Industrial and Systems Engineering Colloquium

October 13, 2020
October 13, 2020
Presenter: Shenghan Guo, PhD                    
Topic: "Quality Prediction for Laser-Based Additive Manufacturing by Learning from Thermal Images
Time: 5:00 pm to 6:00 pm EST
Password: 1r455o 
Abstract: Laser-based additive manufacturing (LBAM) is a branch of highly commercialized additive manufacturing technology. It plays a critical role in manufacturing customized, high-valueadded products for its design flexibility and rapid prototyping. However, LBAM is subject to unstable part quality and process status due to the intensive heat transfer within the melt pool during manufacturing. The in-situ thermal images, collected by inline infrared camera or pyrometer, are the primary information sources for understanding the defect formulation in LBAM. Researchers are actively exploring thermal images and developing data-driven quality prediction methods. This study concentrates on two critical issues in data-driven LBAM quality prediction: (1) how to model/monitor the spatial-temporal correlations in thermal images and (2) how to make predictions with a limited amount of training data. A hierarchical monitoring system, based on spatial-temporal modeling, is developed for (1). When training data quantity is too limited for establishing such data-driven monitoring systems, LBAM-cGAN, which is developed to solve (2), can predict thermal images by learning from a small amount of existing data.
Biography: Dr. Shenghan Guo received the B.S. degree in Financial Engineering from Jilin University, Changchun, China, in 2013, the M.S. degree in Financial Mathematics from the Johns Hopkins University, Baltimore, MD, U.S., in 2014, and the M.S. degree in Engineering Sciences and Applied Mathematics from Northwestern University, Evanston, IL, U.S., in 2016. She joined the Ph.D. program in Industrial and Systems Engineering at Rutgers University, Piscataway, NJ, U.S. in 2016. Her research focuses on data-driven process monitoring and predictive analytics, with emphasis on deep learning approaches. The application fields are mainly in smart manufacturing, including laser-based additive manufacturing, resistance spot welding, hot stamping, etc. She was awarded the Tayfur Altiok scholarship and the department nominee of Louis Bevier Dissertation Completion Fellowship in 2019. Outside the department, she was the finalist of Quality, Statistics, and Reliability (QSR) Paper Competition in 2018, finalist and winner of Quality Control and Reliability Engineering (QCRE) Data Challenge in 2019, and finalist of Data Analytics and Information Sciences (DAIS) 1st Student Data Analytics Competition in 2020. 
For additional information please contact Dr. Aziz Ezzat at