I-Corps: An Intelligent Re-Design Recommender System for Additive and Hybrid Manufacturing

I-Corps项目的更广泛的影响/商业潜力是开发一种潜在的新颖、强大、智能和自动化的评估和重新设计全球评估系统，为先进制造的组件可打印性提供精确的反馈。这种评估可以减少错误和打印失败，潜在地避免昂贵的试错练习，并消除由于效率低下或人工评估过程而产生的偏见和不一致。该系统允许潜在有效地组织评估，并可以避免昂贵的计算和修改。因此，这种能力可以防止由于当前手工评估组件的可打印性而造成的能量、时间和财务资源的浪费。I-Corps项目的基础是开发一种新的重新设计推荐系统，该系统可以让拥有大量现有零件库存的公司快速评估每个零件采用增材制造的可行性，并酌情实施必要的重新设计方法。该技术包括多种智能评估和重新设计方法，以及一个全自动校正系统，该系统可以校正有问题部件的几何形状，并将设计转换为与先进制造兼容的设计。这些重新设计的解决方案可以使用不同的技术为3d打印组件提供成功的几何形状。最后，该技术可以提出一种新颖的设计推荐系统，该系统使用机器学习技术智能地分析先进制造中密切相关组件的广泛数据库，为当前设计被认为对先进制造效率低下的组件集群提供有效的设计建议。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 I-Corps project is the development of a potentially novel, robust, intelligent, and automated assessment and re-design global evaluation system that provides precise feedback on components’ printability for advanced manufacturing. Such evaluations could reduce mistakes and printing failures, potentially avoid costly trial-and-error exercises, and remove biases and inconsistencies that arise from inefficient or manual evaluation processes. This system allows for potentially effectively organizing assessments and can avoid costly computations and modifications. This capability, therefore, could prevent the waste of energy, time, and financial resources imposed by current manual assessments of components’ printability. This I-Corps project is based on the development of a novel re-design recommender system that may allow companies with large inventories of existing parts to quickly assess the feasibility of employing additive manufacturing for each part and to implement necessary re-design approaches as appropriate. The technology encompasses multiple intelligent assessments and re-design methodologies, as well as a fully automated correction system that rectifies the geometries of problematic components and converts designs to be advanced manufacturing compatible. These re-design solutions can potentially provide successful geometries for 3D-printing components using different techniques. Lastly, this technology can present a novel design recommender system that intelligently analyzes an extensive database of closely related components for advanced manufacturing using machine learning techniques to provide effective design recommendations for those component clusters whose current designs are deemed inefficient for advanced manufacturing.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.