Pub Date : 2024-08-06DOI: 10.1007/s40192-024-00359-1
Nikhil Prabhu, Martin Diehl
Crystal plasticity-based digital twins are an alternative to expensive and time-consuming experiments for the investigation of micro-mechanical material behavior. However, before using simulations as an alternative for experiments, the capabilities and limitations of the modeling approach need to be known. This is best done by juxtaposing the predictions of digital twins against experimental data. The present work assesses the capabilities of full-field crystal plasticity simulations in an additively manufactured (AM) nickel-based superalloy that was characterized in situ by high-energy X-ray diffraction microscopy and electron backscatter diffraction as part of challenge 4 of air force research laboratory’s AM modeling challenge series. To ensure that the grains of interest are initialized with the measured eigenstrains, a novel scheme is proposed and its performance is evaluated. The overall agreement between simulation and experiment is assessed and compared to previous studies using the same dataset and aspects for which a systematic disagreement is seen are discussed.
基于晶体塑性的数字孪晶是研究微观机械材料行为的昂贵而耗时的实验的替代方案。然而,在使用模拟替代实验之前,需要了解建模方法的能力和局限性。最好的办法是将数字孪生预测与实验数据进行对比。本研究评估了全场晶体塑性模拟在加法制造(AM)镍基超合金中的能力,该超合金是通过高能 X 射线衍射显微镜和电子反向散射衍射进行现场表征的,是空军研究实验室 AM 建模挑战系列赛挑战 4 的一部分。为确保相关晶粒根据测量的特征应变进行初始化,提出了一种新方案并对其性能进行了评估。评估了模拟与实验之间的整体一致性,并与之前使用相同数据集进行的研究进行了比较,讨论了存在系统性分歧的方面。
{"title":"Comparison of Full-Field Crystal Plasticity Simulations to Synchrotron Experiments: Detailed Investigation of Mispredictions","authors":"Nikhil Prabhu, Martin Diehl","doi":"10.1007/s40192-024-00359-1","DOIUrl":"https://doi.org/10.1007/s40192-024-00359-1","url":null,"abstract":"<p>Crystal plasticity-based digital twins are an alternative to expensive and time-consuming experiments for the investigation of micro-mechanical material behavior. However, before using simulations as an alternative for experiments, the capabilities and limitations of the modeling approach need to be known. This is best done by juxtaposing the predictions of digital twins against experimental data. The present work assesses the capabilities of full-field crystal plasticity simulations in an additively manufactured (AM) nickel-based superalloy that was characterized in situ by high-energy X-ray diffraction microscopy and electron backscatter diffraction as part of challenge 4 of air force research laboratory’s AM modeling challenge series. To ensure that the grains of interest are initialized with the measured eigenstrains, a novel scheme is proposed and its performance is evaluated. The overall agreement between simulation and experiment is assessed and compared to previous studies using the same dataset and aspects for which a systematic disagreement is seen are discussed.</p>","PeriodicalId":13604,"journal":{"name":"Integrating Materials and Manufacturing Innovation","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141935268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-24DOI: 10.1007/s40192-024-00370-6
Gregory Sparks, Simon A. Mason, Michael G. Chapman, Jun-Sang Park, Hemant Sharma, Peter Kenesei, Stephen R. Niezgoda, Michael J. Mills, Michael D. Uchic, Paul A. Shade, Mark Obstalecki
High-energy diffraction microscopy (HEDM) combined with in situ mechanical testing is a powerful nondestructive technique for tracking the evolving microstructure within polycrystalline materials during deformation. This technique relies on a sophisticated analysis of X-ray diffraction patterns to produce a three-dimensional reconstruction of grains and other microstructural features within the interrogated volume. However, it is known that HEDM can fail to identify certain microstructural features, particularly smaller grains or twinned regions. Characterization of the identical sample volume using high-resolution surface-specific techniques, particularly electron backscatter diffraction (EBSD), can not only provide additional microstructure information about the interrogated volume but also highlight opportunities for improvement of the HEDM reconstruction algorithms. In this study, a sample fabricated from undeformed “low solvus, high refractory” nickel-based superalloy was scanned using HEDM. The volume interrogated by HEDM was then carefully characterized using a combination of surface-specific techniques, including epi-illumination optical microscopy, zero-tilt secondary and backscattered electron imaging, scanning white light interferometry, and high-precision EBSD. Custom data fusion protocols were developed to integrate and align the microstructure maps captured by these surface-specific techniques and HEDM. The raw and processed data from HEDM and serial sectioning have been made available via the Materials Data Facility (MDF) at https://doi.org/10.18126/4y0p-v604 for further investigation.
