Browse Prior Art Database

Method to Calculate InterConnect System Reliability Failure Rate Using Statistical Software Packages.

IP.com Disclosure Number: IPCOM000240652D
Publication Date: 2015-Feb-16
Document File: 3 page(s) / 269K

Publishing Venue

The IP.com Prior Art Database

Abstract

A method utilizing any statistical software package to calculate interconnect system reliability failure rate is described.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 57% of the total text.

Page 01 of 3

Method to Calculate InterConnect System Reliability Failure Rate Using Statistical Software Packages.

Abstract:

A method utilizing any statistical software package to calculate interconnect system reliability failure rate is described.

Introduction:

Currently there are other methods to calculate failure rate, they tend to fit or transform data into one preselected distribution. That result in much larger sample size needed, a minimum of 1000 datapoints is considered in the current methods, and that preselected distribution may not be the best fit for every set of data.

This method utilizes any statistical analysis software package to identify the best fit distribution to the data set, that best fit distribution is then used to estimate the probability of data above a limit specs. The estimate probability is then fitted into the failure rate formula to calculate failure rate.

Since there is no transform data, smaller sample size, minimum of 400 is considered reasonable for the calculation. And in addition, since the best fit is used, the result found to be represents the characteristic data set better.

Failure Rate Calculation:


1. Failure Rate Formula:

  6 10

FR LIFE

FIELD

Where:
10^6 x IFR: Probability of failure per million. Or the numbers of data points estimated greater than upper specs limit per one million data points

Field Life: Ten Years = 10 x 365 x 24 / 1000 = 87.60

Seven Years = 7 x 365 x 24 / 1000 = 61.32

Five Years = 5 x 365 x 24 / 1000 = 43.80


2. Collect test data, normally maximum delta LLCR's from the environment test sequence is obtained.


3. Use Minitab or other statistical software packages to find the best fit distribution. For this particular example, Minitab16 is used. Minitab16 can idendity up to 16 different distributions depend on data type, review normal charts and/or look for minimum AD...