Search for: All records

Abstract Materials design aims to identify the material features that provide optimal properties for various engineering applications, such as aerospace, automotive, and naval. One of the important but challenging problems for materials design is to discover multiple polycrystalline microstructures with optimal properties. This paper proposes an end-to-end artificial intelligence (AI)-driven microstructure optimization framework for elastic properties of materials. In this work, the microstructure is represented by the Orientation Distribution Function (ODF) that determines the volume densities of crystallographic orientations. The framework was evaluated on two crystal systems, cubic and hexagonal, for Titanium (Ti) in Joint Automated Repository for Various Integrated Simulations (JARVIS) database and is expected to be widely applicable for materials with multiple crystal systems. The proposed framework can discover multiple polycrystalline microstructures without compromising the optimal property values and saving significant computational time. 

There are two broad modeling paradigms in scientific applications: forward and inverse. While forward modeling estimates the observations based on known causes, inverse modeling attempts to infer the causes given the observations. Inverse problems are usually more critical as well as difficult in scientific applications as they seek to explore the causes that cannot be directly observed. Inverse problems are used extensively in various scientific fields, such as geophysics, health care and materials science. Exploring the relationships from properties to microstructures is one of the inverse problems in material science. It is challenging to solve the microstructure discovery inverse problem, because it usually needs to learn a one-to-many nonlinear mapping. Given a target property, there are multiple different microstructures that exhibit the target property, and their discovery also requires significant computing time. Further, microstructure discovery becomes even more difficult because the dimension of properties (input) is much lower than that of microstructures (output). In this work, we propose a framework consisting of generative adversarial networks and mixture density networks for inverse modeling of structure–property linkages in materials, i.e., microstructure discovery for a given property. The results demonstrate that compared to baseline methods, the proposed framework can overcome the above-mentioned challenges and discover multiple promising solutions in an efficient manner.

 

Abstract Many photosynthetic species have evolved CO2-concentrating mechanisms (CCMs) to improve the efficiency of CO2 assimilation by Rubisco and reduce the negative impacts of photorespiration. However, the majority of plants (i.e. C3 plants) lack an active CCM. Thus, engineering a functional heterologous CCM into important C3 crops, such as rice (Oryza sativa) and wheat (Triticum aestivum), has become a key strategic ambition to enhance yield potential. Here, we review recent advances in our understanding of the pyrenoid-based CCM in the model green alga Chlamydomonas reinhardtii and engineering progress in C3 plants. We also discuss recent modeling work that has provided insights into the potential advantages of Rubisco condensation within the pyrenoid and the energetic costs of the Chlamydomonas CCM, which, together, will help to better guide future engineering approaches. Key findings include the potential benefits of Rubisco condensation for carboxylation efficiency and the need for a diffusional barrier around the pyrenoid matrix. We discuss a minimal set of components for the CCM to function and that active bicarbonate import into the chloroplast stroma may not be necessary for a functional pyrenoid-based CCM in planta. Thus, the roadmap for building a pyrenoid-based CCM into plant chloroplasts to enhance the efficiency of photosynthesis now appears clearer with new challenges and opportunities. 

Part quality manufactured by the laser powder bed fusion process is significantly affected by porosity. Existing works of process–property relationships for porosity prediction require many experiments or computationally expensive simulations without considering environmental variations. While efforts that adopt real-time monitoring sensors can only detect porosity after its occurrence rather than predicting it ahead of time. In this study, a novel porosity detection-prediction framework is proposed based on deep learning that predicts porosity in the next layer based on thermal signatures of the previous layers. The proposed framework is validated in terms of its ability to accurately predict lack of fusion porosity using computerized tomography (CT) scans, which achieves a F1-score of 0.75. The framework presented in this work can be effectively applied to quality control in additive manufacturing. As a function of the predicted porosity positions, laser process parameters in the next layer can be adjusted to avoid more part porosity in the future or the existing porosity could be filled. If the predicted part porosity is not acceptable regardless of laser parameters, the building process can be stopped to minimize the loss.

 

Nickel‐rich layered materials LiNi_1‐x‐yMn_xCo_yO₂are promising candidates for high‐energy‐density lithium‐ion battery cathodes. Unfortunately, they suffer from capacity fading upon cycling, especially with high‐voltage charging. It is critical to have a mechanistic understanding of such fade. Herein, synchrotron‐based techniques (including scattering, spectroscopy, and microcopy) and finite element analysis are utilized to understand the LiNi_0.6Mn_0.2Co_0.2O₂material from structural, chemical, morphological, and mechanical points of view. The lattice structural changes are shown to be relatively reversible during cycling, even when 4.9 V charging is applied. However, local disorder and strain are induced by high‐voltage charging. Nano‐resolution 3D transmission X‐ray microscopy data analyzed by machine learning methodology reveal that high‐voltage charging induced significant oxidation state inhomogeneities in the cycled particles. Regions at the surface have a rock salt–type structure with lower oxidation state and build up the impedance, while regions with higher oxidization state are scattered in the bulk and are likely deactivated during cycling. In addition, the development of micro‐cracks is highly dependent on the pristine state morphology and cycling conditions. Hollow particles seem to be more robust against stress‐induced cracks than the solid ones, suggesting that morphology engineering can be effective in mitigating the crack problem in these materials.