{"title":"3D Reconstruction of a High-Energy Diffraction Microscopy Sample Using Multi-modal Serial Sectioning with High-Precision EBSD and Surface Profilometry","authors":"Gregory Sparks, Simon A. Mason, Michael G. Chapman, Jun-Sang Park, Hemant Sharma, Peter Kenesei, Stephen R. Niezgoda, Michael J. Mills, Michael D. Uchic, Paul A. Shade, Mark Obstalecki","doi":"10.1007/s40192-024-00370-6","DOIUrl":"https://doi.org/10.1007/s40192-024-00370-6","url":null,"abstract":"<p>High-energy diffraction microscopy (HEDM) combined with in situ mechanical testing is a powerful nondestructive technique for tracking the evolving microstructure within polycrystalline materials during deformation. This technique relies on a sophisticated analysis of X-ray diffraction patterns to produce a three-dimensional reconstruction of grains and other microstructural features within the interrogated volume. However, it is known that HEDM can fail to identify certain microstructural features, particularly smaller grains or twinned regions. Characterization of the identical sample volume using high-resolution surface-specific techniques, particularly electron backscatter diffraction (EBSD), can not only provide additional microstructure information about the interrogated volume but also highlight opportunities for improvement of the HEDM reconstruction algorithms. In this study, a sample fabricated from undeformed “low solvus, high refractory” nickel-based superalloy was scanned using HEDM. The volume interrogated by HEDM was then carefully characterized using a combination of surface-specific techniques, including epi-illumination optical microscopy, zero-tilt secondary and backscattered electron imaging, scanning white light interferometry, and high-precision EBSD. Custom data fusion protocols were developed to integrate and align the microstructure maps captured by these surface-specific techniques and HEDM. The raw and processed data from HEDM and serial sectioning have been made available via the Materials Data Facility (MDF) at https://doi.org/10.18126/4y0p-v604 for further investigation.</p>","PeriodicalId":13604,"journal":{"name":"Integrating Materials and Manufacturing Innovation","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141775532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Advances in materials science require leveraging past findings and data from the vast published literature. While some materials data repositories are being built, they typically rely on newly created data in narrow domains because extracting detailed data and metadata from the enormous wealth of publications is immensely challenging. The advent of large language models (LLMs) presents a new opportunity to rapidly and accurately extract data and insights from the published literature and transform it into structured data formats for easy query and reuse. In this paper, we build on initial strategies for using LLMs for rapid and autonomous data extraction from materials science articles in a format curatable by materials databases. We presented the subdomain of polymer composites as our example use case and demonstrated the success and challenges of LLMs on extracting tabular data. We explored different table representations for use with LLMs, finding that a multimodal model with an image input yielded the most promising results. This model achieved an accuracy score of 0.910 for composition information extraction and an F(_1) score of 0.863 for property name information extraction. With the most conservative evaluation for the property extraction requiring exact match in all the details, we obtained an F(_1) score of 0.419. We observed that by allowing varying degrees of flexibility in the evaluation, the score can increase to 0.769. We envision that the results and analysis from this study will promote further research directions in developing information extraction strategies from materials information sources.
