The rapid development of new mechanical assemblies capable of operating in extreme conditions requires the rapid determination/estimation of friction. Often, during the design phase, materials friction coefficients are unknown. Here, data mining and materials informatics methods are used to generate a predictive model that enables efficient high-throughput screening of ceramic materials, some of which are candidate high-temperature solid-state lubricants. Through the combination of principal component analysis and recursive partitioning using a small dataset comprised of intrinsic material properties, we develop a decision tree based model comprised of if-then rules, which estimates the friction coefficients of a wide range of materials derived from the interrelationships between the intrinsic material properties. This predictive model lays the foundation for new studies in predictive modeling and tailoring materials with specific tribological characteristics. It is applied to predict the tribological performance of a range of different materials.

This work is supported by the Office of Naval Research.