SBIR Phase I: Ultra Low-Cost Mechanical Metamaterials to Enable Mobility and Interactivity for Cyber-Physical Devices

这个小企业创新研究（SBIR）第一阶段项目的更广泛的影响/商业潜力是开发折纸启发的机械超材料。这些技术可以产生镶嵌图案，增加和增强普通材料。由于能够同时使传统材料变得更轻、更强、更多功能，这种材料设计主题有可能影响硬件、制造、能源效率、机器人和航空航天领域的广泛技术。这种潜力可以通过在材料中嵌入精心设计的几何图案来挖掘。实现这种潜在影响的当前未遇到的挑战是明显缺乏标准的超材料设计库。该项目通过探索完整运动学集的可行性来解决这一挑战，并确定所得到的物理性质是否适合更广泛的工程应用。如果成功，通过这项努力设计和验证的超材料将为用基于机械超材料的技术取代、增强或增强所有类型的机器奠定基础。这个小企业创新研究（SBIR）第一阶段项目利用人工智能增强的优化方案，自动生成满足用户定义目标属性的机械超材料设计。为了生成建议的运动学完整机械超材料集，将需要基于软件的超材料设计方法与经验验证相结合。有监督和无监督机器学习技术的结合将用于保证超材料设计师经常生成有用的、健壮的、高性能的原理图，随着超材料设计管道的反复执行，这些原理图在定性和定量上都得到了改进。核心算法提高了产生高影响的基于超材料的技术的能力，同时减少了收敛于优化设计原理图的时间。因此，先进材料技术的市场渗透障碍变得更低、更快，并受到机器学习进步的推动。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。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is the development of origami-inspired mechanical metamaterials. These techniques can generate tessellated patterns that augment and enhance common materials. With the capacity for simultaneously making conventional materials lighter, stronger, and multi-functional, this material design motif has the potential to impact a wide range of technologies in hardware, manufacturing, energy-efficiency, robotics, and aerospace. This potential can be tapped by embedding carefully designed geometric patterns into materials. The current unmet challenge for realizing this potential impact is the conspicuous absence of a standard library of metamaterial designs. This project addresses the challenge by exploring the feasibility of a complete kinematic set and to determine whether the resulting physical properties are suitable for broader engineering applications. If successful, the metamaterials designed and validated by this effort will lay the foundation for replacing, augmenting, or enhancing machines of all types with mechanical metamaterial-based technology.This Small Business Innovation Research (SBIR) Phase I project utilizes an artificial intelligence-enhanced optimization scheme to automatically generate mechanical metamaterial designs meeting user-defined target properties. To generate the proposed set of kinematically-complete mechanical metamaterials the software-based approach to metamaterial design will be required to mesh with empirical validations. A combination of supervised and unsupervised machine learning techniques will be used to guarantee the metamaterial designer routinely generates useful, robust, and high-performing schematics that qualitatively and quantitatively improve as the pipeline for metamaterial design is repeatedly executed. The core algorithm improves the ability to produce high-impact metamaterial-based technology while taking less time to converge on optimized design schematics. As such, the barrier to market penetration of advanced material technology becomes lower, faster, and is driven by advances in machine learning.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.