{"title":"How Well Do Large Language Models Understand Tables in Materials Science?","authors":"Defne Circi, Ghazal Khalighinejad, Anlan Chen, Bhuwan Dhingra, L. Catherine Brinson","doi":"10.1007/s40192-024-00362-6","DOIUrl":"https://doi.org/10.1007/s40192-024-00362-6","url":null,"abstract":"<p>Advances in materials science require leveraging past findings and data from the vast published literature. While some materials data repositories are being built, they typically rely on newly created data in narrow domains because extracting detailed data and metadata from the enormous wealth of publications is immensely challenging. The advent of large language models (LLMs) presents a new opportunity to rapidly and accurately extract data and insights from the published literature and transform it into structured data formats for easy query and reuse. In this paper, we build on initial strategies for using LLMs for rapid and autonomous data extraction from materials science articles in a format curatable by materials databases. We presented the subdomain of polymer composites as our example use case and demonstrated the success and challenges of LLMs on extracting tabular data. We explored different table representations for use with LLMs, finding that a multimodal model with an image input yielded the most promising results. This model achieved an accuracy score of 0.910 for composition information extraction and an F<span>(_1)</span> score of 0.863 for property name information extraction. With the most conservative evaluation for the property extraction requiring exact match in all the details, we obtained an F<span>(_1)</span> score of 0.419. We observed that by allowing varying degrees of flexibility in the evaluation, the score can increase to 0.769. We envision that the results and analysis from this study will promote further research directions in developing information extraction strategies from materials information sources.</p>","PeriodicalId":13604,"journal":{"name":"Integrating Materials and Manufacturing Innovation","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141745350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-19DOI: 10.1007/s40192-024-00368-0
Kristen J. Hernandez, Thomas G. Ciardi, Rachel Yamamoto, Mingjian Lu, Arafath Nihar, Jayvic Cristian Jimenez, Pawan K. Tripathi, Brian Giera, Jean-Baptiste Forien, John J. Lewandowski, Roger H. French, Laura S. Bruckman
Metal-based additive manufacturing requires active monitoring solutions for assessing part quality. Multiple sensors and data streams, however, generate large heterogeneous data sets that are impractical for manual assessment and characterization. In this work, an automated pipeline is developed that enables feature extraction from high-speed camera video and multi-modal data analysis. The framework removes the need for manual assessment through the utilization of deep learning techniques and training models in a weakly supervised paradigm. We demonstrate this pipeline’s capability over 700,000 high-speed camera frames. The pipeline successfully extracts melt pool and spatter geometries and links them to corresponding pyrometry, radiography, and processparameter information. 715 individual prints are examined to reveal melt pool areas that exceeds 0.07 mm2 and pyrometry signal over a threshold (375 pyrometry units) were more likely to have defects. These automated processes enable massive throughput of characterization techniques.
{"title":"L-PBF High-Throughput Data Pipeline Approach for Multi-modal Integration","authors":"Kristen J. Hernandez, Thomas G. Ciardi, Rachel Yamamoto, Mingjian Lu, Arafath Nihar, Jayvic Cristian Jimenez, Pawan K. Tripathi, Brian Giera, Jean-Baptiste Forien, John J. Lewandowski, Roger H. French, Laura S. Bruckman","doi":"10.1007/s40192-024-00368-0","DOIUrl":"https://doi.org/10.1007/s40192-024-00368-0","url":null,"abstract":"<p>Metal-based additive manufacturing requires active monitoring solutions for assessing part quality. Multiple sensors and data streams, however, generate large heterogeneous data sets that are impractical for manual assessment and characterization. In this work, an automated pipeline is developed that enables feature extraction from high-speed camera video and multi-modal data analysis. The framework removes the need for manual assessment through the utilization of deep learning techniques and training models in a weakly supervised paradigm. We demonstrate this pipeline’s capability over 700,000 high-speed camera frames. The pipeline successfully extracts melt pool and spatter geometries and links them to corresponding pyrometry, radiography, and processparameter information. 715 individual prints are examined to reveal melt pool areas that exceeds 0.07 mm<sup>2</sup> and pyrometry signal over a threshold (375 pyrometry units) were more likely to have defects. These automated processes enable massive throughput of characterization techniques.</p>","PeriodicalId":13604,"journal":{"name":"Integrating Materials and Manufacturing Innovation","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141745346","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-17DOI: 10.1007/s40192-024-00372-4
Lyle Levine, Brandon Lane, Chandler Becker, James Belak, Robert Carson, David Deisenroth, Edward Glaessgen, Thomas Gnaupel-Herold, Michael Gorelik, Gretchen Greene, Saadi Habib, Callie Higgins, Michael Hill, Nik Hrabe, Jason Killgore, Jai Won Kim, Gerard Lemson, Kalman Migler, Shawn Moylan, Darren Pagan, Thien Phan, Maxwell Praniewicz, David Rowenhorst, Edwin Schwalbach, Jonathan Seppala, Brian Simonds, Mark Stoudt, Jordan Weaver, Ho Yeung, Fan Zhang
The Additive Manufacturing Benchmark Test Series (AM Bench) provides rigorous measurement data for validating additive manufacturing (AM) simulations for a broad range of AM technologies and material systems. AM Bench includes extensive in situ and ex situ measurements, simulation challenges for the AM modeling community, and a corresponding conference series. In 2022, the second round of AM Bench measurements, challenge problems, and conference were completed, focusing primarily upon laser powder bed fusion (LPBF) processing of metals, and both material extrusion processing and vat photopolymerization of polymers. In all, more than 100 people from 10 National Institute of Standards and Technology (NIST) divisions and 21 additional organizations were directly involved in the AM Bench 2022 measurements, data management, and conference organization. The international AM community submitted 138 sets of blind modeling simulations for comparison with the in situ and ex situ measurements, up from 46 submissions for the first round of AM Bench in 2018. Analysis of these submissions provides valuable insight into current AM modeling capabilities. The AM Bench data are permanently archived and freely accessible online. The AM Bench conference also hosted an embedded workshop on qualification and certification of AM materials and components.
