LEAP-HI: AI-Optimized 3D Printing of Super-Soft Materials for Personalized Sensing

医学界的一个共同需求是能够连续监测局部组织，但目前的传感技术缺乏针对不同个体独特解剖的轮廓传感器所需的个性化。这项领先的美国繁荣、健康和基础设施工程(LEAP-HI)研究旨在开发可按需制造的低成本个性化传感器，以提高美国各行各业的健康和福祉。该方法利用对新材料的基础研究，结合先进的机器学习和人工智能，将个性化传感器进行3D打印，应用于医疗保健--从假肢到诊断和治疗--可能会影响数百万人。这些跨越材料科学、工程和计算的进步将提高美国创新的经济竞争力，并通过实验研究和计算研究之间的紧密协作，帮助培养下一代科学家和工程师。一系列跨越多样性、教育和外联的举措将进一步推动各年龄段工作的关键方面。这包括(A)在爱荷华州立大学辅修的一个新的网络物理系统中关于网络制造的模块，(B)与芝加哥人/西班牙裔促进协会、科学中的美洲原住民和全国黑人工程师协会的当地分会合作，吸引学生参与研究，(C)通过在沃尔夫探索和创新博物馆(MOXI)为儿童开展活动，让K-12参与进来，(D)与工业研究和服务中心(CIRAS)合作，传播网络制造方面的最佳做法和培训模块，以及(E)与加州大学圣巴巴拉分校和爱荷华州立大学的通讯办公室合作，向公众传播这项研究，以促进美国对工程领导地位的需求。这项研究将通过开发具有与人体组织匹配的机械性能的3D打印聚合物的新材料和加工技术，克服用于个性化健康监测的传统传感器技术的局限性。我们的战略将通过以下方式对先进材料向制造的转化产生基本的见解：(1)设计和合成固有地为3D打印提供可加工性的材料，同时保持生物兼容性和机械功能；(2)通过在设备尺度上的建模和预测动力学对打印过程进行先进的多尺度模拟，以了解构建过程中的宏观进展，并在微观尺度上根据材料沉积和固化的函数来定制材料特性；(3)来自传感器响应和物理感知的机器学习模型的数据融合，以实现对3D打印过程的实时预测和控制；以及(4)创造超软结构的传感器，使独特的传感模式能够在个性化的人类健康中产生社会影响。这些研究旨在通过利用计算和机器学习模型来以收敛的方式设计更有效的聚合物和传感器，从而利用数据革命。这项研究将产生也可以应用于其他工程学科的实验和计算方法。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

A common need in the medical community is an ability to monitor local tissue continuously, but current sensing technology lacks the personalization necessary to contour sensors for the unique anatomy of different individuals. This Leading Engineering for America's Prosperity, Health, and Infrastructure (LEAP-HI) research seeks to develop low-cost personalized sensors which can be fabricated on demand to enhance the health and well-being of Americans from all walks of life. The approach leverages fundamental research into new materials in tandem with advanced machine learning and artificial intelligence to ‘3D print’ personalized sensors with applications in health care—from prosthetics to diagnostics and therapeutics—that could impact millions of people. These advances spanning materials science, engineering, and computation will improve the economic competitiveness of the United States’ innovation and help train the next generation of scientists and engineers through a tight synergy between experimental and computational research. A series of initiatives spanning diversity, education, and outreach to further will advance key aspects of the work across age groups. This includes (a) modules on cybermanufacturing in a new cyber physical systems minor at Iowa State University, (b) working with the local chapters of Society for Advancement of Chicanos/Hispanics, Native Americans in Science, and the National Society of Black Engineers to draw students into research, (c) K-12 engagement through activities at the Wolf Museum of Exploration and Innovation (MOXI) for children, (d) working with Center for Industrial Research and Service (CIRAS) to disseminate best practices and training modules in cyber manufacturing, and (e) working with the communications offices of both the University of California at Santa Barbara and Iowa State University to disseminate the research to the public to promote the need for Engineering Leadership in the United States.This research will overcome the limitations of conventional sensor technologies for personalized health monitoring by developing new materials and processing techniques to 3D print polymers with mechanical properties that are matched to human tissue. Our strategy will yield fundamental insights into the translation of advanced materials to manufacturing by: (1) Designing and synthesizing materials that inherently provide processability for 3D printing while maintaining biocompatibility and mechanical function; (2) Advanced multi-scale simulations of the printing process through modeling and predictive dynamics at the device scale to understand macroscopic progression during the build process, and at the microstructure scale to tailor the material properties as a function of material deposition and curing; (3) Data fusion from sensor response and physics-aware machine learning models to enable real-time prediction and control of the 3D printing process; and (4) Creating ultra-soft structured sensors that enable unique sensing modalities for societal impact in personalized human health. These research aims to harness the data revolution by exploiting computational and machine-learning models to design more effective polymers and sensors in a convergent fashion. This research will yield experimental and computational methodologies that can also be applied to other engineering disciplines.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.