Skip to Main Content

Project applies data mining to help improve software’s decision-making

Getty Images

An interdisciplinary team of Texas A&M University researchers has received a $1 million National Science Foundation grant to research data mining to optimize decision making in the software brain of the Autonomous Experimentation Platform for Accelerating Manufacturing of Advanced Materials.

The project introduces artificial intelligence and autonomy modules into an autonomous experimentation platform to mimic a human scientist’s ability to handle surprising observations, synthesize diverse bodies of knowledge and explore a large, complex design space. The key research components in this platform are organized around three capability themes: exploitation to efficiently determine the most promising regions of a design space, exploration to recognize and reason about surprises arising from unusual designs and the expansion of newly discovered design spaces based on mining new knowledge from literature and databases, while preferentially gaining knowledge in regions likely to contain superior material design solutions.

The proposed system is cognizant, adaptive, knowledge-rich and taskable, interacting with human scientists by way of simple commands and executing an autonomous discovery process with a minimal and appropriate degree of human intervention. 

Yu Ding, professor in the Department of Industrial and Systems Engineering, College of Engineering, is the principal investigator of the team.

Co-principal investigators are Satish Bukkapatnam, professor, also in the Department of Industrial and Systems Engineering, and director of the Texas A&M Engineering Experiment Station’s Institute for Manufacturing Systems; Xia “Ben” Hu, assistant professor, Department of Computer Science, College of Engineering; and Raymundo Arroyave, professor, Department of Materials Science and Engineering, which is jointly operated by the colleges of engineering and science.

“Once the machine is able to data mine past literature of the design space, its knowledge base will surpass that of a group of industry experts,” said Hu. “This will enhance the artificial intelligence decision making function of the software brain.”

His work in data mining began four years ago when he began researching automated machine learning to replicate human efforts in a task.

The autonomous experimental testbed could have significant impacts on engineering practice and revolutionize the material discovery and advanced manufacturing landscape.

This interdisciplinary effort is a result of a President’s Excellence Fund program, X-Grants, which are designed to bring faculty together across disciplines and emphasize sustainable research excellence.