Machine learning-aided real-time detection of keyhole pore generation in laser powder bed fusion

• 成果类型: Article
• 署名作者: Ren, Zhongshu; Gao, Lin; Clark, Samuel J.; Fezzaa, Kamel; Shevchenko, Pavel; Choi, Ann; Everhart, Wes; Rollett, Anthony D.; Chen, Lianyi; Sun, Tao
• 署名单位: University of Virginia; United States Department of Energy (DOE); Argonne National Laboratory; United States Department of Energy (DOE); Honeywell; Carnegie Mellon University; University of Wisconsin System; University of Wisconsin Madison
• 刊物名称: SCIENCE
• ISSN/ISSBN: 0036-13158
• DOI: 10.1126/science.add4667
• 发表日期: 2023-01-06
• 页码: 89-93
• 关键词: formation mechanisms; x-ray; DYNAMICS; porosity; physics

摘要

Porosity defects are currently a major factor that hinders the widespread adoption of laser-based metal additive manufacturing technologies. One common porosity occurs when an unstable vapor depression zone (keyhole) forms because of excess laser energy input. With simultaneous high-speed synchrotron x-ray imaging and thermal imaging, coupled with multiphysics simulations, we discovered two types of keyhole oscillation in laser powder bed fusion of Ti-6Al-4V. Amplifying this understanding with machine learning, we developed an approach for detecting the stochastic keyhole porosity generation events with submillisecond temporal resolution and near-perfect prediction rate. The highly accurate data labeling enabled by operando x-ray imaging allowed us to demonstrate a facile and practical way to adopt our approach in commercial systems.