FMRG: Artificial Intelligence Driven Cybermanufacturing of Quantum Material Architectures

FMRG：人工智能驱动的量子材料架构网络制造

• 批准号: 2036359
• 负责人: Radhika Nagpal
• 金额: $ 375万
• 依托单位: Harvard University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2036359&HistoricalAwards=false
• 关键词: FMRG; Artificial; Intelligence; Driven; Cybermanufacturing

Quantum material architectures consist of graphene and other two-dimensional materials, which, when stacked in precise three-dimensional architectures, exhibit unique and tunable mechanical, electrical, optical, and magnetic properties. These three-dimensional architectures have broad potential applications and are highly promising components for microchips, batteries, antennas, chemical and biological sensors, solar-cells and neural interfaces. However, currently, due to the lack of fundamental understanding of the physical and chemical processes, it has been difficult to control or scale the manufacturing of these three-dimensional structures. This Future Manufacturing (FM) grant is to develop a transformative Future Manufacturing platform for quantum material architectures using a cybermanufacturing approach, which combines artificial intelligence, robotics, multiscale modeling, and predictive simulation for the automated and parallel assembly of multiple two-dimensional materials into complex three-dimensional structures. This platform enables future production of high-quality, custom quantum material architectures for broad and critical applications, supporting continued U.S. leadership in technology development. The research in cybermanufacturing is integrated with innovative educational programs for cross-disciplinary training of scientists and engineers, especially, women and underrepresented minorities, in advanced manufacturing, artificial intelligence and quantum structures, as well as engaging the public in future manufacturing concepts. This grant research focuses on a fundamentally new method for scalable manufacturing of 3D quantum material architectures or van der Waals heterostructures (vdWHs) using microfluidic assembly. vdWHs are composed of unlimited combinations of atomically thin layers and exhibit interesting emerging functionalities. The key process innovation is precision microfluidic folding of 2D materials, which has been demonstrated at a small-scale. This method has promising potential to scale up to wafer scale, with no fundamental limit on scaling. A second key innovation is embedding artificial intelligence (AI) across all aspects of the manufacturing process flow, from low-level precision control, to automated characterization, to high-level structure predictions. Predictive simulation and visualization tools combined with in situ spectroscopy allow real-time analysis of atomic-scale physical and chemical processes and their control. Moreover, parallel self-assembly in microfluidic environments is investigated as a pathway toward truly scalable manufacturing. The expected outcome of the award is to produce superlattices consisting of tens of atomic layers with precisely engineered stacking order and alignment, leading to fundamentally new custom quantum material architectures with electronic and photonic properties impossible to obtain from conventional material architectures. This research advances fundamental knowledge in material physics, nanoscale electronics and photonic science leading the way to manufacturing of future devices, such as twistronics. A key outcome is an AI-driven, robotics-controlled cybermanufacturing microfluidic platform that is capable of manufacturing complex structures for emerging quantum and other device applications.This Future Manufacturing research grant is supported by the following Divisions in the Engineering Directorate: Civil, Mechanical and Manufacturing Innovation; Electrical, Communications and Cyber Systems; and Engineering Education and Centers; and the following Divisions in the Mathematical and Physical Sciences: Materials Research; Chemistry; and Mathematical Sciences.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.

