SBIR Phase I: Development of an AI PCB Prototyping Service called FlashPCB

SBIR第一阶段项目的更广泛影响是创建一个人工智能驱动的印刷电路板组装（PCBA）服务，以促进美国的创新和经济增长。PCBA原型制作是从消费品到医疗设备的所有电子产品创新过程中的关键要素，但目前的PCBA原型制作服务受到手动步骤和供应链短缺的限制。该项目的人工智能创新将通过战略自动化、缩短创新时间表和更快地将新产品推向市场来节省客户的时间。目前，中国和其他亚洲国家仍然主导着PCBA市场份额，为来自美国的许多客户提供服务。有机会在美国提供高质量、具有成本竞争力的制造业，以更好地服务于市场，满足对PCBA不断增长的需求。此外，对国内制造业的投资将加强电子制造能力，减少对外国市场的依赖，并保护知识产权。该项目的技术创新是开发两种人工智能算法，共同确定要安装在客户印刷电路板上的元件的最佳选择。第一个算法读取设计文件并识别用户为其设计指定的组件属性。第二种算法将这些属性作为其输入，并为设计中的组件选择库存部件，然后将其安装到印刷电路板上。这是一项节省成本和时间的创新，使用最先进的人工智能算法并编码电气工程原理。该项目的主要目标是了解我们的客户可能在其设计中使用的组件的类型和组合，定义和测试组件属性识别的算法，并定义和测试算法，该算法将选择用于制造PCBA的最佳组件。该奖项反映了NSF的法定使命，并通过使用基金会的学术价值和更广泛的影响评审标准。

The broader impact of this SBIR Phase I project is to create an artificial intelligence-powered printed circuit board assembly (PCBA) service that facilitates innovation and economic growth in the United States. Prototyping PCBAs is a key element in the innovation process for all electronics from consumer goods to medical devices, but current PCBA prototyping services are limited by manual steps and supply chain shortages. The artificial intelligence innovation of this project will save the customers time through strategic automation, shortening innovation timelines, and bringing new products to market faster. Currently, China and other Asian countries are still dominating the PCBA market share, serving many customers from the United States. There is an opportunity to provide high-quality, cost-competitive manufacturing in the United States to better serve the market and meet the rising demand for PCBAs. Additionally, investment in domestic manufacturing will strengthen electronic manufacturing capabilities, reduce dependence on foreign markets, and protect intellectual property. The technical innovation of this project is the development of two artificial intelligence algorithms that work together to determine the optimal selection of components to be mounted on a customer’s printed circuit board. The first algorithm reads the design file and identifies the properties of the components that the user has specified for their design. The second algorithm takes these properties as its input and selects in stock parts for the components in the design which will then be mounted onto the printed circuit board. This is a cost and time saving innovation that uses state of the art artificial intelligence algorithms and encodes electrical engineering principles. The key objectives for this project are to understand the types and combinations of components that our customers are likely to use in their designs, to define and test the algorithm for component property identification, and to define and test the algorithm which will choose the optimal components used for the manufacture of PCBAs.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.