Scribd
Upload
1K views6 pages

Success Run Theorem

The document provides formulas and examples for calculating sample sizes needed to determine reliability. It gives equations for calculating sample size given reliability and confidence level, or for estimating reliability given a sample size and number of failures. Examples are shown for different reliability scenarios including binomial and Weibull distributions.

Uploaded by

Shriramkumar Singh
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as XLS, PDF, TXT or read online on Scribd
1K views6 pages

Success Run Theorem

The document provides formulas and examples for calculating sample sizes needed to determine reliability. It gives equations for calculating sample size given reliability and confidence level, or for estimating reliability given a sample size and number of failures. Examples are shown for different reliability scenarios including binomial and Weibull distributions.

Uploaded by

Shriramkumar Singh
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as XLS, PDF, TXT or read online on Scribd
You are on page 1/ 6

Succes Run Theorem

www.world-class-quality.com

Rc = reliability at some time x C = percent confidence ( 90% => C = 0.9 ) n = sample size Note : FPH = -100 ln (R)

Sample size calculation when reliability is given


Confidence Level "Cx100" Reliability "Rc" Sample Size -1+ln(1-C/100)/ln(Rc/100) 96 95 62

Reliability estimate when sample size is given


Confidence Level "Cx100" Reliability "Rc" Sample Size n (given) 89 0.72955 6

% %

% %

Sample Size with Binomial


(some failures expected)

Sample size calculation (Binomial)


www.world-class-quality.com

Confidence Level "Cx100" Reliability "Rx100" Number of Failures r Defects Per Hundred (DPH) (FPH = -100 ln (R)) Sample Size n

0.5 (2 1 C , 2( r 1)) 1 R

Reliability estimate when sample size is given


Confidence Level "Cx100" Sample Size n Number of Failures r Reliability (x100) Defects Per Hundred (DPH) (FPH = -100 ln (R))

R 1

0 .5 (2 1 C , 2 ( r 1)) n

90 99 1 1 389

% %

80 25 3 77.9 25

www.world-class-quality.com

n = - [2(1-C,2)] / [2 (k) ln(Rlower(t))]

1 2 3 4 5 6 7

Sample size calculation (Weibayes)


Rc = reliability at some time x C = percent confidence ( 90% => C = 0.9 ) n = sample size Note : FPH = -100 ln (R) Shape Parameter b Confidence Level "Cx100" Reliability "Rc" Reliability to be demonstrated at time t Test Length (T) Bogie Ratio k (T/t) Sample Size n

2 90 90 1 1.5 1.5 10

% % hrs/km/cycles hrs/km/cycles (same units)

You might also like