2025 ASEE Annual Conference & Exposition

A critical review of approaches to teaching artificial intelligence in undergraduate materials engineering

Presented at Materials Division (MATS) Technical Session 4

Software tools utilizing artificial intelligence (AI) through machine learning are becoming increasingly vital in materials engineering, especially materials design and development. However, these tools are not yet widely integrated into undergraduate materials engineering curricula. This paper presents a critical review of existing approaches to introducing machine learning concepts to undergraduate students in materials engineering. Although Python-based frameworks such as Jupyter Notebooks, Scikit-Learn, and Google Colab, as well as AI modules in MATLAB, have been developed, their adoption remains limited. Programming complexity and the unclear role of materials engineers in these exercises are likely reasons for this limited uptake. We propose a greater emphasis on materials engineering domain knowledge and structured material data to enhance the application of machine learning in solving materials engineering problems, as is required in industry. Additionally, there is a shortage of suitable datasets and tools for teaching machine learning to engineering students with minimal computer science (coding) background. Hence, more openly available real-world datasets for a range of materials engineering problems that could be used across various years of study would be beneficial in increasing adoption. The introduction of user-friendly AI software tools, which do not require coding, would likely facilitate their integration into the classroom. A comparison can be drawn to the increased prevalence of finite element modeling software in engineering education over recent decades. We offer perspectives from a primarily undergraduate institution (PUI), a research-intensive institution (R1 University), and industry. We aim to engage the community in dialogue to foster ideas and encourage the adoption of AI tools in materials design and development within modern materials engineering curricula.

Authors

Dr. Joel L Galos http://orcid.org/0000-0003-2490-7232 California Polytechnic State University, San Luis Obispo [biography]

Dr. Joel Galos is a tenure-track Assistant Professor of Materials Engineering at California Polytechnic State University (Cal Poly), San Luis Obispo. His teaching and research interests are centered on the design, analysis and optimization of engineering materials, especially polymer composites.
Dr. Mohsen Beyramali Kivy California Polytechnic State University, San Luis Obispo [biography]

Assistant Professor of Materials Engineering.
Prof. Lessa Grunenfelder University of Southern California [biography]

Lessa Grunenfelder has a BS in astronautical engineering and a MS and PhD in materials science, all from the University of Southern California. In 2015 she joined the USC Mork Family Department of Chemical Engineering and Materials Science as teaching faculty. She teaches both undergraduate and graduate courses on material properties, processing, selection, and design. She is passionate about sharing her love of materials science with students through curriculum that combines fundamental science and engineering application. Her research interest is in efficient manufacturing of high performance composites. She is an active member of the Society for the Advancement of Material and Process Engineers (SAMPE), and the American Society for Engineering Education (ASEE).
Ken-ichi Nomura University of Southern California [biography]

Senior Lecturer of Mork Family Department of Chemical Engineering and Materials Science at USC. Developed an MS program of Materials Engineering with Machine Learning emphasis along with several graduate and undergraduate courses of computational materials science and machine learning. Co-PI of NSF CyberMAGICS and chief software architect for AIQ-XMaS (AI & quantum-computing enabled exascale materials simulator). A former NSF ACI-REF member to forge a nationwide alliance of educators to empower local campus scientists and engineers.
James E Saal Citrine Informatics, Inc.

Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 22, 2025, and to all visitors after the conference ends on June 25, 2025

« View session