Public Lecture: Data-driven 3D printing technology - Interdisciplinary research cooperation

Time: 14:00 to  16:00 Ngày 11/04/2023

Venue/Location:

Content:

Time: 14:00, April 11, 2023
Place: Laurent Schwartz Hall, VIASM, 157 Chua Lang Street, Dong Da, Hanoi

Speaker: Prof. Nguyen Xuan Hung, Director of CIRTech Institute, HUTECH University, Vietnam.

Prof. Hung Nguyen Xuan (H. Nguyen-Xuan) is the Director of CIRTech Institute, HUTECH University, Vietnam. He is currently an adjunct professor at China Medical University (Taiwan) (from 2015 to present) and a visiting professor at Sejong University (South Korea) (from 2014 to present). Prof. Nguyen-Xuan is the President of Vietnam Association for Computational Mechanics. He serves on the editorial board of Composite Structures, Computers & Structures, Engineering Fracture Mechanics and CMC: Computers, Materials & Continua. He is also an editor of CMES: Computer Modeling in Engineering & Sciences, a subject editor of Underground Space, and an associate editor of International Journal of Hydromechatronics.
Dr. Nguyen-Xuan received his Ph.D. in Computational Mechanics from The University of Liège (Belgium) in 2008. His research focuses on advanced computational methods in engineering, data-driven machine learning modelling, and 3D printing. He has published more than 250 peer-reviewed papers indexed in WoS. His remarkable work has earned him recognition as a 1% Highly Cited Researcher – Clarivate through nine continuous years, from 2014 to 2021 in the category of Computer Science and 2022 in the field of Cross-Field category.
Dr. Nguyen-Xuan has earned several prestigious awards, including the Alexander von Humboldt Foundation Digital Cooperation Fellowship (2021), the Outstanding Humboldtian (2019), and the Georg Forster Research Award – Humboldt Foundation (2015), making him the youngest-ever recipient of the award. Additionally, he has received recognition from the Vietnam National University HCMC (2008 – 2013), and Nguyen Van Dao Award (2011).
Abstract: Additive manufacturing (AM), commonly known as 3D printing, is a cutting-edge technology in Industry 4.0, which is expected to revolutionize the manufacturing sector in the next 50 years. Over the past decade, AM technology has rapidly advanced, emerging into high-value manufacturing applications across various interdisciplinary industrial sectors. The market size for AM has grown from $18.33 billion in 2022 to an estimated of $83.90 billion by 2029 [1]. A development trend in the 3D printing industry can be found in [2]. AM is more than just producing a prototype. It involves tackling complex mathematical models of multi-scale and multi-physics problems, large-scale computations, and developing advanced materials in conjunction with the next-generation 3D printers. Simultaneous and accurate solving procedure of advanced AM processes – such as optimal design, material tuning, process optimization, in situ monitoring, cloud service, and cybersecurity – can yield significant benefits for both suppliers and customers. Therefore, successful development of 3D printing products requires interdisciplinary knowledge and collaboration in fields such as mathematics, computer science, physics, material science, and engineering. In our recent work, we have developed mathematical models and deep learning techniques for the 3D printing cycle [3]. Our approaches [3,4] can be applied to various stages, including data preprocessing, data normalization, data analysis, printing process normalization, printing process optimization, and handling customer feedback [5]. To effectively commercialize 3D printing-based products, interdisciplinary cooperation in this area is essential.
References:
[1] https://www.fortunebusinessinsights.com/industry-reports/
[2] https://3dprintingindustry.com/
[3] Phuong D Nguyen, Thanh Q Nguyen, QB Tao, Frank Vogel, H Nguyen-Xuan, A data-driven machine learning approach for the 3D printing process optimisation, Virtual and Physical Prototyping, 17, 768-786, 2022.
[4] Thang Le-Duc, Quoc-Hung Nguyen, J. Lee, H Nguyen-Xuan, Strengthening Gradient Descent by Sequential Motion Optimization for Deep Neural Networks, IEEE Transactions on Evolutionary Computation, in press, 2022.
[5] https://ht3dprint.com/

Registration: here
https://docs.google.com/forms/d/e/1FAIpQLScpPRqX4gyzbRnA8_6zdzCYvAlqGpXUUeQfVPukIX-jbHGfkw/viewform
Liên hệ:

Ms. Ngân Hà - 0984.612.338
Ms. Huyền My - 0981158499