SRC Forum - Message Replies


Forum: Reliability & Maintainability Questions and Answers

Topic: Reliability & Maintainability Questions and Answers

Topic Posted by: Reliability & Maintainability Forum (src_forum@alionscience.com )
Organization: System Reliability Center
Date Posted: Mon Aug 31 12:47:36 US/Eastern 1998

Back to message list Show all replies Topics List About this forum
Original Message:

Posted by: Nicole
Date posted: Fri Nov 15 8:27:57 US/Eastern 2002
Subject: AMSAA or Observed MTBF??
Message:
I encountered a problem during my growth testing. After a period of 1500hrs of testing and i collected 4 failures. Should i use the AMSAA model to compute the results or simply divide the test duration by the number of observed failures? In this case i have only 4 failures so which method is more accurate? The AMSAA model passed the Goodness of Fit Test however. I understand taht AMSAA model is not too suitable when the number of failures are too small right? Please advised?


Reply:

Subject: Growth Testing
Reply Posted by: BWD (bdudley@alionscience.com )
Organization: RAC
Date Posted: Mon Nov 25 15:40:00 US/Eastern 2002
Message:
The more failures you have to work with the better the growth projection or lack of projection is as the case may be. The limited number of failures can still be ploted using the AMSSA model and the result can be used to indicate if there is positive growth. By mearly taking the hours and failures and performing a statistical analysis you have voided the growth effect or lack of growth effect.


Reply to this message