I/UCRC: Phase I: Center for Advanced Electronics through Machine Learning (CAEML)

I/UCRC：第一阶段：机器学习先进电子学中心 (CAEML)

• 批准号: 1624811
• 负责人: Maxim Raginsky
• 金额: $ 60万
• 依托单位: University of Illinois at Urbana-Champaign
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-08-01 至 2023-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1624811&HistoricalAwards=false
• 关键词: UCRC; Phase; Center; Advanced; Electronics

The semiconductor industry is perennially one of America's top exporters. Worldwide semiconductor sales for 2014 reached $335.8 billion, and the number of U.S. jobs in this sector was estimated to be around 250,000 in 2013. More broadly, the U.S. tech industry, which depends on semiconductor innovation to spur new products and applications, is itself estimated to represent no less than 5.7% of the entire U.S. private sector workforce (at nearly 6.5 million jobs), and with a tech industry payroll of $654 billion in 2014, it accounted for over 11% of all U.S. private sector payroll. Yet despite its success, the industry must continue to innovate if the U.S. is to retain global leadership in this highly competitive area. The complexity of modern microelectronic products necessitates the use of computer tools to formulate and verify product designs prior to manufacturing. When a product doesn't operate as intended or suffers early failures, this can often be attributed to inadequacy of the models used during the design process. In fact, the shortcomings of existing approaches for system component modeling have become a serious impediment to continued innovation. The Center for Advanced Electronics through Machine Learning (CAEML) proposes to create machine-learning algorithms to derive models used for electronic design automation with the objective of enabling fast, accurate design of microelectronic circuits and systems. Success will make it much easier and cheaper to optimize a system design, allowing the industry to produce lower-power and lower-cost electronic systems without sacrificing functionality. The eventual result will be significant growth in capabilities that will drive innovation throughout the electronics industry, leading to new devices and applications, continued entrepreneurial leadership, and economic growth. While achieving those goals, CAEML will also focus on diversifying the undergraduate engineering student body and improving the undergraduate experience. Students from groups traditionally underrepresented in engineering will be targeted for recruitment as undergraduate research assistants. Member companies will provide internships and mentors for participating students, and the diverse graduate and undergraduate student researchers in CAEML will receive hands-on multidisciplinary education. CAEML will also participate in all three site universities' existing avenues for student and faculty engagement with local youth. In particular, university-based summer camps are a tried and tested method of making high-school students familiar with and comfortable on our campuses. The Girls' Adventures in Mathematics, Engineering, and Science (GAMES) summer camp program at the University of Illinois at Urbana-Champaign ("Illinois") brings high-school girls to campus for a week of hands-on engineering activities and camaraderie. The engineering content for many of the GAMES camps, including the one on electrical engineering, is developed by engineering faculty. CAEML undergraduate and graduate students can serve as counselors or instructors for camps; the CAEML team proposes to develop new activities and workshops for high-school campers on all three sites' campuses. In addition, the Beginning Teacher STEM Conference at Illinois brings 150 teachers who have just completed their first year in the classroom to the Urbana-Champaign campus for 2 days to deepen their knowledge of STEM fields and try out activities for use in their classrooms; several of the sessions are taught by College of Engineering faculty including those affiliated with CAEML. The Center for Advanced Electronics through Machine Learning (CAEML) will create machine-learning algorithms to derive models used