Machine learning for design, phase transformation and mechanical properties of alloys

The potency of defects on fatigue of additively manufactured metals

“…In recent years, machine learning (ML) based big data driven methods have played an important role in developing a predictive capability for material properties and lightweight design based on extensive experimental evidence [20][21][22][23] . Indeed, support vector machine (SVM), Random-Forest (RF), Gaussian process regression (GPR), shallow neural network (SNN), deep neural network (DNN), Linear regression (LR), and artificial neural networks (ANN) have all been found to make accurate life and crack propagation predictions, based on fatigue-related data for conventionally processed metals and alloys [24][25][26][27][28][29][30][31][32] .…”

Machine learning for high-entropy alloys: Progress, challenges and opportunities

“…Identifying them allows researchers to explore the enormous design space of HEAs more efficiently. The above merits of ML has ushered in a new data-driven paradigm to the research of HEAs [66,67], as demonstrated in its success in the atomistic simulations [68,69,70], physical property prediction [48][71], and materials design [72,73,74].…”

“…While several excellent reviews have already been available on the broader topic of ML for materials science [75,76,77,78,79,80,67,66], there is a lack of comprehensive reviews for the exciting progress and huge potential of ML for HEAs. For instance, Drodola reviewed the applications of ML for alloys in a recent publication [66], which focused on using artificial neural networks for alloy design, processing, and characterization. Another review on ML for alloys was presented by Hart et al [67], where they summarized the current state of machine-learning-driven alloy research.…”

Modelling of phase stability: integrating computational materials science and materials informatics

“…Recently, great successes have been achieved in machine learning studies of a large variety of materials [118][119][120] . However, the lack interpretability of machine learning algorithms and results limits the applications of machine learning in reality and especially stability-sensitive tasks.…”