IUCRC Planning Grant Carnegie Mellon University: Center for Materials Data Science for Reliability and Degradation (MDS-Rely)

该项目计划在材料可靠性和降级数据科学中心(MDS-RELY)规划一个新的站点，方法是在应用数据科学研究以了解材料的可靠性和寿命方面获得行业支持和反馈，并利用这些反馈确保该中心能够响应行业需求。材料、零部件和产品的可靠性对美国在能源、国防以及国家健康和福利方面的基础设施至关重要。MDS-Repend将招募有兴趣与该中心进行研究的潜在行业合作伙伴，将数据科学应用于材料开发。然后，规划拨款将获得这些行业合作伙伴对该中心以下目标的反馈：(1)加强可靠性测试，(2)开发退化模型，(3)应用退化模型，以及(4)发展教育计划。这些努力将共同提高国家利益。MDS-Repend将利用产业界和学术界之间的关系，在将数据科学应用于应用材料开发、设计和可靠性方面取得进展。将有三个智能推动力：(1)软和生物材料配方；(2)材料数据科学的自然语言处理；以及(3)催化材料和工艺的数据驱动设计。软性和生物材料配方的推力将包括机器学习、实验的增强设计和自动化科学。自然语言处理的重点将是在材料可靠性和退化方面更有效地利用现有文献。最后，催化剂材料和工艺的数据驱动设计将把自动化模拟与工艺系统工程结合起来，以发现对降解具有健壮性的材料和工艺。新网站将利用卡内基梅隆大学在软材料和生物材料以及催化领域的专业知识，利用计算、数据科学和机器学习的交叉领域的优势。这一奖项反映了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。

This project proposes to plan a new site in the Center on Data Science for Materials Reliability and Degradation (MDS-Rely) by garnering industry support and feedback on applying data science-informed research to understand reliability and lifetime of materials, and use this feedback to ensure the Center is responsive to industry needs. Reliability of materials, parts and products are essential for US infrastructure in energy, defense, and national health and welfare. MDS-Rely will recruit potential industry partners interested in conducting research with the Center to apply data science to materials development. The planning grant will then garner feedback from these industry partners on the following objectives of the Center: (1) Enhance reliability testing, (2) Develop degradation models, (3) Apply degradation models, and (4) Develop educational programs. Together these efforts will enhance national interests.MDS-Rely will harness relationships between industry and academia to make headways in applying data science to applied materials development, design, and reliability. There will be three intellectual thrusts: (1) Soft and biomaterial formulation; (2) Natural language processing for data science of materials; and (3) Data-driven design of catalytic materials and processes. The soft and biomaterial formulation thrust will encompass machine-learning augmented design of experiments and automated science. The natural language processing thrust will focus on leveraging the existing literature more effectively in the area of materials reliability and degradation. Finally, the data-driven design of catalyst materials and processes will combine automated simulation with process systems engineering to discover materials and processes that are robust to degradation. The new site will leverage strengths at the intersections of computing, data science and machine learning with domain expertise in soft and biomaterials as well as catalysis at Carnegie Mellon University.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.