for electronic design automation, with the objective of enabling fast, accurate design of microelectronic circuits and systems. The electronics industry's continued ability to innovate requires the creation of optimization methodologies that result in low-power integrated systems that meet performance specifications, despite being composed of components whose characteristics exhibit variability and that operate in different physical or signal domains. Today, shortcomings in accuracy and comprehensiveness of component-level behavioral models impede the advancement of computer-aided electronic system design optimization. The model accuracy also impacts system verification. Ultimately, the proper functionality of an electronic system is verified through testing of a representative sample. However, modern electronic systems are so complex that it is unthinkable to bring one to the manufacturing stage without first verifying its operation using simulation. Today, simulation generally does not ensure that an integrated circuit or electronic system will pass qualification testing the first time, and failures are often attributed to insufficiency of the simulation models. With an improved modeling capability, one could achieve better design efficiency, and also perform design optimization. For system simulation, behavioral models of the components' terminal responses are desired for both computational tractability and protection of intellectual property. Despite many years of significant effort by the electronic design automation community, there is not a general, systematic method to generate accurate and comprehensive behavioral models, in part because of the nonlinear, complex, and multi-port nature of the components being modeled.CAEML will pioneer the use of machine-learning methods to extract behavioral models of electronic components and subsystems from simulation waveforms and/or measurement data. The Center will make 2 primary contributions to the field of machine learning: it will demonstrate the application of machine learning to electronics modeling, and develop the entire machine-learning pipeline. Historically, machine-learning theorists have focused on the model learning and evaluation tasks, but CAEML will focus on end-to-end performance of the pipeline, including data acquisition, selection and filtering, as well as cost function specification. CAEML will develop a methodology to use prior knowledge, i.e., physical constraints and the domain knowledge provided by designers, to speed up the learning process. Novel methods of incorporating component variability, including that due to semiconductor process variations, will be developed. The intended end-users are electronic design automation (EDA) tool developers, IC design houses, and system design and manufacturing companies.CAEML consists of 3 sites: Illinois, Georgia Tech, and NC State. The scope of research at each site encompasses both algorithm development and the application of the derived models to a variety of IC and system design tasks. Investigators at all 3 university sites have unique skills and expertise while sharing interests in electronic design automation, IC design, system-level signal integrity, and power distribution. To leverage the cross-campus expertise, many of the Center's proposed projects involve investigators from more than one site. The Illinois investigators have special expertise in computational electromagnetics, electrostatic discharge (ESD), and optimization; they bring capabilities in areas such as circuit design for ESD-induced error detection, computationally-efficient stochastic electromagnetic field simulation, reduced-order modeling and behavioral modeling of electrical/electromagnetic circuits and systems, and multi-domain physics modeling in the presence of uncertainty and variability. All three sites have strong research records in the fields of signal integrity analysis and electronic design automation. Excellent computational resources are available at Illinois for the proposed work; the necessary test and measurement equipment is also available, including a system-level ESD test-bed.

