|
A method for estimating upper and lower bounds of eigenvalues of closedloop systems with uncertain parameters |
Revised:December 09, 2002 |
View Full Text View/Add Comment Download reader |
DOI:10.7511/jslx20045094 |
KeyWord:three-parameter Weibull distribution,parameter estimation,probability weighted moments,fatigue life |
Deng Jian~* Gu Desheng Li Xibing |
|
Hits: 1198 |
Download times: 8 |
Abstract: |
Weibull distribution is a three-parameter distribution that contains normal, exponential and Rayleigh distribution as special cases. It is one of the most common and widely-used distribution in reliability theory, especially in fatigue life estimation. The goal of this paper is to use the method of probability weighted moments for estimating parameters and quantiles of fatigue life distribution (i.e. Weibull distribution) and to describe our MATLAB implementation of the method of probability weighted moments from field sample data. The relationship between sample probability weighted moments and the parameters of Weibull distribution was investigated. Two examples were presented to illustrate the applicability of the method. The results obtained from probability weighted moments were compared with the actual parameters by the method of Monte-Carlo method and with the results obtained by the method of Mean Rank Fitting and the method of Correlation Coefficient. It was demonstrated that the parameters estimated by the method of probability weighted moments are accurate enough to be used in reliability analysis. |