SBIR Phase I: Intelligent Cloud-based Advanced Manufacturing Services

这个小企业创新研究（SBIR）第一阶段项目的更广泛的影响/商业潜力是将先进制造扩展到原型制造之外，以实现数字到物理过程的更高生产力吞吐量。包括机器学习在内的组合算法管理直接数字化制造应用程序的数字线程和物理创建工作流，同时保留开放式（变化友好型）设计演变和敏捷零件创建。从企业活动到军事应用，客户/任务需求的动态性要求在设计和最终产品推出方面做出快速反应。需要将快速设计过程与敏捷制造过程同步，以最大限度地减少响应滞后。在这个SBIR项目中开发的算法解决了数字到物理阈值的端到端通信不一致性，同时提高了生产力，减少了昂贵的计划外停机时间的负面影响。该SBIR项目的预期结果是提高吞吐量并为智能先进制造提供所需的物流。这个小企业创新研究（SBIR）第一阶段项目旨在验证解决库存管理和生产排队所需的组合算法，以确保数字设计演变和通过增材制造进行的生产保持同步。当反直觉的零件创建排队问题得到充分解决时，制造点下游的活动（如装配和集成）与大型零件的长周期制造同步进行时，就可以实现快速制造。从本质上讲，下游的工人保持生产效率，因为更长的主要部件正在制造/打印。然而，当产品的设计是开放式的，并对生产队列和下游后组装/集成造成持续的中断时，问题就变得复杂了。开放式设计演变对物理制造演变的动态影响造成了重大的管理困难；因此，组合算法及其机器学习能力是实现智能制造的关键。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 to extend advanced manufacturing beyond prototyping to enable higher productivity throughput in digital-to-physical processes. Combinatorial algorithms, including machine learning, manage both the digital thread and the physical creation workflow of direct digital manufacturing applications, while retaining open-ended (change-friendly) design evolution and agile part creation. From entrepreneurial activities to military applications, the dynamic nature of customer/mission needs requires quick reaction in both design and end-product roll-out. Synchronizing the rapid design process with an agile manufacturing process is required to minimize response lags. The algorithms developed in this SBIR project solve the end-to-end communication inconsistencies across the digital-to-physical threshold while increasing productivity and reducing the negative impact of costly unplanned downtime. The desired result of this SBIR project is to enhance throughput and deliver the needed logistics to intelligent advanced manufacturing.This Small Business Innovation Research (SBIR) Phase I project aims to validate the combinatorial algorithm solving the inventory management and production queueing needed to ensure that the digital design evolution and on-going production via additive manufacturing remain in synchronicity. Rapid manufacturing is achieved when the counter-intuitive part creation queueing is adequately solved so activities downstream of the point of fabrication, like assembly and integration, occurs in sync with the long lead fabrication of larger parts. Essentially, workers downstream remain productive as longer lead parts are being fabricated/printed. However, the problem is compounded when the design of the product is open-ended and creates ongoing disruption to the production queueing and downstream post assembly/integration. The dynamic impact of open-ended design evolution on physical fabrication evolution creates significant management difficulties; therefore, the combinatorial algorithm and its machine learning capability is the key enabler to creating smart 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.