTeXRIS
BibTeX
@misc{sanpui2026from,
  title = {{From Processing to Programmable Properties: A Review of Artificial Intelligence in Metal Additive Manufacturing}},
  author = {Dipayan Sanpui and Sukriti Manna and Subramanian KRS Sankaranarayanan},
  howpublished = {ChemRxiv},
  year = {2026},
  month = oct,
  doi = {10.26434/chemrxiv.15011182/v1},
  url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011182/v1},
  note = {CC BY},
}
RIS
TY  - UNPB
TI  - From Processing to Programmable Properties: A Review of Artificial Intelligence in Metal Additive Manufacturing
AU  - Dipayan Sanpui
AU  - Sukriti Manna
AU  - Subramanian KRS Sankaranarayanan
PY  - 2026
DA  - 2026/10/28
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15011182/v1
UR  - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011182/v1
AB  - Machine learning has accelerated process–structure–property (PSP) prediction in metal additive manufacturing (AM), but a predicted optimum is useful only if it can be realized through processing and verified experimentally. This review examines that transition by connecting physics-based simulation, data curation, microstructure representation and reconstruction, and inverse design. We assess the information each stage retains, the assumptions it introduces, and the uncertainty it passes to subsequent decisions. Three tests organize the synthesis: structural fidelity, independently evaluated property performance, and accessibility through a specified processing route. Using these tests, we compare forward and inverse methods in terms of their data requirements, physical constraints, and validation evidence, distinguishing metal-AM demonstrations from transferable approaches developed in adjacent fields. Recurring limitations include simulation–experiment mismatch, incomplete dataset provenance, representation-dependent ambiguity, and insufficient testing outside the training domain. We outline benchmarks and reporting practices that make these limitations visible and connect them to priorities in physics-informed, multifidelity, interpretable, and multimodal learning. The resulting roadmap places experimental feedback at the center of the design workflow and identifies the evidence needed to translate rapid predictions into reproducible control of microstructure and properties.
ER  -