增材制造基准测试系列(AM Bench)为验证各种增材制造(AM)技术和材料系统的增材制造(AM)模拟提供了严格的测量数据。AM Bench 包括广泛的原位和非原位测量、针对 AM 建模社区的模拟挑战以及相应的系列会议。2022 年,第二轮 AM Bench 测量、挑战问题和会议已经完成,主要侧重于金属的激光粉末床熔融 (LPBF) 加工以及聚合物的材料挤压加工和大桶光聚合。来自美国国家标准与技术研究院(NIST)10 个部门和另外 21 个组织的 100 多人直接参与了 AM Bench 2022 的测量、数据管理和会议组织工作。国际AM界提交了138套盲法建模模拟,用于与原位和离场测量进行比较,比2018年第一轮AM Bench提交的46套有所增加。对这些提交数据的分析为了解当前的 AM 建模能力提供了宝贵的信息。AM Bench 数据永久存档,可免费在线访问。AM Bench 会议还举办了关于 AM 材料和组件的资格认证和认证的嵌入式研讨会。
{"title":"Outcomes and Conclusions from the 2022 AM Bench Measurements, Challenge Problems, Modeling Submissions, and Conference","authors":"Lyle Levine, Brandon Lane, Chandler Becker, James Belak, Robert Carson, David Deisenroth, Edward Glaessgen, Thomas Gnaupel-Herold, Michael Gorelik, Gretchen Greene, Saadi Habib, Callie Higgins, Michael Hill, Nik Hrabe, Jason Killgore, Jai Won Kim, Gerard Lemson, Kalman Migler, Shawn Moylan, Darren Pagan, Thien Phan, Maxwell Praniewicz, David Rowenhorst, Edwin Schwalbach, Jonathan Seppala, Brian Simonds, Mark Stoudt, Jordan Weaver, Ho Yeung, Fan Zhang","doi":"10.1007/s40192-024-00372-4","DOIUrl":"https://doi.org/10.1007/s40192-024-00372-4","url":null,"abstract":"<p>The Additive Manufacturing Benchmark Test Series (AM Bench) provides rigorous measurement data for validating additive manufacturing (AM) simulations for a broad range of AM technologies and material systems. AM Bench includes extensive in situ and ex situ measurements, simulation challenges for the AM modeling community, and a corresponding conference series. In 2022, the second round of AM Bench measurements, challenge problems, and conference were completed, focusing primarily upon laser powder bed fusion (LPBF) processing of metals, and both material extrusion processing and vat photopolymerization of polymers. In all, more than 100 people from 10 National Institute of Standards and Technology (NIST) divisions and 21 additional organizations were directly involved in the AM Bench 2022 measurements, data management, and conference organization. The international AM community submitted 138 sets of blind modeling simulations for comparison with the in situ and ex situ measurements, up from 46 submissions for the first round of AM Bench in 2018. Analysis of these submissions provides valuable insight into current AM modeling capabilities. The AM Bench data are permanently archived and freely accessible online. The AM Bench conference also hosted an embedded workshop on qualification and certification of AM materials and components.</p>","PeriodicalId":13604,"journal":{"name":"Integrating Materials and Manufacturing Innovation","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141745347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-15DOI: 10.1007/s40192-024-00369-z
Khaled Alrfou, Tian Zhao, Amir Kordijazi
{"title":"Deep Learning Methods for Microstructural Image Analysis: The State-of-the-Art and Future Perspectives","authors":"Khaled Alrfou, Tian Zhao, Amir Kordijazi","doi":"10.1007/s40192-024-00369-z","DOIUrl":"https://doi.org/10.1007/s40192-024-00369-z","url":null,"abstract":"","PeriodicalId":13604,"journal":{"name":"Integrating Materials and Manufacturing Innovation","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141647259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-15DOI: 10.1007/s40192-024-00371-5
L. E. Levine, M. E. Williams, A. Creuziger, M. Stoudt, S. A. Young, K. W. Moon, B. M. Lane
{"title":"Location-Specific Microstructure Characterization Within AM Bench 2022 Nickel Alloy 718 3D Builds","authors":"L. E. Levine, M. E. Williams, A. Creuziger, M. Stoudt, S. A. Young, K. W. Moon, B. M. Lane","doi":"10.1007/s40192-024-00371-5","DOIUrl":"https://doi.org/10.1007/s40192-024-00371-5","url":null,"abstract":"","PeriodicalId":13604,"journal":{"name":"Integrating Materials and Manufacturing Innovation","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141648228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-10DOI: 10.1007/s40192-024-00367-1
