Term of Award

Spring 2012

Degree Name

Master of Science in Applied Engineering (M.S.A.E.)

Document Type and Release Option

Thesis (open access)

Copyright Statement / License for Reuse

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


Department of Mechanical Engineering

Committee Chair

Brain L. Vlcek

Committee Member 1

David Williams

Committee Member 2

Anoop Desai


Author's abstract: In the area of reliability engineering it is necessary to be confident that a component or system of components will not fail under use for safety and cost reasons. One major mechanism of failure to a mechanical component is fatigue. This is the repetitious motion of loading and unloading of the material, typically below the ultimate tensile strength of the material, which ultimately leads to a catastrophic failure. To ensure this does not happen, engineers design components based on tests to determine the life of these components. These tests are typically conducted on a bench type tester in which a sample it subjected to tension and compression, or supported in a rotational machine in which a load is applied to one end to simulate constant bending. The results from these tests tell how long it is predicted that the part will last. This data however is not always complete. It sometimes happens that not every specimen tested actually makes it to failure; the un-failed specimens are known as suspensions. This can occur for numerous reasons. Methods currently exist for handling suspensions; however these methods require tedious hand calculations and interpolations from multiple graphs which are limited in availability. Presented here are five methods utilizing the Monte Carlo technique in a computer simulation based on Weibull-Johnson confidence numbers that take into account suspensions. This simulation allows for data from an existing experiment to be used as inputs and either validate the findings or bring attention for more testing. The model allows for two different data sets containing suspensions to be analyzed and determine with statistical confidence whether or not there is a difference between the two populations.

Research Data and Supplementary Material