 |
Related Topics: |  |
 |
 |
|
 |
 |
 |
This topic provides a brief overview of the major analysis, data management and reporting capabilities provided by RGA.
You can also review an introduction to the Synthesis Platform and a list of what's new in the Synthesis version.
ReliaSoft's RGA is a powerful software tool that allows you to apply reliability growth models to analyze data from both developmental testing and fielded repairable systems.
In the development stage, RGA allows you to quantify the reliability growth achieved with each successive design prototype and also supports advanced methods for reliability growth projections, planning and management.
For systems operating in the field, RGA uses the NHPP model (and the assumption of minimal repair) to calculate optimum overhaul times and other results without the detailed data sets that normally would be required for repairable system analysis.
RGA provides a comprehensive array of analysis options for situations when it is appropriate to assume that all permanent design improvements are applied by the end of the test (test-fix-test). To accommodate the wide variety of potential test/data collection scenarios, the software supports a flexible selection of data types, growth models and calculated analysis results. This includes:
When you have data from developmental testing in which the systems were operated continuously until failure, you can use the Crow-AMSAA (NHPP) or Duane models.
RGA provides a choice of data types for individual or grouped failure times, and also for combining data from multiple identical systems. This can include situations where:
All systems operate concurrently so the operating time of each non-failed system is the same as the time recorded for the failed system.
You have recorded the exact operating times for both the failed and non-failed systems.
You have recorded the calendar date for each failure so the software can estimate the operating times of the non-failed systems based on the average daily usage rate for the relevant time period.
When you have data from one-shot (pass/fail) reliability growth tests, you can use the Crow-AMSAA (NHPP), Duane, Standard Gompertz, Modified Gompertz, Lloyd-Lipow or Logistic models.
For discrete data, RGA provides a choice of data types that can handle tests in which a single trial is performed for each design configuration, multiple trials per configuration, or a combination of both. RGA also supports failure discounting if you have recorded the specific failure modes from sequential one-shot tests.
When you simply wish to analyze the calculated reliability values for different times/stages within developmental testing, you can use the Standard Gompertz, Modified Gompertz, Lloyd-Lipow or Logistic models.
With the Crow-AMSAA (NHPP) model, RGA offers some additional analysis options that may be appropriate in certain situations.
If you believe that some portion of the data is erroneous or missing, the Gap Analysis feature allows you to retain the gap interval’s contribution to the total test time without making assumptions about the actual number of failures during that time period.
If a major change in the system design or operational environment has caused a significant change in the failure intensity observed during testing, a single model may not provide a good fit for the data. In such cases, you can use the Change of Slope feature to split the data into two segments and apply a separate Crow-AMSAA (NHPP) model to each segment.
For traditional reliability growth analysis (and depending on the data type and RGA model), you will be able to:
Calculate the MTBF, failure intensity or reliability for a given time/stage.
Determine the amount of testing that will be required to demonstrate a specified MTBF, failure intensity or reliability.
Estimate the expected number of failures for a given time/stage.
An effective reliability growth test planning and management strategy can contribute greatly to your organization’s ability to meet desired reliability goals on time and within the project budget. RGA provides exclusive support for several innovative reliability growth projections and planning methods based on the Crow Extended and Crow Extended – Continuous Evaluation models.
Although traditional reliability growth analysis requires the assumption that all design improvements are incorporated before the end of the test (test-fix-test), many real-world testing scenarios may also include some failure modes that are not fixed, and others where some or all of the fixes are delayed until a later time (test-fix-find-test or test-find-test). With the Crow Extended and Crow Extended – Continuous Evaluation models, you can use Failure Mode Classifications to provide the appropriate analysis treatment for any of these management strategies.
A indicates that no fix will be applied (i.e., management chooses not to address the failure mode because of technical, financial or other reasons).
BC indicates that a fix was applied at any time during the test (Crow Extended) or immediately after the failure and before testing continues (Crow Extended – Continuous Evaluation).
BD indicates that the fix will be delayed until after the completion of the test (Crow Extended) or until some later time in the same test phase, between test phases, in a subsequent test phase or after the last test phase (Crow Extended – Continuous Evaluation).
For delayed fixes, both models use Effectiveness Factors to indicate how much the failure intensity of each mode will be reduced once the fix has been implemented (e.g., EF=.7 indicates that 70% of the failure intensity from the mode is expected to be removed while 30% will remain).