量子材料结构由石墨烯和其他二维材料组成，当它们以精确的三维结构堆叠时，表现出独特且可调节的机械、电学、光学和磁性能。这些三维架构具有广泛的潜在应用，是微芯片、电池、天线、化学和生物传感器、太阳能电池和神经接口的非常有前途的组件。然而，目前，由于缺乏对物理和化学过程的基本了解，很难控制或规模化制造这些三维结构。这项未来制造 (FM) 拨款旨在使用网络制造方法为量子材料架构开发一个变革性的未来制造平台，该平台结合了人工智能、机器人、多尺度建模和预测模拟，用于将多种二维材料自动并行组装成复杂的三维结构。该平台使未来能够生产适用于广泛和关键应用的高质量、定制量子材料架构，支持美国在技术开发方面继续保持领先地位。网络制造研究与创新教育计划相结合，为科学家和工程师（特别是女性和少数族裔）提供先进制造、人工智能和量子结构方面的跨学科培训，并让公众了解未来的制造概念。这项资助研究的重点是使用微流体组件可扩展制造 3D 量子材料架构或范德华异质结构 (vdWH) 的全新方法。 vdWH 由原子薄层的无限组合组成，并表现出有趣的新兴功能。 关键的工艺创新是二维材料的精密微流体折叠，该技术已在小规模上得到验证。这种方法具有扩大到晶圆尺寸的巨大潜力，并且对缩放没有根本限制。第二个关键创新是将人工智能 (AI) 嵌入到制造工艺流程的各个方面，从低级精度控制到自动表征，再到高级结构预测。预测模拟和可视化工具与原位光谱相结合，可以实时分析原子级物理和化学过程及其控制。 此外，微流体环境中的并行自组装被研究为实现真正可扩展制造的途径。该奖项的预期成果是生产由数十个原子层组成的超晶格，这些原子层具有精确设计的堆叠顺序和排列，从而产生全新的定制量子材料架构，其电子和光子特性是传统材料架构无法获得的。这项研究推进了材料物理、纳米电子学和光子科学的基础知识，引领了未来设备（例如双电子学）的制造。一个关键成果是人工智能驱动、机器人控制的网络制造微流体平台，能够为新兴量子和其他设备应用制造复杂的结构。这项未来制造研究拨款得到了工程局以下部门的支持：土木、机械和制造创新；电气、通信和网络系统；和工程教育和中心；以及以下数学和物理科学部门：材料研究；化学;该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Thickness dependence of dielectric constant of alumina films based on first-principles calculations

基于第一性原理计算的氧化铝薄膜介电常数的厚度依赖性

• DOI: 10.1063/5.0106721
• 发表时间: 2022-08
• 期刊: Applied Physics Letters
• 影响因子: 4
• 作者: Fukushima, Shogo;Kalia, Rajiv K.;Nakano, Aiichiro;Shimojo, Fuyuki;Vashishta, Priya
• 通讯作者: Vashishta, Priya

Recent Advances in Artificial Intelligence for Wireless Internet of Things and Cyber–Physical Systems: A Comprehensive Survey

无线物联网和网络物理系统人工智能的最新进展：综合调查

• DOI: 10.1109/jiot.2022.3170449
• 发表时间: 2022-08-01
• 期刊: IEEE Internet of Things Journal
• 影响因子: 10.6
• 作者: Babajide A. Salau;A. Rawal;D. Rawat
• 通讯作者: D. Rawat

Tailoring the Angular Mismatch in MoS 2 Homobilayers through Deformation Fields

通过变形场定制 MoS 2 Homobilayers 中的角度失配

• DOI: 10.1002/smll.202300098
• 发表时间: 2023-04
• 期刊: Small
• 影响因子: 13.3
• 作者: Burns, Kory;Tan, Anne Marie;Hachtel, Jordan A.;Aditya, Anikeya;Baradwaj, Nitish;Mishra, Ankit;Linker, Thomas;Nakano, Aiichiro;Kalia, Rajiv;Lang, Eric J.;et al
• 通讯作者: et al

EZFF: Python library for multi-objective parameterization and uncertainty quantification of interatomic forcefields for molecular dynamics

EZFF：用于分子动力学原子间力场的多目标参数化和不确定性量化的 Python 库

• DOI: 10.1016/j.softx.2021.100663
• 发表时间: 2021-01
• 期刊: SoftwareX
• 影响因子: 3.4
• 作者: Krishnamoorthy, Aravind;Mishra, Ankit;Kamal, Deepak;Hong, Sungwook;Nomura, Ken;Tiwari, Subodh;Nakano, Aiichiro;Kalia, Rajiv;Ramprasad, Rampi;Vashishta, Priya
• 通讯作者: Vashishta, Priya

Hidden Markov Model Enabled Prediction and Visualization of Cyber Agility in IoT era

隐马尔可夫模型实现物联网时代网络敏捷性的预测和可视化

• DOI: 10.1109/jiot.2021.3056118
• 发表时间: 2021-02
• 期刊: IEEE Internet of Things Journal
• 影响因子: 10.6
• 作者: Muhati, Eric;Rawat, Danda B.
• 通讯作者: Rawat, Danda B.