AI Institute: Planning: AI-Enabled Secure and Responsive Smart Manufacturing

人工智能研究院：规划：人工智能赋能的安全响应式智能制造

• 批准号: 2020246
• 负责人: Vijay Gupta
• 金额: $ 50万
• 依托单位: University of Notre Dame
• 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 2022-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2020246&HistoricalAwards=false
• 关键词: AI; Institute; Planning; Enabled; Secure

Advanced manufacturing is on the cusp of a Fourth Industrial revolution, captured by the term Industry 4.0 or Smart Manufacturing. However, challenges abound in realizing the smart manufacturing paradigm. Rapidly reconfigurable production systems envisaged in smart manufacturing are inherently tied to acquisition of large amounts of continuous streaming data from machines and automated robots on the shop floor, as well as from entities dispersed in the supply-logistics chain, using heterogeneous sensors. The data has to be transmitted over wireless channels with tight latency and security guarantees, and coupled with real-time analysis to allow precise trouble-shooting, coordination, and monitoring. The inescapable conclusion is that to enable smart manufacturing, a tight integration – and, in fact, cross-layer optimization – of manufacturing technologies, robotics and control, networking protocols such as 5G, and machine learning paradigms such as inference on the edge is needed. Achieving this vision is the goal of the institute envisaged in this planning grant. Realizing an effective institute will require experts in advanced manufacturing, AI, sensing, computation, and sensing, as well as collaboration with industry and federal research labs. The major activities in this planning grant aim at developing such a team through a range of activities. The intellectual bulwark of the institute is the enabling of smart manufacturing through a tight integration and cross-layer optimization of manufacturing technologies, networking protocols such as 5G, robotics and control, and machine learning paradigms such as inference on the edge. This integration will also generate and revitalize new research areas that encompass fundamental materials science to large-scale supply networking and cybersecurity to AI-enabled collaborative robotics and human-robot interaction and beyond. The activities also include new curriculum development both at the participating universities and community colleges, as well as plans for outreach through local governments and high schools, for developing the workforce for such a paradigm and broadening participation into AI-related technology among society.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.

先进的制造业是第四次工业革命的风口浪尖，该工业革命被“行业4.0”或“智能制造”一词所捕获。但是，在实现智能制造范式方面，挑战比比皆是。智能制造中设想的快速重新配置的生产系统固有地与从机器和商店地板上的机器机器人以及使用异构传感器在供应链链中启动的实体中获取大量连续流数据有关。数据必须通过无线通道传输，并具有严格的延迟和安全保证，并加上实时分析，以允许精确进行故障射击，协调和监视。不可避免的结论是，为了实现制造技术，机器人技术和控制的紧密整合（实际上是跨层优化），需要5G等网络协议以及机器学习范式，例如对边缘的推断。实现这一愿景是该研究所的目标的目标。实现有效的机构将需要高级制造，AI，敏感性，计算和敏感性的专家，以及与行业和联邦研究实验室的合作。该计划赠款的主要活动旨在通过一系列活动发展这样的团队。该研究所的智能堡垒是通过紧密的整合和跨层优化制造技术，网络协议（例如5G，机器人和控制）以及机器学习范式（例如Edge推论）来实现智能制造。这种整合还将生成并振兴新的研究领域，从而增强基本材料科学，以对支持AI支持AI的协作机器人技术和人类机器人交互及以后的大规模供应网络和网络安全。这些活动还包括参与大学和社区大学的新课程开发，以及通过地方政府和高中的外展计划，以开发这种范式的劳动力，并在社会上扩大了与AI相关技术的参与。该奖项反映了NSF的法定任务，并通过使用基金会的智力效果和广泛的评估来进行评估，以此来评估。

项目成果

Effect of contaminations on the acoustic emissions during wire and arc additive manufacturing of 316L stainless steel

• DOI: 10.1016/j.addma.2021.102585
• 发表时间: 2021-12
• 期刊: Additive Manufacturing
• 影响因子: 11
• 作者: A. Ramalho;T. Santos;Ben Bevans;Z. Smoqi;Prahalada K. Rao;J. P. Oliveira

Closed-loop Control of Meltpool Temperature in Directed Energy Deposition

• DOI: 10.1016/j.matdes.2022.110508
• 发表时间: 2022-03
• 期刊: Materials & Design
• 作者: Z. Smoqi;Ben Bevans;A. Gaikwad;J. Craig;Alan Abul-Haj;B. Roeder;B. Macy;J. Shield;Prahalada K. Rao

Adversarial attacks in consensus-based multi-agent reinforcement learning

• DOI: 10.23919/acc50511.2021.9483080
• 发表时间: 2021-03
• 期刊: 2021 American Control Conference (ACC)
• 作者: Martin Figura;K. Kosaraju;V. Gupta

In-process monitoring and prediction of droplet quality in droplet-on-demand liquid metal jetting additive manufacturing using machine learning

• DOI: 10.1007/s10845-022-01977-2
• 发表时间: 2022-06
• 期刊: Journal of Intelligent Manufacturing
• 影响因子: 8.3
• 作者: A. Gaikwad;Tammy Chang;B. Giera;N. Watkins;S. Mukherjee;A. Pascall;D. Stobbe;Prahalada K. Rao

Prediction of recoater crash in laser powder bed fusion additive manufacturing using graph theory thermomechanical modeling

• DOI: 10.1007/s40964-022-00331-5
• 发表时间: 2022-08-05
• 期刊: PROGRESS IN ADDITIVE MANUFACTURING
• 作者: Kobir, Md Humaun;Yavari, Reza;Rao, Prahalada
• 通讯作者: Rao, Prahalada