半导体行业长期以来是美国顶级出口商之一。 2014年的全球半导体销售额达到了3358亿美元，该领域的美国工作人数估计在2013年约为25万美元。更广泛地说，美国科技行业依赖于刺激新产品和应用的美国科技行业本身不少于付款，估计该行业的工作不少于5.7％（在美国私人部门的6.5百万美元）中（在5.7％的工作中） 2014年6540亿美元，占美国所有私营部门工资的11％以上。尽管取得了成功，但如果美国要在这个竞争激烈的地区保留全球领导力，该行业必须继续创新。现代微电子产品的复杂性需要在制造前使用计算机工具来制定和验证产品设计。当产品无法按预期运行或遭受早期故障的损失时，这通常归因于设计过程中使用的模型不足。实际上，现有的系统组件建模方法的缺点已成为持续创新的严重障碍。通过机器学习的高级电子中心（CAEML）提议创建机器学习算法，以得出用于电子设计自动化的模型，目的是实现快速，准确的微电子电路和系统的设计。成功将使优化系统设计变得更加容易，更便宜，从而使行业能够在不牺牲功能的情况下生产低功率和低成本的电子系统。最终的结果将是能力的显着增长，这些能力将推动整个电子行业的创新，导致新的设备和应用，持续的企业家领导和经济增长。在实现这些目标的同时，CAEML还将专注于多样化的本科工程学生团体并改善本科体验。传统上，工程中代表人数不足的团体的学生将成为本科研究助理的招聘目标。会员公司将为参与学生提供实习和导师，而CAEML的多元化研究生和本科生研究人员将接受动手的多学科教育。 Caeml还将参加三所场地大学与当地青年的学生和教师互动的现有途径。特别是，大学夏令营是一种经过久经考验的方法，可以使高中生在我们的校园中熟悉并舒适。伊利诺伊大学Urbana-Champaign（“伊利诺伊州”）在伊利诺伊大学的数学，工程和科学（游戏）夏令营计划的女子冒险活动将高中女孩带到校园，进行一周的动手工程活动和友情。许多游戏训练营的工程内容，包括电气工程的一个营地，都是由工程教师开发的。 CAEML本科生和研究生可以担任营地的辅导员或讲师； Caeml团队建议在所有三个地点的校园内为高中露营者开发新的活动和研讨会。此外，在伊利诺伊州举行的初学教师STEM会议还带来了150名教师，他们刚刚在教室里完成了第一年，到Urbana-Champaign校园呆了2天，以加深对STEM领域的了解，并尝试在教室中使用活动；工程学院教师（包括隶属于Caeml）教授了一些课程。通过机器学习的高级电子中心（CAEML）将创建机器学习算法，以得出用于电子设计自动化的模型，目的是实现快速，准确的微电子电路和系统的设计。电子行业的持续创新能力需要创建优化方法，从而导致低功率集成系统符合性能规格，尽管该组件由其特征表现出可变性并且在不同的物理或信号域中运行的组件组成。如今，组件级行为模型的准确性和全面性的缺点阻碍了计算机辅助电子系统设计优化的进步。模型的准确性还会影响系统验证。最终，通过测试代表性样本来验证电子系统的正确功能。但是，现代电子系统是如此复​​杂，以至于不先使用仿真验证其操作而将其带入制造阶段是不可想象的。如今，仿真通常不能确保集成电路或电子系统将首次通过资格测试，并且故障通常归因于模拟模型的不足。通过提高的建模能力，可以提高设计效率，并执行设计优化。对于系统仿真，对于计算障碍和知识产权的保护，需要对组件终端响应的行为模型。尽管电子设计自动化社区多年来付出了多年的努力，但并没有一种一般的，系统的方法来产生准确和全面的行为模型，部分原因是要建模的组件的非线性，复杂和多端口性质。Caeeml会先开拓机器实行方法来利用机器学习方法来从模型和测量量和/或测量下或/或/或/或/或/或/或/或//点或//或///simulation supulation Waversulation和/simaulation supluality Waver和/simale suplations and/of/noge。该中心将对机器学习领域做出2个主要贡献：它将证明机器学习对电子产品建模的应用，并开发整个机器学习管道。从历史上看，机器学习理论家一直专注于模型学习和评估任务，但是CAEML将专注于管道的端到端性能，包括数据采集，选择和过滤以及成本函数的规范。 CAEML将开发一种使用先验知识的方法，即物理约束和设计师提供的领域知识，以加快学习过程。将开发合并组件变异性的新方法，包括由于半导体过程变化而发展。预期的最终用户是电子设计自动化（EDA）工具开发人员，IC设计公司以及系统设计和制造公司。CAEML由3个站点组成：伊利诺伊州，乔治亚州理工大学和北卡罗来纳州立大学。每个站点的研究范围都包含算法开发以及派生模型在各种IC和系统设计任务中的应用。所有三个大学站点的研究人员都有独特的技能和专业知识，同时分享了电子设计自动化，IC设计，系统级信号完整性和电源分配的兴趣。为了利用跨校园专业知识，该中心的许多项目涉及来自一个以上站点的调查人员。伊利诺伊州的研究人员在计算电磁，静电放电（ESD）和优化方面具有特殊的专业知识。它们在诸如ESD诱导的误差检测之类的电路设计，计算有效的随机电磁场模拟，减少阶段的建模以及电气/电磁电路和系统的行为建模以及在不存在的不确定性和可变性的情况下进行多域物理学建模的领域带来了功能。这三个站点在信号完整性分析和电子设计自动化领域的研究记录都有很强的研究记录。伊利诺伊州提供优质的计算资源，可用于拟议的工作；还提供必要的测试和测量设备，包括系统级ESD测试床。

项目成果

Surrogate Modeling with Complex-valued Neural Nets and its Application to Design of sub-THz Patch Antenna-in-Package

• DOI: 10.1109/ims37964.2023.10187990
• 发表时间: 2023-06
• 期刊: 2023 IEEE/MTT-S International Microwave Symposium - IMS 2023
• 作者: O. Akinwande;Osama Waqar Bhatti;Kai-Qi Huang;Xingchen Li;Madhavan Swaminathan