Towards high-throughput microstructure simulation in compositionally complex alloys via machine learning
نویسندگان
چکیده
Abstract The coupling of computational thermodynamics and kinetics has been the central research theme in Integrated Computational Material Engineering (ICME). Two major bottlenecks implementing this performing efficient ICME-guided high-throughput multi-component industrial alloys discovery or process parameters optimization, are slow responses kinetic calculations to a given set compositions processing conditions quality large amount calculated thermodynamic data. Here, we employ machine learning techniques eliminate them, including (1) intelligent corrupt data detection re-interpolation (i.e. purge/cleaning) big tabulated dataset based on an unsupervised algorithm (2) parameterization via artificial neural networks purged into non-linear equation consisting base functions coefficients. two enable linkage high-quality with previously developed microstructure model. This proposed approach not only improves model performance by eliminating interference stability due boundedness continuity obtained but also dramatically reduces running time demand for computer physical memory simultaneously. high robustness, efficiency, accuracy, which prerequisites computing, verified series case studies aluminum, steel, high-entropy alloys. purge methods expected apply various simulation approaches bridging multi-scale where handling input is required. It concluded that valuable tool fueling development ICME throughput materials simulations.
منابع مشابه
Machine Learning for Market Microstructure and High Frequency Trading
In this chapter, we overview the uses of machine learning for high frequency trading and market microstructure data and problems. Machine learning is a vibrant subfield of computer science that draws on models and methods from statistics, algorithms, computational complexity, artificial intelligence, control theory, and a variety of other disciplines. Its primary focus is on computationally and...
متن کاملMachine Learning for High-Throughput Stress Phenotyping in Plants.
Advances in automated and high-throughput imaging technologies have resulted in a deluge of high-resolution images and sensor data of plants. However, extracting patterns and features from this large corpus of data requires the use of machine learning (ML) tools to enable data assimilation and feature identification for stress phenotyping. Four stages of the decision cycle in plant stress pheno...
متن کاملCHARACTERIZATION OF THE MICROSTRUCTURE OF THE COMPOSITIONALLY COMPLEX ALLOY Al1MoNb1Ta0.5Ti1Zr1 (POSTPRINT)
متن کامل
High-Throughput Characterization of Surface Segregation in CuxPd1 x Alloys
High-Throughput Characterization of Surface Segregation in CuxPd1 x Alloys Deepika Priyadarshini, Petro Kondratyuk, Yoosuf N. Picard, Bryan D. Morreale, Andrew J. Gellman, and James B. Miller* National Energy Technology Laboratory, U.S. Department of Energy, Pittsburgh, Pennsylvania 15236, United States Department of Chemical Engineering and Department of Materials Science and Engineering, Carn...
متن کاملPreparation of compositionally-controlled Pt-based nanoparticle alloys via microplasma reduction of aqueous metal ions
Nanoparticle alloys of platinum (Pt) and another metal are desirable for catalytic applications to decrease the loading of the precious metal and alter the physiochemical structure of these materials to enhance their catalytic properties. This study explores the potential of producing gold and platinum nanoparticle alloys using a microplasma reduction technique. In this process, metal salt prec...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Calphad-computer Coupling of Phase Diagrams and Thermochemistry
سال: 2021
ISSN: ['1873-2984', '0364-5916']
DOI: https://doi.org/10.1016/j.calphad.2020.102231