http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
생성모델을 적용한 나트륨이온 배터리용 슈퍼 이온전도성 고체 전해질 설계
강승표(Seungpyo Kang),민경민(Kyoungmin Min) 대한기계학회 2022 대한기계학회 춘추학술대회 Vol.2022 No.11
Na-Ion Batteries(NIBs) is an alternative to Li-Ion Batteries(LIBs). Solid-state electrolytes solve critical safety issues of liquid electrolyte. In this study, we developed a platform involving generative model, high-throughput screening process and a machine learning surrogate model for identifying superionic Na-SSEs among Na-containing materials. Through the screening process, materials which showed potentially superior performance are selected, and their ionic conductivity were predicted. The surrogated model was constructed by ensembling two models with the best performance. 100 predictions were made for each model. In all 100 times, materials predicted to be superionic were inter-aggregated, and no material was recommended. Detail structural Descriptor will be considered. After this consideration, we believe this platform will accelerate the search for Na-SSEs with high ionic conductivity at a minimum cost.
기계학습을 이용한 신규 Double Perovskite 스크리닝
김준철(Joonchul Kim),민경민(Kyoungmin Min) 대한기계학회 2020 대한기계학회 춘추학술대회 Vol.2020 No.12
Double perovskite structures have brought a lot of attention due to their great potentials for applications of batteries, lighting-devices, and energy harvesting materials. In this study, machine learning algorithm is employed to search for new stable double perovskite materials. First, the materials properties are adopted from well-established Materials Project database to develop a prediction model for the formation energy and the convex hull energy. Then, the bagging and boosting based algorithms are implemented to train the database for regression as well as classification model and their prediction accuracy is compared. For prediction of the formation energy, it’s R2 and RMSE value reaches to 0.97 and 0.2020 eV/atom. In addition, the classification accuracy for the convex hull energy shows 0.76 with F1-score of 0.763. Finally, trained machine learning model is applied to the whole chemical space of the double perovskite structures and it exhibits that 8,613 structures are potentially stable to be synthesized. In the meanwhile, 25,062 and 19,766 structures are shown to be metastable and instable, respectively.
Molecular Dynamics simulation을 이용한 3D printed zeolite 구조체의 미시적, 거시적 기계적 거동 분석
김준철(Joonchul Kim),민경민(Kyoungmin Min) 대한기계학회 2023 대한기계학회 춘추학술대회 Vol.2023 No.11
Mechanical properties are important properties from atomic unit structures to micro-level structures. Discovering the correlation between structural information and mechanical reactions can accelerate the structure design with desired mechanical properties. By establishing a link between mechanical properties and structural information, we prove the possibility of purposeful structural design. We focus on uncovering resemblances in mechanical behavior between atomistic arrangements and 3D-printed zeolite structures. Employing molecular dynamics simulations, we validate the emergence of similar mechanical responses at both atomic and macroscopic scales. 3D printed structure using thermoplastic polyurethane (TPU) filaments can reflect the response of microstructural-level simulations, which can link between experiment and theory. These results demonstrate that the design can realize meta-materials with ideal mechanical reactions based on theoretical results of atomic structures.
생성모델을 적용한 나트륨이온 배터리용 슈퍼 이온전도성 고체 전해질 설계
강승표(Seungpyo Kang),민경민(Kyoungmin Min) 대한기계학회 2022 대한기계학회 춘추학술대회 Vol.2022 No.11
Na-Ion Batteries(NIBs) is an alternative to Li-Ion Batteries(LIBs). Solid-state electrolytes solve critical safety issues of liquid electrolyte. In this study, we developed a platform involving generative model, high-throughput screening process and a machine learning surrogate model for identifying superionic Na-SSEs among Na-containing materials. Through the screening process, materials which showed potentially superior performance are selected, and their ionic conductivity were predicted. The surrogated model was constructed by ensembling two models with the best performance. 100 predictions were made for each model. In all 100 times, materials predicted to be superionic were inter-aggregated, and no material was recommended. Detail structural Descriptor will be considered. After this consideration, we believe this platform will accelerate the search for Na-SSEs with high ionic conductivity at a minimum cost.
기계학습을 이용한 나트륨 이온 배터리 양극소재 스크리닝
김민선(Minseon Kim),민경민(Kyoungmin Min) 대한기계학회 2022 대한기계학회 춘추학술대회 Vol.2022 No.11
Sodium-ion batteries (SIBs) as a highly promising candidate to replace Li-ion batteries have price competitiveness from abundant resources and a similar intercalation mechanism. In addition, they are eco-friendly because Sodium-ion can be obtained from seawater. To commercialize SIBs, it is essential to find new cathode materials with high energy density and cycling retention. In particular, layered transition metal oxides (Na<SUB>x</SUB>TMO₂ (0.5 ≤ x ≤ 1; TM = transition metal) having high capacity and appropriate voltage are powerful cathode candidates. However, the O3 phase changes to the P3 phase, causing irreversible structural changes and low cycling stability during sodium (de)intercalation. The possibility of phase transformation can be estimated by the energy difference of the O3-P3 phase. This research deals with various combinations of layered transition metal oxides using machine learning. By developing a machine learning platform, new cathodes can solve the structural degradation issue.
능동학습을 통한 우수한 기계적 특성을 가지는 제올라이트 구조의 발견
김남중(Namjung Kim),민경민(Kyoungmin Min) 대한기계학회 2021 대한기계학회 춘추학술대회 Vol.2021 No.11
In this work, a Bayesian active learning platform is developed for the accelerated discovery of mechanically superior zeolites structures from more than half a million hypothetical candidates. An initial database containing the mechanical properties of experimentally synthesizable zeolite structures was constructed to train the machine learning regression model. Then, a Bayesian optimization scheme is utilized to identify zeolites with potentially superior mechanical properties. The iteratively updated database consists of 876 labeled zeolite structures, and the uncertainty of the predictive model in terms of the standard deviation is reduced by 40% and 58% for the bulk and shear moduli, respectively. A rigorous study of the model convergence shows that no further improvement occurs after the 10th iteration in which labeled data is gradually added. The proposed platform is able to discover 23 new zeolite structures that have unprecedented shear moduli, including the superior shear modulus (127.81 GPa) which is 250% higher than those in the initial dataset. The proposed platform enhances the predictive accuracy of the mechanical properties of zeolites, and the proposed framework based on Bayesian active learning accelerates the material discovery process while maximizing computational efficiency.
기계학습을 이용한 나트륨 이온 배터리 양극소재 스크리닝
김민선(Minseon Kim),민경민(Kyoungmin Min) 대한기계학회 2022 대한기계학회 춘추학술대회 Vol.2022 No.11
Sodium-ion batteries (SIBs) as a highly promising candidate to replace Li-ion batteries have price competitiveness from abundant resources and a similar intercalation mechanism. In addition, they are eco-friendly because Sodium-ion can be obtained from seawater. To commercialize SIBs, it is essential to find new cathode materials with high energy density and cycling retention. In particular, layered transition metal oxides (Na<SUB>x</SUB>TMO₂ (0.5 ≤ x ≤ 1; TM = transition metal) having high capacity and appropriate voltage are powerful cathode candidates. However, the O3 phase changes to the P3 phase, causing irreversible structural changes and low cycling stability during sodium (de)intercalation. The possibility of phase transformation can be estimated by the energy difference of the O3-P3 phase. This research deals with various combinations of layered transition metal oxides using machine learning. By developing a machine learning platform, new cathodes can solve the structural degradation issue.