Fast-Track Consensus Study on Foundational Research Gaps and Future Directions for Digital Twins

关于数字孪生基础研究差距和未来方向的快速共识研究

• 批准号: 2233022
• 负责人: Michelle Schwalbe
• 金额: $ 9.5万
• 依托单位: National Academy of Sciences
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-01 至 2025-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2233022&HistoricalAwards=false
• 关键词: Fast; Track; Consensus; Study; Foundational

The National Academies of Sciences, Engineering, and Medicine is undertaking a study to identify needs and opportunities to advance the mathematical, statistical, and computational foundations of digital twins in applications across science, medicine, engineering, and society. A digital twin is a computer model that changes over time to represent the structure or behavior of a unique physical entity, such as a manufacturing process, piece of equipment, or even a person. Based on data inputs, the digital twin can be used to gain insight into present and future states of the physical twin. The exploration and use of digital twins is growing across domains, but many state-of-the-art digital twins are largely the result of custom implementations that require considerable deployment resources and a high level of expertise. Due to the individualized nature of many digital twin implementations, the relative maturity of digital twins varies significantly across problem spaces. Moving from one-off digital twins to digital twin implementations at scale will involve addressing foundational mathematical, statistical, and computational gaps. This study aims to highlight these critical research gaps and provide options to address them with the goal of advancing the use of digital twins across disciplinary communities.The proposed study by the National Academies of Sciences, Engineering, and Medicine, will highlight needs and opportunities to advance the mathematical, statistical, and computational foundations of digital twins in applications across science, medicine, engineering, and society. A digital twin assimilates observational data and uses this information to continually update its internal models so that they reflect the evolving physical system. The digital twin is therefore continuously improving and provides a dynamic digital history of the physical entity. These core functionalities can be augmented with feedback control and artificial intelligence, combined with ensembles of similar twins, or used in tandem with other predictive tools to analyze and diagnose operational states and to optimize performance under real-world conditions. Utilization of digital twins varies across disciplines. This study will address the following: (1) diverging definitions of digital twins and domain-inspired use cases; (2) foundational mathematical, statistical, and computational gaps for the continued development of digital twins; (3) best practices for digital twin development and use; and (4) opportunities to move the community and state of practice forward. Three domain-specific workshops will be held to explore the methods, practices, use cases, and challenges for the development and use of digital twins—focus areas include biomedical domains, Earth and environmental systems, and aerospace engineering. Four reports will be released by the National Academies during the course of this 18-month study: three short summaries of the domain-specific workshops and a consensus report focused on the cross-cutting foundational research gaps and future directions for digital twins.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

美国国家科学院、工程院和医学院正在进行一项研究，以确定在科学、医学、工程和社会应用中推进数字孪生的数学、统计和计算基础的需求和机会。数字孪生是一种计算机模型，它随着时间的推移而变化，以表示一个独特的物理实体的结构或行为，比如一个制造过程、一件设备，甚至一个人。基于数据输入，数字孪生可以用来洞察物理孪生的当前和未来状态。数字孪生的探索和使用正在跨领域发展，但是许多最先进的数字孪生主要是定制实现的结果，这些实现需要大量的部署资源和高水平的专业知识。由于许多数字孪生实现的个性化性质，数字孪生的相对成熟度在不同的问题空间中差异很大。从一次性数字孪生到大规模数字孪生的实现将涉及解决基础数学、统计和计算方面的差距。本研究旨在突出这些关键的研究差距，并提供解决这些差距的选择，目标是促进跨学科社区使用数字双胞胎。这项由美国国家科学院、工程院和医学院提出的研究将强调在科学、医学、工程和社会的应用中推进数字双胞胎的数学、统计和计算基础的需求和机会。数字孪生体吸收观测数据，并利用这些信息不断更新其内部模型，以反映不断发展的物理系统。因此，数字孪生正在不断改进，并提供物理实体的动态数字历史。这些核心功能可以通过反馈控制和人工智能来增强，也可以与类似的双胞胎组合在一起，或者与其他预测工具一起使用，以分析和诊断操作状态，并在现实条件下优化性能。不同学科对数字孪生的利用各不相同。本研究将解决以下问题：(1)数字孪生和领域启发用例的不同定义；(2)数字孪生持续发展的基础数学、统计和计算差距；(3)数字孪生体开发和使用的最佳实践；(4)推动社区和实践状态向前发展的机会。将举办三个特定领域的研讨会，探讨开发和使用数字孪生的方法、实践、用例和挑战，重点领域包括生物医学领域、地球和环境系统以及航空航天工程。在为期18个月的研究过程中，美国国家科学院将发布四份报告：三份针对特定领域研讨会的简短总结，以及一份针对数字孪生的跨领域基础研究差距和未来方向的共识报告。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。