Efficiently exploiting process-structure-property relationships in material design by multi-information source fusion

Materials design calls for the (inverse) exploitation of Process-Structure-Property (PSP) relationships to produce materials with targeted properties. Unfortunately, most frameworks are not optimal, given resource constraints. Bayesian Optimization (BO)-based increasingly used in as they balance exploration and spaces. Most BO-based assume that space can be queried by a single information source (e.g. experiment or simulation). Recently, we demonstrated microstructure-sensitive alloys BO framework capable exploiting multiple sources. While promising, previous is limited it assumes optimal microstructure always feasible considers microstructural features space. Herein, sidestep this unwarranted assumption instead consider chemistry processing conditions constitute amenable optimization. We demonstrate efficacy our expanded optimizing mechanical performance ferritic/martensitic dual-phase material adjusting composition/processing parameters. The uses thermodynamic results predict attributes which then properties using variety micromechanical models microstructure-based finite element model. final stage involves implementing model reification fusion, knowledge-gradient acquisition function determine next best point sources query. A detailed discussion various components demonstration how implemented under three sets cost-based constraints presented.