RII Track 2 FEC: Enabling Factory to Factory (F2F) Networking for Future Manufacturing

RII Track 2 FEC：为未来制造实现工厂到工厂 (F2F) 网络

• 批准号: 2119654
• 负责人: Ramy Harik
• 金额: $ 383.23万
• 依托单位: University of South Carolina at Columbia
• 依托单位国家: 美国
• 项目类别: Cooperative Agreement
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2025-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2119654&HistoricalAwards=false
• 关键词: RII; Track; FEC; Enabling; Factory

Cyber infrastructure and artificial intelligence (AI) are core components of smart manufacturing in South Carolina (SC), West Virginia (WV), and the United States. To drive radical transformation of industry, factories must securely expand beyond their physical boundaries. These Future Factories (FF) consume and create interdisciplinary knowledge along with the ability to forge innovative technological transformations. This project introduces a novel future cyber-manufacturing paradigm – the Factory-to-Factory (F2F) network framework. Geared towards automation, F2F networks require interoperability of stakeholders and efficient understanding systems for data, information, and knowledge. This collaboration between academia – led by the University of South Carolina and West Virginia University - and industry will produce advanced smart manufacturing technologies and an educated upskilled workforce in SC and WV. Furthermore, it will create a blueprint model for future manufacturing technologies that can be integrated with a F2F network to increase small-scale and industrial manufacturing capabilities across the US. To expand our workforce infrastructure, we will establish a lifelong learning pipeline for smart manufacturing ranging from K-12 education, higher education, to professional development support for scholars and industrial professionals. Particularly, we will create online learning resources and STEM-oriented smart manufacturing summer programs for K-12 students and provide internships for college and graduate students through our industrial partners. This project will adapt, enhance, and integrate informational technologies (IT) and operational technologies (OT) such as real-time secured sensing, high performance computing, wireless communications, and AI, to support process optimization among distributed smart manufacturing systems for F2F. Convergence and true progress can only be achieved by fusing expert knowledge of manufacturing processes with newly emerged hardware and software technologies. The project focuses on manufacturing knowledge stemming from: (1) autonomous feature extraction and recognition from product ‘manufacturing DNAs’ as a novel manufacturing knowledge representation among distributed systems, (2) architecture of interactive cyber spaces that combines cross-platform simulation results within product lifecycles, (3) data-driven control theories during process monitoring leading to rapid autonomous decision-making in replacement of manual input/output modules, and (4) robust business models and operations research (information service-oriented) concerning autonomous Key Performance Indicator (KPI) decomposition among distributed sub-systems and rapid feedback control loops. This will build a foundation for real-time production information sharing and control platforms and facilitate manufacturing knowledge generation and utilization among networked systems to address manufacturing management challenges. Furthermore, it enables human interventions and interoperations in the development and decision-making process of these highly collaborative networked smart manufacturing systems. This project will showcase several novel cyber manufacturing implementations and establish a roadmap towards a universal digital F2F standard.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.

网络基础设施和人工智能（AI）是南卡罗来纳州（SC）、西弗吉尼亚州（WV）和美国智能制造的核心组成部分。为了推动工业的彻底转型，工厂必须安全地扩展到物理边界之外。这些未来工厂（FF）消耗和创造跨学科的知识，同时有能力进行创新的技术变革。本项目介绍了一种新型的未来网络制造范式——工厂到工厂（F2F）网络框架。面向自动化，F2F网络需要利益相关者的互操作性和有效的数据、信息和知识理解系统。由南卡罗来纳大学和西弗吉尼亚大学领导的学术界与工业界的合作将在南卡罗来纳州和西弗吉尼亚州生产先进的智能制造技术和受过良好教育的高技能劳动力。此外，它将为未来的制造技术创建一个蓝图模型，可以与F2F网络集成，以提高美国的小规模和工业制造能力。为了扩大劳动力基础设施，我们将建立智能制造的终身学习管道，从K-12教育到高等教育，再到为学者和工业专业人士提供专业发展支持。特别是，我们将为K-12学生创建在线学习资源和面向stem的智能制造暑期项目，并通过我们的工业合作伙伴为大学生和研究生提供实习机会。该项目将适应、增强和集成信息技术（IT）和操作技术（OT），如实时安全传感、高性能计算、无线通信和人工智能，以支持F2F分布式智能制造系统之间的流程优化。只有将制造工艺的专业知识与新出现的硬件和软件技术融合在一起，才能实现融合和真正的进步。该项目侧重于以下方面的制造知识：(1)从产品“制造dna”中自主提取和识别特征，作为分布式系统中新颖的制造知识表示；(2)结合产品生命周期内跨平台仿真结果的交互式网络空间体系结构；(3)过程监控期间的数据驱动控制理论，导致替代人工输入/输出模块的快速自主决策；(4)基于分布式子系统之间自主关键绩效指标（KPI）分解和快速反馈控制回路的稳健业务模型和运筹学（信息服务）。这将为实时生产信息共享和控制平台奠定基础，并促进网络化系统之间的制造知识生成和利用，以应对制造管理挑战。此外，它使这些高度协作的网络化智能制造系统的开发和决策过程中的人为干预和互操作成为可能。该项目将展示几种新颖的网络制造实施方案，并为通用数字F2F标准制定路线图。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。

项目成果

Knowledge Graph Empowered Machine Learning Pipelines for Improved Efficiency, Reusability, and Explainability

知识图赋能机器学习管道，提高效率、可重用性和可解释性

• DOI: 10.1109/mic.2022.3228087
• 发表时间: 2023
• 期刊: IEEE Internet Computing
• 影响因子: 3.2
• 作者: Venkataramanan, Revathy;Tripathy, Aalap;Foltin, Martin;Yip, Hong Yung;Justine, Annmary;Sheth, Amit
• 通讯作者: Sheth, Amit

Automated manufacturability analysis in smart manufacturing systems: a signature mapping method for product-centered digital twins

• DOI: 10.1007/s10845-022-01991-4
• 发表时间: 2022-08
• 期刊: Journal of Intelligent Manufacturing
• 影响因子: 8.3
• 作者: K. Xia;Thorsten Wuest;R. Harik

CausalKG: Causal Knowledge Graph Explainability Using Interventional and Counterfactual Reasoning

• DOI: 10.1109/mic.2021.3133551
• 发表时间: 2022-01
• 期刊: IEEE Internet Computing
• 影响因子: 3.2
• 作者: Utkarshani Jaimini;A. Sheth

A Semantic Web Approach to Fault Tolerant Autonomous Manufacturing

• DOI: 10.1109/mis.2023.3235677
• 发表时间: 2023-01
• 期刊: IEEE Intelligent Systems
• 影响因子: 6.4
• 作者: Fadi El Kalach;Ruwan Wickramarachchi;R. Harik;A. Sheth

Knowledge-Based Entity Prediction for Improved Machine Perception in Autonomous Systems

• DOI: 10.1109/mis.2022.3181015
• 发表时间: 2022-03
• 期刊: IEEE Intelligent Systems
• 影响因子: 6.4
• 作者: Ruwan Wickramarachchi;C. Henson;A. Sheth