Tribology Letters

, Volume 47, Issue 2, pp 211–221

Data-Driven Model for Estimation of Friction Coefficient Via Informatics Methods

  • Eric W. Bucholz
  • Chang Sun Kong
  • Kellon R. Marchman
  • W. Gregory Sawyer
  • Simon R. Phillpot
  • Susan B. Sinnott
  • Krishna Rajan
Original Paper

DOI: 10.1007/s11249-012-9975-y

Cite this article as:
Bucholz, E.W., Kong, C.S., Marchman, K.R. et al. Tribol Lett (2012) 47: 211. doi:10.1007/s11249-012-9975-y
  • 383 Downloads

Abstract

As technologies progress, the development of new mechanical systems demands the rapid determination of friction coefficients of materials. Data mining and materials informatics methods are used here 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. This data-driven model has a high degree of accuracy with an R2 value of 0.8904 and provides a range of possible friction coefficients that accounts for the possible variability of a material’s actual friction coefficient.

Keywords

CeramicsStatistical analysisTribology databasesUnlubricated friction

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  • Eric W. Bucholz
    • 1
  • Chang Sun Kong
    • 2
  • Kellon R. Marchman
    • 3
  • W. Gregory Sawyer
    • 3
  • Simon R. Phillpot
    • 1
  • Susan B. Sinnott
    • 1
  • Krishna Rajan
    • 2
  1. 1.Department of Materials Science and EngineeringUniversity of FloridaGainesvilleUSA
  2. 2.Department of Materials Science and EngineeringIowa State UniversityAmesUSA
  3. 3.Department of Mechanical and Aerospace EngineeringUniversity of FloridaGainesvilleUSA