I-Corps: Translation potential of accelerating process development for additive manufacturing of metals

I-Corps项目的更广泛影响是开发基于机器学习的原位方法来监测金属增材制造过程。目前，由于材料的复杂加工性质和相关的物理现象，金属合金的印刷是困难的。印刷结果和印刷部件质量的可变性是降低印刷部件质量及其充分生产潜力的主要障碍。该技术使用原位测量，它允许缺陷监视和质量保证报告、自动反馈控制、过程参数映射，以及对缺陷形成机制的理解。此外，该解决方案还研究了加工-结构-性能关系，研究了新合金的可打印性，减少了对非原位表征的需求，并通过早期识别零件故障减少了材料浪费和生产时间。这个I-Corps项目利用体验式学习和对行业生态系统的第一手调查来评估该技术的翻译潜力。该解决方案基于人工智能辅助方法的发展，以帮助工艺开发和控制激光粉末床熔融增材制造零件的质量。该方法使用想象传感器和机器学习来实时监控过程，并告知处理的最佳参数以及可能导致打印缺陷的过程变量。该方法不需要特殊的、复杂的温度测量装置，这些装置可能无法可靠地用于不同的金属合金。结果表明，该方法适用于不同类型的金属合金在激光粉末床上的测试。控制打印部件质量的能力可能有助于在更广泛的应用范围内采用金属3D打印。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 of this I-Corps project is the development of machine learning-based in-situ methods to monitor the metal additive manufacturing process. Currently, printing in metal alloys is difficult due to the complex processing nature of the materials and the associated physical phenomena. The variability in printing outcomes and the quality of printed parts is a major obstacle that reduces the quality of printed parts and the potential for their full production. This technology uses in-situ measurement, which allows for defect monitoring and quality assurance reporting, automatic feedback control, process parameter mapping, and an understanding of defect formation mechanisms. In addition, the solution studies processing–structure-property relationships, investigates the printability of new alloys, reduces the need for ex-situ characterization, and reduces material waste and production time by early identification of part failure.This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of the technology. The solution is based on the development of an artificial intelligence-assisted approach to aid process development and the control of the quality of parts additively manufactured by laser powder bed fusion. The method uses imagining sensors and machine learning to monitor the process in real time and to inform the optimal parameters for processing as well as the process variables that can lead to printing defects. The method does not require special, complicated setups for temperature measurements that may not work reliably for different metal alloys. The method was found to be generalizable to different types of metal alloys tested on a laser powder bed machine. The ability to control the quality of printed parts may help in adopting 3D printing of metals in a wider scope of applications.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.