One of the major design issues in machine learning (ML) models for materials property prediction(MPP) is how to enable the models to learn property related physicochemical features. While many composition...

No abstract

The availability and easy access of large-scale experimental and computational materials data have enabled the emergence of accelerated development of algorithms and models for materials property prediction, structure prediction, and generative design of materials. However, the lack of user-friendly materials informatics web servers has severely constrained the wide adoption of such tools in the daily practice of materials screening, tinkering, and design space exploration by materials scientists. Herein we first survey current materials informatics web apps and then propose and develop MaterialsAtlas.org, a web-based materials informatics toolbox for materials discovery, which includes a variety of routinely needed tools for exploratory materials discovery, including material’s composition and structure validity check (e.g. charge neutrality, electronegativity balance, dynamic stability, Pauling rules), materials property prediction (e.g. band gap, elastic moduli, hardness, and thermal conductivity), search for hypothetical materials, and utility tools. These user-friendly tools can be freely accessed at http://www.materialsatlas.org. We argue that such materials informatics apps should be widely developed by the community to speed up materials discovery processes.

SiC f -SiC m composites are being actively developed as fuel cladding for improving accident tolerance of light water reactor fuel. Online monitoring of the degradation process in SiC f -SiC m composites is of great importance to ensure the safety of the nuclear reactor system. The degradation monitoring task can be mapped as a classification problem: given the Acoustic Emission(AE) events at a given timeslot, the model is expected to predict which one of the following three stages the material is in: elastic, matrix-driven and fiber-driven cracking. In this paper, degradation tests on SiC f -SiC m composite tubes were conducted using a bladder-based internal pressure technique with AE monitoring. We then trained a deep learning based endto-end convolutional neural network (CNN) model for online monitoring of the damage progression process of SiC f -SiC m composite tubes using the AE data as the raw input. As a comparison, we also applied Random Forest (RF) with expert-crafted audio event features to the damage stage prediction problem. Experimental results show that both RF and CNN models yield good results but on average our end-to-end CNN models outperform the RF models due to its high-level feature extraction capability. The CNN model with single events can reach an average prediction accuracy of 84.4% compared to 74% of the RF models. Combining multiple audio samples typically improves the accuracy of the models with RF accuracy reaching 82.8% and CNN accuracy reaching 86.6%.INDEX TERMS Acoustic emission (AE), convolutional neural network (CNN), deep learning, online damage monitoring, random forest (RF), SiC composites.

No abstract