Bryce R. Jolley, Daniel M. Sparkman, Michael G. Chapman, Edwin J. Schwalbach, Michael D. Uchic
An additively manufactured titanium alloy sample has been characterized by X-ray computed tomography and optical microscopy serial sectioning to enable a correlative analysis of internal porosity. Titanium alloy ball bearings were adhered to the surface of the cylindrical sample to aid the registration of the datasets. The characterization data includes five X-ray computed tomography scans from four different instruments and optical microscopy serial sectioning images. The methods and parameters used for collecting these multiple datasets, and reconstructed data for each dataset‘s selected volume of interest are provided. Raw projection data from each computed tomography scan are also offered. Unanticipated artifacts within the serial sectioning experiment are highlighted, and the potential impact of these artifacts is discussed.
通过 X 射线计算机断层扫描和光学显微镜连续切片对添加制造的钛合金样品进行了表征,以便对内部孔隙率进行相关分析。钛合金球轴承被粘附在圆柱形样品的表面,以帮助数据集的登记。表征数据包括来自四种不同仪器的五次 X 射线计算机断层扫描和光学显微镜连续切片图像。本文提供了收集这些多个数据集的方法和参数,以及每个数据集所选感兴趣体积的重建数据。此外,还提供了每次计算机断层扫描的原始投影数据。重点介绍了序列切片实验中的意外伪影,并讨论了这些伪影的潜在影响。
{"title":"Correlative X-ray Computed Tomography and Optical Microscopy Serial Sectioning Data of Additive Manufactured Ti-6Al-4V","authors":"Bryce R. Jolley, Daniel M. Sparkman, Michael G. Chapman, Edwin J. Schwalbach, Michael D. Uchic","doi":"10.1007/s40192-024-00367-1","DOIUrl":"https://doi.org/10.1007/s40192-024-00367-1","url":null,"abstract":"<p>An additively manufactured titanium alloy sample has been characterized by X-ray computed tomography and optical microscopy serial sectioning to enable a correlative analysis of internal porosity. Titanium alloy ball bearings were adhered to the surface of the cylindrical sample to aid the registration of the datasets. The characterization data includes five X-ray computed tomography scans from four different instruments and optical microscopy serial sectioning images. The methods and parameters used for collecting these multiple datasets, and reconstructed data for each dataset‘s selected volume of interest are provided. Raw projection data from each computed tomography scan are also offered. Unanticipated artifacts within the serial sectioning experiment are highlighted, and the potential impact of these artifacts is discussed.</p>","PeriodicalId":13604,"journal":{"name":"Integrating Materials and Manufacturing Innovation","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141587790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-01DOI: 10.1007/s40192-024-00363-5
Bingyin Hu, Anqi Lin, L. Catherine Brinson
There is an urgent need for ready access to published data for advances in materials design, and natural language processing (NLP) techniques offer a promising solution for extracting relevant information from scientific publications. In this paper, we present a domain-specific approach utilizing a Transformer-based model, T5, to automate the generation of sample lists in the field of polymer nanocomposites (PNCs). Leveraging large-scale corpora, we employ advanced NLP techniques including named entity recognition and relation extraction to accurately extract sample codes, compositions, group references, and properties from PNC papers. The T5 model demonstrates competitive performance in relation extraction using a TANL framework and an EM-style input sequence. Furthermore, we explore multi-task learning and joint-entity-relation extraction to enhance efficiency and address deployment concerns. Our proposed methodology, from corpora generation to model training, showcases the potential of structured knowledge extraction from publications in PNC research and beyond.
