- Apply to UW
- Programs & Majors
- Cost & Financial Aid
- Current Students
- UW Life
- About UW
Dr. Johnson along with co-PI’s Lars Kotthoff from Computer Science and DP Aidhy and
Ray Fertig from Mechanical Engineering have established a newly funded center to advance
materials synthesis and fabrication through the use of artificial intelligence informed
experimental and computational studies.
Advanced materials and manufacturing are important pillars and drivers of today’s
They have made consumer devices like TVs and computers ubiquitous by enabling cheap mass
production of reliable products, and enabled industrial applications on a scale not seen before.
However, designing new materials is a slow and laborious process, requiring significant
investments in capital and labor.
Recent advances in artificial intelligence allow to improve and speed up this process. In
particular, machine learning techniques can replace expensive and time-consuming laboratory
processes and computational simulations to quickly and reliably predict how to create materials
with desired properties and how materials will behave in specific circumstances. So-called
surrogate models learn how properties of materials and experimental parameters relate to
We propose to apply these techniques to materials engineering and manufacturing, to reduce cost
and improve performance. The proposed center merges synergistic expertise at CEAS in
materials development, chemical engineering, mechanical engineering, and computer science for
the development of powerful methods to design and model the behavior of advanced materials
and manufacture advanced devices.
We will demonstrate the feasibility and usefulness of the approach through prototype
applications that demonstrate the breadth of the center and leverage the diverse expertise of the
PIs. We will create carbon-based electronic devices from thin polymeric films as an example of
new materials and methods of manufacturing enabled by the center’s research. The AI will
dynamically control a laser in real time to create conductive paths on non-conductive sheets of
carbon. Furthermore, we will model the failure of composite materials under stress using
machine learning to determine safe deployment conditions more efficiently. The proposed
techniques can also facilitate insights that lead to a better understanding of the processes
affecting the properties and behavior of materials in manufacturing by analyzing what the
surrogate models have learned and how this relates to our current knowledge.