AI for alloy design and additive-manufacturing qualification: Junction Brief – November 2026

Acentric Research is produced with AI tools under human review. The authors are not financial professionals, and nothing here is investment advice or a recommendation to buy or sell any security. AI analysis can be wrong; check every claim against its cited source.

This Brief is an initial scan, not a full investigation. The method and scores behind it are in AI × Materials in the Landscape Report.

Overview

Metal parts can be 3D printed layer by layer, which is called additive manufacturing. The Paul Scherrer Institute says printed parts are typically used as built, so their structure and performance are set almost entirely by the alloy and the rapid heating and cooling during printing, and the alloy must resist cracking. [1] This Brief covers artificial intelligence (AI), here mainly machine learning, used to design alloys for printing and to check the printed parts.

What stands out is that the public evidence found is a research paper and defense-funded projects, not production use. In the sources opened, the work is at the project stage. [1][2] The two project sources are from August 2025; later developments were not searched.

Current state

Alloy design. The Paul Scherrer Institute in Switzerland describes a machine-learning framework for designing alloys for additive manufacturing. It combines thermodynamic simulations with predictive models to evaluate properties relevant to printing, such as solidification behaviour, resistance to cracking and how quickly strengthening particles form. One alloy was designed, printed with different laser-based techniques and examined with X-ray microdiffraction, which the institute says provided experimental validation of the design framework. The measurements mapped local crystal phases and dislocation density at points across the printed material, which the institute says helped explain the alloy’s mechanical performance. The institute notes that printing makes intricate metal parts without the multiple processing steps of traditional routes, which often include heat or deformation treatments after casting or forging. The work was published in Materials Today in 2025. [1]

Checking printed parts. In August 2025 the University of Arizona’s Mach-X team reported a $5 million U.S. Army grant for an alloy manufacturing process that integrates 3D printing and machine learning, for components of hypersonic vehicles (vehicles that travel at least five times the speed of sound). The team is working with Raytheon, an RTX business, on nickel alloy prototypes meant to keep their integrity above 1,100 degrees Celsius. The team says it will apply machine learning and an acoustic, non-destructive technique to assess quality as the part is built, and will train the algorithm on simpler parts first. [2]

What the team expects. The team lead says the main task is to identify the best metal compositions and design a durable printed microstructure. The team says the algorithm will be trained on the simpler parts and used to interpret acoustic responses, which “will tell us with a high degree of confidence if there are defects”. [2]

Federal aims. DOE’s Genesis Mission opportunity includes a focus area on AI-enabled materials discovery, development and qualification. Its structural-materials focus area asks for interpretable AI models and agentic experimental workflows to understand how materials behave under stress and extreme environments. The qualification focus area seeks closed-loop autonomous systems and AI-enabled prediction “to compress traditional multi-year qualification processes”, and covers high-temperature structural materials, among others. [3] A separate focus area on plasma-facing materials for fusion energy proposes AI-enabled digital twins of heat and plasma exposure facilities to support the characterization, manufacturing and qualification of materials that face extreme temperatures and neutron fluxes. [3]

Why the gap matters. DOE’s Genesis opportunity calls the gap between scientific discovery and commercially viable products the “valley of death” and names it the biggest challenge in industrial manufacturing. [3]

How far it has come. A designed alloy printed and examined in a research laboratory, and funded projects to apply machine learning to printing and inspection. The sources opened do not report a qualified production part; other published work on alloys for printing exists that this Brief did not open.

Opportunities

DOE’s call names the compression of multi-year qualification as its aim, which is a stated goal. [3] If in-process checking works as the Arizona team describes, defects could be found as a part is built rather than after. [2] The report says the award follows an earlier $3.1 million Army grant for refractory alloy research, and that the team is working with Raytheon, an RTX business, on prototypes. [2] The institute’s work shows one route to alloys designed for printing rather than adapted from casting. [1]

Challenges

  • Engineering. The Arizona team says its components must keep their integrity above 1,100 degrees Celsius for extended periods under significant mechanical stress. [2] Alloys for printing must withstand rapid solidification, thermal cycling and cracking risks. [1]
  • Evidence. The sources opened describe one designed alloy and funded projects, not results from the Army project. [1][2]
  • Qualification. DOE’s call describes qualification as a multi-year process that it aims to shorten. [3]

Data sources

  • Defense and university announcements for projects such as Mach-X, as institutional claims. [2]
  • Scientific journals for alloy-design papers. [1]
  • DOE funding opportunities, including Genesis. [3]
  • USAspending.gov for federal awards. [4]
  • No registry lists qualified printed parts or the methods used.

Changelog

  • 2026-11-18: First published.

Sources

  1. Paul Scherrer Institute, “Machine Learning Accelerates Alloy Design for Additive Manufacturing”, scientific highlight, 2025-08-19 (institute statement on a paper by J. Su and others, Materials Today 88, 240, 2025). psi.ch(accessed 2026-11-18)
  2. Paloma Duran, “Mach-X Team Secures $5 Million to Integrate 3D Printing and Machine Learning for Hypersonics”, 3D Printing Industry, 2025-08-21 (reports University of Arizona statements). 3dprintingindustry.com(accessed 2026-11-18)
  3. US Department of Energy, “The Genesis Mission: Transforming Science and Energy with AI”, Notice of Request for Application DE-FOA-0003612, issued 2026-03-17, Amendment 000003 of 2026-04-20; challenges 1 and 12, focus area F. science.osti.gov (accessed 2026-11-18)
  4. USAspending.gov, home page. usaspending.gov (accessed 2026-11-18)