[HTML][HTML] Review of conventional and advanced non-destructive testing techniques for detection and characterization of small-scale defects

MI Silva, E Malitckii, TG Santos, P Vilaça - Progress in Materials Science, 2023 - Elsevier
Inspection reliability of small-scale defects, targeting dimensions below 100 µm, is crucial for
structural safety of critical components in high-value applications. Early defects are often …

Materials data toward machine learning: advances and challenges

L Zhu, J Zhou, Z Sun - The Journal of Physical Chemistry Letters, 2022 - ACS Publications
Machine learning (ML) is believed to have enabled a paradigm shift in materials research,
and in practice, ML has demonstrated its power in speeding up the cost-efficient discovery of …

Combining crystal plasticity and phase field model for predicting texture evolution and the influence of nuclei clustering on recrystallization path kinetics in Ti-alloys

AM Roy, S Ganesan, P Acar, R Arróyave… - Acta Materialia, 2024 - Elsevier
A three-dimensional computational framework has been developed combining a crystal
plasticity (CP) and a phase-field (PF) approach that can efficiently simulate static …

Multi-fidelity microstructure-induced uncertainty quantification by advanced Monte Carlo methods

A Tran, P Robbe, H Lim - Materialia, 2023 - Elsevier
Quantifying uncertainty associated with the microstructure variation of a material can be a
computationally daunting task, especially when dealing with advanced constitutive models …

[HTML][HTML] Confidence intervals of inversely identified material model parameters: A novel two-stage error propagation model based on stereo DIC system uncertainty

A Maček, B Starman, S Coppieters, J Urevc… - Optics and Lasers in …, 2024 - Elsevier
Digital image correlation (DIC) is a powerful tool for characterising materials and
determining material model parameters. To assess the reliability of the full-field …

Uncertainty quantification of metallic microstructures using principal image moments

A Senthilnathan, I Javaheri, H Zhao… - Computational Materials …, 2022 - Elsevier
The present work uses Markov Random Field (MRF) algorithm to construct large-scale and
statistically-equivalent samples from small-scale experimental data of metallic …

Methods and applications of machine learning in computational design of optoelectronic semiconductors

X Yang, K Zhou, X He, L Zhang - Science China Materials, 2024 - Springer
The development of high-throughput computation and materials databases has laid the
foundation for the emergence of data-driven machine learning methods in recent years …

Monotonic Gaussian process for physics-constrained machine learning with materials science applications

A Tran, K Maupin, T Rodgers - … of Computing and …, 2023 - asmedigitalcollection.asme.org
Physics-constrained machine learning is emerging as an important topic in the field of
machine learning for physics. One of the most significant advantages of incorporating …

Uncertainty quantification in multivariable regression for material property prediction with Bayesian neural networks

L Li, J Chang, A Vakanski, Y Wang, T Yao, M Xian - Scientific Reports, 2024 - nature.com
With the increased use of data-driven approaches and machine learning-based methods in
material science, the importance of reliable uncertainty quantification (UQ) of the predicted …

Performance prediction of gas turbine blade with multi-source random factors using active learning-based neural network

Z Qiu, Y Wang, J Li, Y Xie, D Zhang - Applied Thermal Engineering, 2024 - Elsevier
Rapid and accurate performance acquisition of high-temperature gas turbine blades is
fundamental to energy system design, analysis, and evaluation. Data-driven surrogate …