Skip to content
Preprint

Physics-guided inverse design of Co-based superalloys using machine learning and multi-objective optimization for enhanced $\gamma'$ solvus temperature

Sep 2026 · 0 citations · 47 references
Physics

TL;DR

This physics-informed inverse design framework provides an efficient route for identifying high-performance Co-based superalloys and can be adapted to other advanced structural alloys.

Abstract

The discovery of next-generation Co-based superalloys with improved high-temperature stability is hindered by the vast compositional design space and complex interactions among alloying elements governing gamma-prime phase stability. This study presents a physics-informed machine learning framework for the inverse design of Co-based superalloys with higher gamma-prime solvus temperature while accounting for alloy density. Four descriptors representing atomic size mismatch (delta-MV), mixing enthalpy (Delta-Hm), electronegativity mismatch (delta-EN), and valence electron concentration mismatch (delta-VEC) were used to characterize the chemistry governing phase stability. Regression algorithms were evaluated using leave-one-out cross-validation, with Gaussian Process Regression (GPR) achieving the best performance (R2 = 0.932, RMSE = 34.7 deg C, and MAE = 25.9 deg C). The probabilistic nature of GPR enabled uncertainty-aware Bayesian optimization for exploring the uncharted composition space. Non-dominated Sorting Genetic Algorithm II (NSGA-II) and Genetic Algorithms were used to simultaneously increase gamma-prime solvus temperature and reduce alloy density. The optimization generated numerous previously unexplored Co-based alloy compositions, with predicted gamma-prime solvus temperatures of 1248-1353 deg C, including candidates approaching or exceeding the maximum value in the experimental dataset. Descriptor analysis identified atomic size mismatch and mixing enthalpy as key factors governing gamma-prime stability, while principal component analysis confirmed that the proposed alloys occupy chemically relevant descriptor regions. This physics-informed inverse design framework provides an efficient route for identifying high-performance Co-based superalloys and can be adapted to other advanced structural alloys.

View source

Similar papers

Open access Aug 2026

Multi-objective and cross-scale inverse design of temperature-control materials via physics-constrained machine learning

An artificial intelligence framework that incorporates a physics-constrained inverse-design system (PHICS) built upon a directed acyclic graph (DAG) architecture for CPCMs, integrating interface, phase, and carrier engineering.

Dong-Liang Ding, Min-Hao Zou, Ruo-Yu Huang et al. · 0 citations
Open access Sep 2026

AI/ML-Assisted Inverse Alloy Design of Multi-Principal Element Alloys for High-Temperature Energy Systems: Comparative Tree Ensembles and Deep Neural-Network Surrogates

AI/ML is positioned not as a replacement for experiment, but as a transparent decision-support layer for narrowing high-dimensional alloy spaces and prioritising candidates for experimental validation in high-temperature energy applications.

Harikrishnan Kumarasamy · 0 citations
Open access Aug 2026

Resolving the strength-ductility trade-off in Al-Mg-Si alloys via physics-informed machine learning

Composition-based machine learning for Al-Mg-Si alloys lacks generalization. A physics-informed strategy incorporating physicochemical descriptors was proposed, improving the coefficient of determination (R2) by 30% over composition-only models. Shapley additive explanations (SHAP) identified electronegativity differen...

Jun Li, Chen Su, Chen-Lu Yu et al. · 1 citation
Open access Sep 2026

Phase-stability-guided explainable machine learning for mechanical-property prediction and experimentally supported candidate screening of high-entropy alloys

High-entropy alloys (HEAs) provide a broad compositional space for developing structural materials with balanced phase stability and mechanical performance. However, reliable mechanical-property prediction remains challenging because alloy chemistry, phase constitution, processing state, and model uncertainty are s...

De-Rong Yuan, De-Lin Yuan, Xiao-Yu Xu · 0 citations
Preprint Oct 2026

Mechanical properties of V-4Ti-4Cr alloy from molecular dynamics with a neural-network potential

Machine-learning interatomic potentials enable large-scale atomistic simulations of vanadium alloys relevant to fusion applications, but reliable training and validation remain challenging in multicomponent systems. Here, we develop a descriptor-based DeepMD-DPA1 potential for the V-Ti-Cr system using a two-stage workf...

G. S. Demyanov, D. Minakov, S. B. Saltykov et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.