Hierarchical modeling of microstructural images for porosity prediction in metal additive manufacturing via two-point correlation function

Abstract

Porosity is one of the most critical quality issues in Additive Manufacturing (AM). As process parameters are closely related to porosity formation, it is vitally important to study their relationship for better process optimization. In this article, motivated by the emerging application of metal AM, a three-level hierarchical mixed-effects modeling approach is proposed to characterize the relationship between microstructural images and process parameters for porosity prediction and microstructure reconstruction. Specifically, a Two-Point Correlation Function (TPCF) is used to capture the morphology of the pores quantitatively. Then, the relationship between the TPCF profile and process parameters is established. A blocked Gibbs sampling approach is developed for parameter inference. Our modeling framework can reconstruct the microstructure based on the predicted TPCF through a simulated annealing optimization algorithm. The effectiveness and advantageous features of our method are demonstrated by both the simulation study and the case study with real-world data from metal AM applications.

Keywords:

• Additive manufacturing
• two-point correlation function
• Bayesian hierarchical model
• blocked Gibbs sampling
• porosity prediction

Acknowledgments

The authors would like to thank the editor, associate editor, and anonymous reviewers for many constructive comments which greatly improved the article.

Additional information

Funding

This work is supported in part by National Natural Science Foundation of China NSFC-51875003, NSFC-72171003 and NSFC-71932006.

Notes on contributors

Yuanyuan Gao

Yuanyuan Gao received a BS degree in aircraft design and engineering from Beihang University, Beijing, China, in 2018. She is currently pursuing a PhD degree in industrial engineering and management with Peking University, Beijing. Her research interests are focused on data mining, advanced data analytics, quality, and reliability engineering. She is a recipient of the National Scholarship Award from Peking University and won the Championship in the INFORMS QSR Data Challenge. She is a member of IEEE, INFORMS, IISE.

Xinming Wang

Xinming Wang received a BS degree in mechanical engineering from Tsinghua University, Beijing, China, in 2020. He is currently working towards a PhD degree in industrial and system engineering with Peking University, Beijing, China. His current research interests include data science, transfer learning, and intelligent manufacturing.

Junbo Son

Junbo Son received a BS degree in industrial systems and information engineering from the Korea University, Seoul, South Korea, in 2010, and a M.S. degree in statistics and a PhD degree in industrial & systems engineering from the University of Wisconsin-Madison, Madison, WI, USA, in 2015 and 2016, respectively. He is currently an assistant professor in the Alfred Lerner College of Business & Economics at the University of Delaware, Newark, DE, USA. His research interests include data-driven reliability engineering, medical informatics for advanced healthcare systems, and data analytics for solving various operations management problems.

Xiaowei Yue

Xiaowei Yue received a BS degree in mechanical engineering from the Beijing Institute of Technology in 2011, an MS in power engineering and thermos-physics from the Tsinghua University in 2013, an MS in statistics, PhD in industrial engineering from the Georgia Institute of Technology in 2016 and 2018. Currently, he is an assistant professor at the Grado Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, USA. His research interests are focused on engineering-driven data analytics for advanced manufacturing. He is a recipient of the Outstanding Young Manufacturing Engineer Award from SME, Manufacturing and Design Outstanding Young Investigator Award from IISE, and Grainger Frontiers of Engineering Grant Award from the National Academy of Engineering. He serves as an associate editor for IISE Transactions, Journal of Intelligent Manufacturing and IEEE Transactions on Neural Networks and Learning Systems. Dr. Yue is a senior member of IISE, ASQ and IEEE.

Jianguo Wu

Jianguo Wu received a BS degree in mechanical engineering from Tsinghua University, Beijing, China in 2009, an MS degree in mechanical engineering from Purdue University in 2011, and an MS degree in statistics in 2014 and PhD degree in industrial and systems engineering in 2015, both from the University of Wisconsin-Madison. Currently, he is an assistant professor in the Department of Industrial Engineering and Management at Peking University, Beijing, China. He was an assistant professor at the Department of Industrial, Manufacturing and Systems Engineering at UTEP, TX, USA from 2015 to 2017. His research interests are mainly in quality control and reliability engineering of intelligent manufacturing and complex systems through engineering-informed machine learning and advanced data analytics. He is a recipient of the STARS Award from the University of Texas Systems, Overseas Distinguished Young Scholars from China, P&G Faculty Fellowship, BOSS Award from MSEC, and several Best Paper Award/Finalists from INFORMS/IISE Annual Meetings. He is an associate editor of the Journal of Intelligent Manufacturing, and a member of IEEE, INFORMS, IISE, and SME.