Title :
Estimating the cumulative probability of failure data points to be plotted on Weibull and other probability paper
Author :
Fothergill, J.C.
Author_Institution :
Dept. of Eng., Leicester Univ., UK
fDate :
6/1/1990 12:00:00 AM
Abstract :
Using both an exact technique and Monte Carlo simulations to estimate the cumulative probability of failure of the ith of n identically stressed samples, it is shown that the approximation F(i,n)=(i-0.3)/(n +0.4) is considerably more accurate than other commonly used approximations. The significance of this in the interpretation of electrical breakdown tests is demonstrated
Keywords :
Monte Carlo methods; electric breakdown; failure analysis; insulation testing; probability; Monte Carlo simulations; Weibull; cumulative probability; electrical breakdown tests; failure data points; identically stressed samples; probability paper; Data engineering; Dielectrics and electrical insulation; Electric breakdown; Equations; Helium; Insulation testing; Maximum likelihood estimation; Parameter estimation; Random number generation; Voltage;
Journal_Title :
Electrical Insulation, IEEE Transactions on
