Reliability HotWire: eMagazine for the Reliability Professional
Reliability HotWire

Issue 54, August 2005

Tool Tips

* How do I allocate a reliability goal across the components of a system in Lambda Predict?

The Allocations utility provides five allocation models that can be used to logically apportion the product design reliability into lower level design criteria such that the cumulative reliability still meets the requirements.

To open this utility, select a project or system in the Project or System panel and then select Allocation from the Tools menu.

The name of the selected project or system appears in the upper left corner of the utility. A page for each allocation model appears at the bottom of the utility. Click the page to use the corresponding model to determine the reliability requirements for each system associated with the selected project or each block associated with the selected system.

Chapter 11 in the Lambda Predict User's Guide provides more information on the Allocations utility and the individual allocation models.

* What goodness-of-fit statistical tests are available in RGA?

There are four goodness-of-fit tests which, depending on their applicability, will become available. The Cramr von Mises goodness-of-fit test tests the hypothesis that the data follows a nonhomogeneous Poisson process with failure intensity equal to u(t) = λβtβ−1. This test can be applied when the failure data is complete over the continuous interval [0, Tq] with no gaps in the data. The Chi-Squared test is a goodness-of-fit test that can be applied under more general circumstances, particularly when the data is grouped. In addition, the Common Beta Hypothesis test can also be used to compare the intensity functions of the individual systems by comparing the βqs of each system. Lastly, the Laplace Trend test checks for trends within the data.

The statistical tests that are available in RGA 6 will vary depending on the current data type and model. The following table shows the statistical tests that can be performed for each data type and model.

Please note that for multiple systems analysis, the Cramr von Mises (CVM) and Common Beta Hypothesis (CBH) statistical test results will only be available for systems that have a start time equal to 0. If a system does not have a start time equal to 0, then the results will not be available for the combined equivalent or superposition system results but will be available for any individual systems with start times equal to 0. In addition, for multiple systems analysis, the CBH statistical test requires that there are two or more individual systems.

If you right-click inside the Results Area, the Show Other shortcut menu will appear, which allows you to specify additional results to be displayed in the Results Area. The Statistical Tests This includes the Chi-Squared Goodness of Fit, Cramr von Mises, Laplace Trend and Common Beta Hypothesis test results. (The statistical test results will appear in the Results Panel instead of the Results Area.)

* Where can RENO examples and case studies be found?

From the Help menu in RENO, click on Open Example Folder. The examples are categorized by application area (e.g. Financial Analysis, Reliability, Risk Analysis, etc). The examples have attached Word documents that explain the example and the steps followed to create the model and perform the analysis. These documents can be accessed under Attachments in the Project Explorer.

There are also many case studies listed online at http://RENO.ReliaSoft.com/examples/index.htm.

Copyright 2005 ReliaSoft Corporation, ALL RIGHTS RESERVED