Browse Prior Art Database

Stress Test Scenario Assessment Process

IP.com Disclosure Number: IPCOM000034260D
Original Publication Date: 1989-Jan-01
Included in the Prior Art Database: 2005-Jan-27
Document File: 3 page(s) / 28K

Publishing Venue

IBM

Related People

Breyfogle, FW: AUTHOR

Abstract

The process described is useful to determine a worst-case machine stress scenario for failure risk assessment of a product design. This test scenario can also be used to reduce the number of test requirements for future control chart evaluations of stress tests. This process utilizes non-parametric statistical techniques to uniquely address the highest exposed area by determining a worst-case scenario even when the given scenario inputs are considerably different. The input data has an example input form shown in the figure. The initial step is to determine which cell (scenario) has the highest risk of failure. Next, an on-going test sample size is determined. Then, a control chart strategy is used to test for process degradation.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 58% of the total text.

Page 1 of 3

Stress Test Scenario Assessment Process

The process described is useful to determine a worst-case machine stress scenario for failure risk assessment of a product design. This test scenario can also be used to reduce the number of test requirements for future control chart evaluations of stress tests. This process utilizes non-parametric statistical techniques to uniquely address the highest exposed area by determining a worst-case scenario even when the given scenario inputs are considerably different. The input data has an example input form shown in the figure. The initial step is to determine which cell (scenario) has the highest risk of failure. Next, an on-going test sample size is determined. Then, a control chart strategy is used to test for process degradation. The solution process described involves non-parametric statistical techniques on percentage values outside tolerance limits. This non- parametric statistical test strategy was developed since no statistical distribution assumptions are needed and some machine scenarios stress levels need termination before failures occur. In determining "high risk" scenarios, the following sub steps are employed. 1. Calculate the percentage value outside the tolerance limit for

each failed system. If the system did not fail

before the

maximum stress was given, the percentage value is

assigned a

very high value. This value is arbitrary but must

be

consistent within an experimental matrix.

2. Rank the percentage values. Tie percentage values are given a

ranking values equal to the average of the rankings

allotted

that group of ties.

3. Calculate the average of the rankings for each test scenario.

4. Rank the average of the scenario rankings to determine which

has the lowest average value. The lowest average

value has

the highest risk of failure...