Researchers at the University of Maryland, led by assistant professor Po-Yen Chen, have developed a machine learning model that accelerates the design of materials used in wearable heating technologies. The model, which uses machine learning and collaborative robotics, can design aerogels with programmable mechanical and electrical properties with a 95% accuracy rate. The aerogels, made from conductive titanium nanosheets, cellulose, and gelatin, are strong, flexible, and could be used in green technologies such as oil spill cleaning and sustainable energy storage. The research was supported by a grant awarded to mechanical engineering professor Teng Li.
Accelerating Green Technology Development with AI and Robotics
Researchers at the University of Maryland have developed a machine learning model that expedites the design of materials used in green technologies, such as wearable heaters. This model, proposed by Po-Yen Chen, an assistant professor in the Department of Chemical and Biomolecular Engineering, aims to eliminate the time-consuming trial-and-error processes often associated with innovation. Published in Nature Communications, the model leverages machine learning and collaborative robotics to automate design processes.
The traditional method of creating materials like aerogels, which are lightweight, porous materials used in thermal insulation and wearable technologies, is complex and time-consuming. It involves numerous experiments and experience-based approaches to explore the vast design space. Chen’s team has addressed these issues by combining robotics, machine-learning algorithms, and material science expertise. This combination enables the design of aerogels with programmable mechanical and electrical properties, with a prediction model that can generate sustainable products with a 95% accuracy rate.
Overcoming Challenges in Material Design with Machine Learning
“Materials scientists often struggle to adopt machine learning design due to the scarcity of high-quality experimental data. Our workflow, which combines robotics and machine learning, not only enhances data quality and collection rates, but also assists researchers in navigating the complex design space,” said Chen. The resulting aerogels, made using conductive titanium nanosheets and naturally-occurring components such as cellulose and gelatin, are strong and flexible.
Expanding Applications of Aerogel Design
The tool developed by Chen’s team has potential applications beyond wearable heaters. It could be used to design aerogels for green technologies used for oil spill cleaning, sustainable energy storage, and thermal energy products like insulating windows. This could make these technologies more accessible sooner than expected, thanks to the accelerated assembly process.
“The blending of these approaches is putting us at the frontier of material design with tailorable complex properties. We foresee leveraging this new scaleup production platform to design aerogels with unique mechanical, thermal, and electrical properties for harsh working environments,” said Eleonora Tubaldi, an assistant professor in mechanical engineering and collaborator in the study.
Future Directions in Aerogel Research
Looking ahead, Chen’s group plans to conduct studies to understand the microstructures responsible for aerogel flexibility and strength properties. His work was supported by the institutional Grand Challenges Team Grant for the programmable design of natural plastic substitutes, jointly awarded to mechanical engineering professor Teng Li. This research represents a significant step forward in the field of material design, with the potential to accelerate the development of green technologies.
External Link: Click Here For More
