General information |
Description |
We assume that user is familiar with the methodology. The purpose of the following is just to provide some information about capabilities
and limitation on the calculation methods. More detailed description of applied techniques can be found in [1].
Rank Regression method |
Parameter a=0.3 yields Benard’s formula, a=0.5 corresponds to Hazen’s approximation. The case a=0 corresponds to the mean ranking. We also use the rank adjustment method for right censored (suspension) data which is based on the Mean Order Number (MON) and is used in the above formula instead of i. It is given by recurrent formula |
Increment Ii is calculated as |
where ri is the total number of items beyond the current suspended set.
For the given data points we calculate parameters of the selected for Weibull prediction probability distribution function minimizing the distance from given points to points corresponding to the probability function (residual sum). If it is done with respect to probability, it is the regression on Y. If the criterion is time, it is regression on X. For the Weibull, Normal, Log-Normal function the solution is exact and simple. The main disadvantage of the regression method is the accuracy of converting failure and suspension times to Unreliability. Maximum Likelihood Estimator Confidence bounds
[1] O’Connor, Patrick D T. and Kleyner, Andre. Practical Reliability Engineering, 5th Edition. Chichester: Wiley, 2012, 512pp. |