{"title":"Tackling Structured Knowledge Extraction from Polymer Nanocomposite Literature as an NER/RE Task with seq2seq","authors":"Bingyin Hu, Anqi Lin, L. Catherine Brinson","doi":"10.1007/s40192-024-00363-5","DOIUrl":"https://doi.org/10.1007/s40192-024-00363-5","url":null,"abstract":"<p>There is an urgent need for ready access to published data for advances in materials design, and natural language processing (NLP) techniques offer a promising solution for extracting relevant information from scientific publications. In this paper, we present a domain-specific approach utilizing a Transformer-based model, T5, to automate the generation of sample lists in the field of polymer nanocomposites (PNCs). Leveraging large-scale corpora, we employ advanced NLP techniques including named entity recognition and relation extraction to accurately extract sample codes, compositions, group references, and properties from PNC papers. The T5 model demonstrates competitive performance in relation extraction using a TANL framework and an EM-style input sequence. Furthermore, we explore multi-task learning and joint-entity-relation extraction to enhance efficiency and address deployment concerns. Our proposed methodology, from corpora generation to model training, showcases the potential of structured knowledge extraction from publications in PNC research and beyond.</p>","PeriodicalId":13604,"journal":{"name":"Integrating Materials and Manufacturing Innovation","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141510126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-28DOI: 10.1007/s40192-024-00366-2
J. Elliott Fowler, Timothy J. Ruggles, Dale E. Cillessen, Kyle L. Johnson, Luis J. Jauregui, Robert L. Craig, Nathan R. Bianco, Amelia A. Henriksen, Brad L. Boyce
The need to optimize the processing conditions of additively manufactured (AM) metals and alloys has driven advances in throughput capabilities for material property measurements such as tensile strength or hardness. High-throughput (HT) characterization of AM metal microstructure has fallen significantly behind the pace of property measurements due to intrinsic bottlenecks associated with the artisan and labor-intensive preparation methods required to produce highly polished surfaces. This inequality in data throughput has led to a reliance on heuristics to connect process to structure or structure to properties for AM structural materials. In this study, we show a transformative approach to achieve laser powder bed fusion (LPBF) printing, HT preparation using dry electropolishing and HT electron backscatter diffraction (EBSD). This approach was used to construct a library of > 600 experimental EBSD sample sets spanning a diverse range of LPBF process conditions for AM Kovar. This vast library is far more expansive in parameter space than most state-of-the-art studies, yet it required only approximately 10 labor hours to acquire. Build geometries, surface preparation methods, and microscopy details, as well as the entire library of >600 EBSD data sets over the two sample design versions, have been shared with intent for the materials community to leverage the data and further advance the approach. Using this library, we investigated process–structure relationships and uncovered an unexpected, strong dependence of microstructure on location within the build, when varied, using otherwise identical laser parameters.
{"title":"High-Throughput Microstructural Characterization and Process Correlation Using Automated Electron Backscatter Diffraction","authors":"J. Elliott Fowler, Timothy J. Ruggles, Dale E. Cillessen, Kyle L. Johnson, Luis J. Jauregui, Robert L. Craig, Nathan R. Bianco, Amelia A. Henriksen, Brad L. Boyce","doi":"10.1007/s40192-024-00366-2","DOIUrl":"https://doi.org/10.1007/s40192-024-00366-2","url":null,"abstract":"<p>The need to optimize the processing conditions of additively manufactured (AM) metals and alloys has driven advances in throughput capabilities for material property measurements such as tensile strength or hardness. High-throughput (HT) characterization of AM metal microstructure has fallen significantly behind the pace of property measurements due to intrinsic bottlenecks associated with the artisan and labor-intensive preparation methods required to produce highly polished surfaces. This inequality in data throughput has led to a reliance on heuristics to connect process to structure or structure to properties for AM structural materials. In this study, we show a transformative approach to achieve laser powder bed fusion (LPBF) printing, HT preparation using dry electropolishing and HT electron backscatter diffraction (EBSD). This approach was used to construct a library of > 600 experimental EBSD sample sets spanning a diverse range of LPBF process conditions for AM Kovar. This vast library is far more expansive in parameter space than most state-of-the-art studies, yet it required only approximately 10 labor hours to acquire. Build geometries, surface preparation methods, and microscopy details, as well as the entire library of >600 EBSD data sets over the two sample design versions, have been shared with intent for the materials community to leverage the data and further advance the approach. Using this library, we investigated process–structure relationships and uncovered an unexpected, strong dependence of microstructure on location within the build, when varied, using otherwise identical laser parameters.</p>","PeriodicalId":13604,"journal":{"name":"Integrating Materials and Manufacturing Innovation","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141510127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}