English

A BRAVE Alloy Design Campaign (Bayesian Risk-aware Alloy discoVery and Exploration)

Materials Science 2026-06-25 v1

Abstract

In constrained alloy optimization, the compositions with the highest performance potential often reside at the boundary of phase stability -- where the risk of experimental failure is also highest. This work demonstrates this principle through a risk-aware Bayesian optimization campaign on single-phase FCC high-entropy alloys in the Al-V-Cr-Mn-Fe-Co-Ni-Cu system. A learned feasibility classifier, integrated directly into the multi-objective acquisition function, probabilistically penalizes candidates likely to produce failed experiments while preserving access to high-performing boundary compositions. From approximately 27,000 CALPHAD-screened candidates, 48 alloys were synthesized over three closed-loop iterations targeting five objectives (yield strength, UTS/YS ratio, strain at UTS, dynamic-to-quasi-static hardness ratio, and simulated depth of penetration), exploring 0.12\% of the feasible space. Two compositional regimes emerged: a V-rich, Ni-rich high-strength regime (UTS up to 1480{\sim}1480~MPa at 50% elongation) and a Mn-containing high-ductility regime (UTS/YS up to 4.20 at >>50% elongation). Among feasible alloys, vanadium simultaneously drives yield strength (r=0.84r = 0.84) and sigma-phase formation (r=0.54r = 0.54 with infeasibility); at V = 24~at.%, the three strongest alloys and three sigma failures share the same compositional point. Additionally, the strongest performing alloys cluster in a narrow region of compositional space (V \geq 20 at.%, Ni \geq 36 at.%), representing 100{\sim}100 of 27,07427,074 feasible candidates -- a probability of P6.5×106P \approx 6.5 \times 10^{-6} under random sampling. This dual role -- consistent with the KKT prediction that constrained optima lie on active constraint boundaries -- required feasibility-aware acquisition to access; hard filtering would have excluded this region entirely.

Keywords

Cite

@article{arxiv.2606.27522,
  title  = {A BRAVE Alloy Design Campaign (Bayesian Risk-aware Alloy discoVery and Exploration)},
  author = {Mrinalini Mulukutla and Danial Khatamsaz and Trevor Hastings and Wenle Xu and Daniel Salas and Joydeep Kundu and Vasanth C. Shunmugasamy and Daniel Lewis and Jacob Hempel and Clinton Strosser and Alexandra Salinas and Brent Vela and Nicolas Flores and Sina Hossein Zadeh and Ali Rachidi and David Elbert and Brady Butler and James Paramore and Dimitris Lagoudas and Justin Wilkerson and George Pharr and Douglas Allaire and Vahid Attari and Ibrahim Karaman and Ankit Srivastava and Raymundo Arróyave},
  journal= {arXiv preprint arXiv:2606.27522},
  year   = {2026}
}

Comments

Main article including appendix - 30 pages. Supplemental information - 24 pages. Link to github repository is included for code and data in the project