{"title":"具有良好玻璃成型能力和性能的金属玻璃的逆向设计机器学习模型","authors":"K. Y. Li, M. Z. Li, W. H. Wang","doi":"10.1063/5.0179854","DOIUrl":null,"url":null,"abstract":"The design of metallic glasses (MGs) with good properties is one of the long-standing bottlenecks in materials science and engineering, which has been relying mostly on far less efficient traditional trial-and-error methods. Even the currently popular machine learning-based forward designs, which use manual input to navigate high dimensional compositional space, often become inefficient with the increasing compositional complexity in MGs. Here, we developed an inverse design machine learning model, leveraging the variational autoencoder (VAE), to directly generate the MGs with good glass-forming ability (GFA). We demonstrate that our VAE with the property prediction model is not only an expressive generative model but also able to do accurate property prediction. Our model allows us to automatically generate novel MG compositions by performing simple operations in the latent space. After randomly generating 3000MG compositions using the model, a detailed analysis of four typical metallic alloys shows that unreported MG compositions with better glass-forming ability can be predicted. Moreover, our model facilitates the use of powerful optimization algorithms to efficiently guide the search for MGs with good GFA in the latent space. We believe that this is an efficient way to discover MGs with excellent properties.","PeriodicalId":15088,"journal":{"name":"Journal of Applied Physics","volume":"17 1","pages":""},"PeriodicalIF":2.7000,"publicationDate":"2024-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Inverse design machine learning model for metallic glasses with good glass-forming ability and properties\",\"authors\":\"K. Y. Li, M. Z. Li, W. H. Wang\",\"doi\":\"10.1063/5.0179854\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The design of metallic glasses (MGs) with good properties is one of the long-standing bottlenecks in materials science and engineering, which has been relying mostly on far less efficient traditional trial-and-error methods. Even the currently popular machine learning-based forward designs, which use manual input to navigate high dimensional compositional space, often become inefficient with the increasing compositional complexity in MGs. Here, we developed an inverse design machine learning model, leveraging the variational autoencoder (VAE), to directly generate the MGs with good glass-forming ability (GFA). We demonstrate that our VAE with the property prediction model is not only an expressive generative model but also able to do accurate property prediction. Our model allows us to automatically generate novel MG compositions by performing simple operations in the latent space. After randomly generating 3000MG compositions using the model, a detailed analysis of four typical metallic alloys shows that unreported MG compositions with better glass-forming ability can be predicted. Moreover, our model facilitates the use of powerful optimization algorithms to efficiently guide the search for MGs with good GFA in the latent space. We believe that this is an efficient way to discover MGs with excellent properties.\",\"PeriodicalId\":15088,\"journal\":{\"name\":\"Journal of Applied Physics\",\"volume\":\"17 1\",\"pages\":\"\"},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2024-01-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Applied Physics\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1063/5.0179854\",\"RegionNum\":3,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"PHYSICS, APPLIED\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Applied Physics","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1063/5.0179854","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PHYSICS, APPLIED","Score":null,"Total":0}
Inverse design machine learning model for metallic glasses with good glass-forming ability and properties
The design of metallic glasses (MGs) with good properties is one of the long-standing bottlenecks in materials science and engineering, which has been relying mostly on far less efficient traditional trial-and-error methods. Even the currently popular machine learning-based forward designs, which use manual input to navigate high dimensional compositional space, often become inefficient with the increasing compositional complexity in MGs. Here, we developed an inverse design machine learning model, leveraging the variational autoencoder (VAE), to directly generate the MGs with good glass-forming ability (GFA). We demonstrate that our VAE with the property prediction model is not only an expressive generative model but also able to do accurate property prediction. Our model allows us to automatically generate novel MG compositions by performing simple operations in the latent space. After randomly generating 3000MG compositions using the model, a detailed analysis of four typical metallic alloys shows that unreported MG compositions with better glass-forming ability can be predicted. Moreover, our model facilitates the use of powerful optimization algorithms to efficiently guide the search for MGs with good GFA in the latent space. We believe that this is an efficient way to discover MGs with excellent properties.
期刊介绍:
The Journal of Applied Physics (JAP) is an influential international journal publishing significant new experimental and theoretical results of applied physics research.
Topics covered in JAP are diverse and reflect the most current applied physics research, including:
Dielectrics, ferroelectrics, and multiferroics-
Electrical discharges, plasmas, and plasma-surface interactions-
Emerging, interdisciplinary, and other fields of applied physics-
Magnetism, spintronics, and superconductivity-
Organic-Inorganic systems, including organic electronics-
Photonics, plasmonics, photovoltaics, lasers, optical materials, and phenomena-
Physics of devices and sensors-
Physics of materials, including electrical, thermal, mechanical and other properties-
Physics of matter under extreme conditions-
Physics of nanoscale and low-dimensional systems, including atomic and quantum phenomena-
Physics of semiconductors-
Soft matter, fluids, and biophysics-
Thin films, interfaces, and surfaces