Neural Network Models of Simple Mechanical Systems Illustrating the Feasibility of Accelerated Life Testing

TITLE AND SUBTITLE:
Neural Network Models of Simple Mechanical Systems Illustrating the Feasibility of Accelerated Life Testing

AUTHOR(S):
Steven P. Jones, Ralph Jansen, and Robert L. Fusaro

REPORT DATE:
May 1996

FUNDING NUMBERS:
WU-323-16-04

PERFORMING ORGANIZATION NAME(S) AND ADDRESS(ES):
National Aeronautics and Space Administration
Lewis Research Center
Cleveland, Ohio 44135-3191

PERFORMING ORGANIZATION REPORT NUMBER:
E-10008

SPONSORING/MONITORING AGENCY NAME(S) AND ADDRESS(ES):
National Aeronautics and Space Administration
Washington, D.C. 20546-0001

REPORT TYPE AND DATES COVERED:
Technical Memorandum

SPONSORING/MONITORING AGENCY REPORT NUMBER:
NASA TM-107108

SUPPLEMENTARY NOTES:
Prepared for the Annual Meeting sponsored by the Society of Tribologists and Lubrication Engineers, Cincinnati, Ohio, May 19-23, 1996. Steven P. Jones, Ohio Aerospace Institute, 22800 Cedar Point Road, Cleveland, Ohio 44142, current affiliation: National Research Council-NASA Research Associate at Phillips Laboratory, Propulsion Directorate, Carbon Materials Research Group, Edwards Air Force Base, California; Ralph Jansen, Ohio Aerospace Institute, 22800 Cedar Point Road, Cleveland, Ohio 44142; and Robert L. Fusaro, NASA Lewis Research Center. Responsible person, Robert L. Fusaro, organization code 5230, (216) 433-6080.

ABSTRACT:
A complete evaluation of the tribological characteristics of a given material/mechanical system is a time-consuming operation since the friction and wear process is extremely systems sensitive. As a result, experimental designs (i.e., Latin Square, Taguchi) have been implemented in an attempt to not only reduce the total number of experimental combinations needed to fully characterize a material/mechanical system, but also to acquire life data for a system without having to perform an actual life test. Unfortunately, these experimental designs still require a great deal of experimental testing and the output does not always produce meaningful information. In order to further reduce the amount of experimental testing required, this study employs a computer neural network model to investigate different material/mechanical systems. The work focuses on the modeling of the wear behavior, while showing the feasibility of using neural networks to predict life data. The model is capable of defining which input variables will influence the tribological behavior of the particular material/mechanical system being studied based on the specifications of the overall system.

SUBJECT TERMS:
Neural networks; Bearings; Life testing; Tribology; Expert systems; Wear devices;
Bench tests; Wear

NUMBER OF PAGES:
19

PDF NOT AVAILABLE VIA WEB:
Reports not available in PDF can be purchased from the Center for AeroSpace Information at:
http://www.sti.nasa.gov select Order Information

This page contains an Adobe® Acrobat® Reader PDF file. The PDF documents have been created to show thumbnails of each page. If the thumbnails do not display properly, download the file to the hard drive and view through Acrobat® Reader. You can download Acrobat® Reader for free.

A service of the NASA Glenn Research Center Logistics and Technical Information Division

Suggestions or questions about this site can be directed to:

NASA official: Technical Publications Manager, Sue.E.Butts@nasa.gov

Web curator: Caroline.A.Rist@grc.nasa.gov

Privacy Policy and Important Notices