Year: 2025
Type: article
Abstract: In this study, we present an artificial intelligence (AI)-driven framework for predicting the microstructural texture of polycrystalline materials after a specific deformation process. The microstructural texture is defined in terms of the orientation distribution function (ODF) which indicates the volume density of crystal orientations. Our approach leverages an encoder-decoder model with Long Short-Term Memory (LSTM) layers to model the relationship between processing conditions and material properties. As a case study, we apply our framework to copper, generating a dataset of 3125 unique processing parameter combinations and their corresponding ODF vectors. The resulting predictions enable the calculation of homogenized properties. Our AI-driven framework outperforms traditional material processing simulations, yielding faster results with limited error rates (< 0.3% for both the elastic matrix C and the compliance matrix S), making it a promising tool for the expedited design of microstructures with tailored properties.
Source: Scientific Reports
Institutions: Northwestern University, Virginia Tech
Language: English
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,690
Awards: RAPIDS2: A SCIDAC INSTITUTE FOR COMPUTER SCIENCE, DATA, AND ARTIFICIAL INTELLIGENCE, Collaborative Research: AI-Driven Multi-Scale Design of Materials under Processing Constraints, PURPOSE: THE PURPOSE OF THIS WORK IS TO FURTHER SEVERAL ONGOING COLLABORATIONS WITH NIST AND THE CENTER FOR HIERARCHICAL MATERIALS DESIGN.ACTIVITIES TO BE PERFORMED: THIS PROJECT WILL SUPPORT SEVERAL KEY ACTIVITIES OF THE CENTER FOR HIERARCHICAL MATERIALS DESIGN IN COLLABORATION WITH NIST. THESE ACTIVITIES ARE THE BENCHMARKING OF PHASE FIELD MODELS, UNCERTAINTY QUANTIFICATION OF PHASE DIAGRAMS, ARTIFICIAL INTELLIGENCE MODELING AND PREDICTION OF MATERIALS PERFORMANCE, AND OUTREACH EFFORTS AND COMMUNITY BUILDING IN SUPPORT OF THESE EFFORTS. EXPECTED OUTCOMES: THE WORK WILL RESULT IN IMPROVED MODELS OF MATERIALS PROCESSING AND PERFORMANCE, AND DISSEMINATION OF THESE RESULTS TO THE BROADER R&D COMMUNITY. SPECIFICS AREAS OF APPLICATION INCLUDE ALLOYS FOR ADDITIVE MANUFACTURING, MATERIALS FOR CLEAN ENERGY, AND IMPROVED RECYCLABILITY. INTENDED BENEFICIARIES: THE MODELS DEVELOPED IN THIS WORK, AND THE ASSOCIATED DATA, HAVE NUMEROUS BENEFICIARIES. THE RESEARCHERS AND THEIR UNIVERSITY BENEFIT VIA ENHANCED PORTFOLIOS OF MATERIALS R&D, WHILE NIST BENEFITS VIA ROBUST COLLABORATION WITH WORLD-CLASS ACADEMIC RESEARCHERS IN MATERIALS SCIENCE AND ENGINEERING. STUDENTS WILL BENEFIT FROM STATE-OF-THE-ART TRAINING IN MATERIALS RESEARCH. THE ULTIMATE BENEFICIARY IS, OF COURSE, THE PUBLIC, AS THE DEVELOPMENT OF NEW MATERIALS CAN IMPACT THE PUBLIC WITH A CLEANER ENVIRONMENT, IMPROVED HEALTHCARE, AND A MORE EFFECTIVE NATIONAL DEFENSE.SUBRECIPIENT ACTIVITIES: THE RECIPIENT DOES NOT INTEND TO SUBAWARD FUNDS, EAGER: XAISE: Explainable Artificial Intelligence for Science and Engineering, Collaborative Research: AI-Driven Multi-Scale Design of Materials under Processing Constraints
OpenAlex ID: W4412049436