Bringing digital twin technology to the classroom

Digital twins are quickly revolutionizing materials science by offering virtual replicas of physical materials or processes that previously required physical experimentation. These digital counterparts are enabling researchers and industry professionals to simulate and analyze materials' behavior under various conditions, saving time and resources.

This fall, “Principles of Digital Twins in Material Science and Advanced Manufacturing” will be offered, allowing engineering students the opportunity to better understand how these technologies are impacting how materials are studied and utilized.

The course, led by Franck Adjogble, will provide an introduction to digital twin modeling, so that students can better understand the applicability of AI-predictive analytics, with particular regard to the metal and steel industries.

Adjogble, who manages digital technologies for the SMS group, has a vision for how this coursework will impact students who participate.

Skills acquired from this class will prepare students to design and develop the materials of the future.

Franck Adjogble, Adjunct professor, Department of Materials Science and Engineering

“In addition to generating and using digital twin models, students will be able to determine how to appropriate digital environments when given specific parameters, which is very useful in many industries,” says Adjogble.

In materials science, digital twins are used for design and development, process optimization, lifecycle management, and prototyping.  While some digital twin environments are better suited for real-time data processing for single assets, others require multi-domain modeling or large-scale simulations. Students will learn the tradeoffs associated with each approach and will be able to justify the selection of environment to diverse stakeholders.

“The skills acquired from this class will prepare students to design and develop the materials of the future,” notes Adjogble. “They will be able to communicate the case for digital twin adoption with professionals in a variety of settings.”

In addition to lectures that incorporate broad artificial intelligence concepts to support modeling, students will also engage in projects where they will develop digital twin models, implement predictive analytics, analyze real-time data processing, and create business cases. These projects will culminate in the design and presentation of a comprehensive digital twin project.