A team of engineers at the University of Maryland (UMD) has developed a model that combines machine learning and collaborative robotics to address challenges in designing materials for wearable technology. By using this accelerated method for creating aerogel materials, the researchers were able to automate the design process for new materials, making it more efficient.
Despite being simple in nature, the assembly line for creating aerogels is complex. Researchers often rely on time-intensive experiments and experience-based approaches to explore the vast design space and create these materials. This presents a challenge to achieving the desired mechanical and electrical properties in aerogels for wearable technology.
To overcome these challenges, the research team combined robotics, machine learning algorithms, and materials science expertise. They were able to accelerate the design of aerogels with programmable mechanical and electrical properties using their prediction model, which boasts a 95% accuracy rate. This innovative approach enhances data quality and collection rates, helping researchers navigate the intricate design space of wearable technology.
The team created strong and flexible aerogels using conductive titanium nanosheets, as well as naturally occurring components like cellulose and gelatine. They believe their tool could be expanded to other applications in aerogel design, such as green technologies for oil spill clean up, sustainable energy storage, and thermal energy products like insulating windows.
Eleonora Tubaldi, a collaborator of the study, emphasized the importance of blending these approaches to push the boundaries of materials design. She plans to leverage this new scaleup production platform to design aerogels with unique mechanical, thermal, and electrical properties tailored for harsh working environments. This advancement signifies a significant step forward in materials science engineering for wearable technology and beyond
