I-Corps: Additive Manufacturing Quality Control Software

这个I-Corps项目的更广泛的影响/商业潜力是开发一个新的增材制造图像引导质量控制框架。在生产时，操作员将被提醒产品缺陷，以便他们可以立即采取纠正措施。反过来，负责产品质量的管理人员可以调查缺陷的根本原因，并对其生产流程进行改进。最终，通过提高产品质量，美国先进制造商可以减少与低质量零件相关的费用，并通过确保只向客户提供最高质量的产品来提高竞争力。这个I-Corps项目是基于开发一种新的方法，用于监测和控制基于多路复用网络的产品的动态图像配置文件。这项工作的重点是创建一个基于传感器的，非线性动力学方法的实时系统信息，监测和控制。工业系统的先进感测已经引起了现场成像，其允许对复杂过程进行实时监测和控制。例如，高速相机通常位于增材制造（AM）机器中的粉末床上方，以逐层捕获图像用于过程监控。这项工作将为增材制造设计和开发一个新的图像引导质量控制框架。这种新方法可能会使美国制造商处于优势地位。在应用人工智能深度神经网络算法时，该团队解决了高维图像流中的复杂结构，用于现场监测和控制制造过程。 该奖项反映了NSF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 new framework for image-guided quality control of additive manufacturing. At the point of production, operators will be alerted to product defects so that they can take corrective action instantly. In turn, managers responsible for product quality can investigate the root causes of defects and make improvements to their production processes. Ultimately, by improving product quality, US advanced manufacturers may decrease expenses associated with poor-quality parts and increase their competitiveness by ensuring only the highest quality products are delivered to their customer. This I-Corps project is based on the development of a novel method for monitoring and controling the dynamic image profiles of their products based on multiplex networks. This work is focused on creating a sensor-based, nonlinear dynamics methodology for real-time system informatics, monitoring, and control. Advanced sensing of industrial systems has given rise to in-situ imaging that allows for real-time monitoring and control of complex processes. For instance, high-speed cameras are often situated above powder beds in additive manufacturing (AM) machines to capture layer-by-layer images for process monitoring. This work will design and develop a new framework of image-guided quality control for additive manufacturing. This novel method may put US manufacturers at an advantage. In applying artificial intelligence deep neural network algorithms, the team addresses the complex structures in the high-dimensional image streams for in-situ monitoring and control of manufacturing processes. This process enables real-time quality inspection, defect mitigation, and process improvement.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.