TY - GEN
T1 - Investigating Statistical Correlation Between Multi-Modality In-Situ Monitoring Data for Powder Bed Fusion Additive Manufacturing
AU - Yang, Zhuo
AU - Adnan, M.
AU - Lu, Yan
AU - Cheng, Fan Tien
AU - Yang, Haw Ching
AU - Perisic, Milica
AU - Ndiaye, Yande
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - In-situ measurements provide vast information for additive manufacturing process understanding and real-time control. Data from various monitoring techniques observe different characteristics of a build process. Fusing multi-modal in-situ monitoring data can significantly enhance process anomaly detection, part defect prediction, and build failure diagnosis, thus improving AM part quality control. This paper compares the powder bed fusion in-process observations from two types of AM in-situ monitoring, coaxial melt pool imaging, and layerwise imaging, and investigates the correlation between the two observations for a build of parts with multiple geometric features and scan patterns. All data were collected from an open architecture powder bed fusion AM testbed. Data analysis shows that both datasets exhibit significant statistical changes when new features are introduced during the build. However, further machine learning-based modeling indicates that statistical features extracted from the two data sets do not correlate very well. Discussions are provided on how the statistical analysis of the observations from the two modality monitoring system can be utilized for data fusion strategy development, especially toward improving process anomaly detection.
AB - In-situ measurements provide vast information for additive manufacturing process understanding and real-time control. Data from various monitoring techniques observe different characteristics of a build process. Fusing multi-modal in-situ monitoring data can significantly enhance process anomaly detection, part defect prediction, and build failure diagnosis, thus improving AM part quality control. This paper compares the powder bed fusion in-process observations from two types of AM in-situ monitoring, coaxial melt pool imaging, and layerwise imaging, and investigates the correlation between the two observations for a build of parts with multiple geometric features and scan patterns. All data were collected from an open architecture powder bed fusion AM testbed. Data analysis shows that both datasets exhibit significant statistical changes when new features are introduced during the build. However, further machine learning-based modeling indicates that statistical features extracted from the two data sets do not correlate very well. Discussions are provided on how the statistical analysis of the observations from the two modality monitoring system can be utilized for data fusion strategy development, especially toward improving process anomaly detection.
UR - http://www.scopus.com/inward/record.url?scp=85141730308&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85141730308&partnerID=8YFLogxK
U2 - 10.1109/CASE49997.2022.9926715
DO - 10.1109/CASE49997.2022.9926715
M3 - Conference contribution
AN - SCOPUS:85141730308
T3 - IEEE International Conference on Automation Science and Engineering
SP - 283
EP - 290
BT - 2022 IEEE 18th International Conference on Automation Science and Engineering, CASE 2022
PB - IEEE Computer Society
T2 - 18th IEEE International Conference on Automation Science and Engineering, CASE 2022
Y2 - 20 August 2022 through 24 August 2022
ER -