08/25/2022
By Sokny Long

The Francis College of Engineering, Department of Plastics Engineering, invites you to attend a doctoral dissertation proposal defense by Tahamina Nasrin on “Applying Machine Learning Approaches to Multilayered Polymer Composites.”

Ph.D. Candidate: Tahamina Nasrin
Proposal Defense Date: Friday, Aug. 26, 2022
Time: 1 to 3 p.m. PM EDT
Location: ETIC 345 and virtual via Zoom. Those interested in attending should contact Tahamina_Nasrin@student.uml.edu and committee advisor, Amy_Peterson.uml.edu, at least 24 hours prior to the defense to request access to the meeting.

Committee Chair (Advisor): Amy Peterson, Associate Professor, Associate Chair-Master’s Studies, Plastics Engineering, University of Massachusetts Lowell

Committee Members:

  • Christopher J. Hansen, Chair, Associate Professor, Mechanical Engineering, University of Massachusetts Lowell
  • Wan-Ting (Grace) Chen, Assistant Professor, Plastics Engineering, University of Massachusetts Lowell
  • Farhad Pourkamali Anaraki, Assistant Professor of Data Science, Department of Mathematical and Statistical Sciences, University of Colorado Denver
  • Robert E. Jensen, Weapons and Materials Research Directorate, DEVCOM-ARL Northeast

Brief Abstract:

Multilayered polymer composites can outperform neat polymers in terms of mechanical and chemical properties. As a result, multilayered polymer and polymer composites have been widely used in additive manufacturing and packaging. However, because the qualities and performance of multilayer polymer composite components vary greatly depending on processing parameters and structure, it is difficult to control them. Furthermore, screening polymer materials for a specific use is tough due to the multiple decision-making metrics. Physics-based models have proved effective for examining specific measures, but their computational complexity makes it impossible to include the entire process. Furthermore, screening techniques are heavily reliant on experiments, which take time and can be costly. Data-driven machine learning techniques can solve these challenges since they can understand the underlying pattern in a dataset and generate predictions for previously unseen cases. Applying machine learning techniques to materials science is challenging because they require large training datasets, which is often difficult to achieve because associated experiments to generate data are time consuming. The overall goal of my PhD research is to apply machine learning techniques to multilayered polymer composites in order to advance our ability to predict their properties. We will apply regression and classification-based machine learning techniques to predict important part properties, screen materials for specific applications, and explore a large design space. The successful completion of the proposed tasks will give a path for applying machine learning approaches in two distinct areas, including the use of complicated materials such as multilayered polymer composites.

All interested students and faculty members are invited to attend the defense in person or via remote online access.