Analysis with the Crow Extended or Crow Extended – Continuous Evaluation model makes it possible to calculate and plot some additional projections and calculated metrics that are useful for managing your reliability testing program, such as:
Projected MTBF (or Failure Intensity) - the reliability that will be achieved after delayed fixes have been implemented.
Growth Potential MTBF (or Failure Intensity) - the best reliability that could be achieved by applying the current reliability growth management strategy. If this metric indicates that your goal cannot be achieved with the current level of testing and fixing, you may be able to adjust the strategy.
MTBF BD Unseen - the rate at which new unique BD failure modes are being discovered at any given time.
Cumulative Number of BD Modes - the total number of unique observed BD failure modes at any given time.
RGA’s growth planning folio has been redesigned in the Synthesis version. You still have the ability to calculate any of the variables in the reliability growth management strategy (such as the MTBF goal that’s feasible for a given management strategy, or the initial MTBF that’s needed before you start the test program), and quickly generate a graphical plot that shows how the idealized growth curves are planned to improve over each test phase. The new interface now makes it easier to view and make adjustments to your inputs to find the most effective reliability growth testing plan.
While the Crow Extended model facilitates reliability growth projections, planning and analysis for a single test phase, the Crow Extended – Continuous Evaluation model is designed for analyzing data across multiple test phases. Specially designed multi-phase data sheets allow you to enter the data from all test phases into the same data sheet and use Event Codes to specify the end time for each phase (PH). You can also use these event codes to specify:
The exact time when a delayed fix was implemented (I).
Failures due to performance (P) or quality (Q) issues, which can be excluded from the analysis, if desired.
Specific analysis points (AP) at which to calculate the MTBF/failure intensity in order to show the progress in multi-phase plots.
Any data point you wish to exclude from the analysis (X).
The multi-phase plot displays key analysis results from data analyzed with the Crow Extended model or Crow Extended – Continuous Evaluation model so you can see how the demonstrated, projected and growth potential MTBF changes across multiple analysis points and/or test phases.
If desired, you can also link the plot to a growth planning folio so you can see how the actual test results compare to the plan, and determine if it’s necessary to make adjustments in subsequent test phases in order to meet your reliability growth goals.
During a development program, it is common practice for systems to be subjected to operational testing in order to evaluate the performance of the system under conditions that represent actual use. It is also common for reliability fixes to be implemented in conjunction with this testing and to perform reliability growth analysis on the data obtained. However, when the system must be tested for a variety of different mission profiles, it can be a challenge to make sure that the testing is applied in a balanced manner that will yield data suitable for reliability growth analysis. RGA's Mission Profile folios can help you to:
Create an operational test plan that effectively balances all of the mission profiles that need to be tested.
Track the expected vs. actual usage for all mission profiles and verify that the testing has been conducted in a manner that will yield data sets that are appropriate for reliability growth analysis.
If there are any significant variations from the test plan that could jeopardize the analysis results, RGA can automatically group the data at specified "convergence points" so the growth model can be applied appropriately.
Some of the models in RGA can be used to analyze data from repairable systems operating in the field under typical customer usage conditions. Such data might be obtained from a warranty system, repair depot, operational testing, etc.
Specifically, you can use the power law or Crow-AMSAA (NHPP) models for repairable system analysis based on the assumption of minimal repair (i.e., the system is “as bad as old” after each repair) to calculate metrics such as:
Optimum overhaul time for a given repair cost and overhaul cost.
Conditional reliability, MTBF or failure intensity for a given time.
Expected number of failures for a given time.
Time for a given conditional reliability, MTBF or failure intensity.
While ReliaSoft’s Weibull++ software provides a test design utility with a choice of methods that are suitable to design a reliability demonstration test (e.g., "zero failure test") for non-repairable items, the test design utility in RGA has been designed specifically for repairable systems. Redesigned in the Synthesis version, this tool uses the NHPP model to determine the test time required per system (or the number of systems that must be tested) in order to demonstrate a specified reliability goal (defined in terms of MTBF or failure intensity at a given time).
RGA makes it easy to create a complete array of plots and charts to present analysis information graphically. The Plot Setup allows you to completely customize the "look and feel" of plot graphics while the RS Draw metafile graphics editor provides the option to insert text, draw objects or mark particular points on plot graphics. You can save your plots in a variety of graphic file formats (*.jpg, *.gif, *.png or *.wmf) for use in other documents.
Overlay Plots (formerly called "MultiPlots") allow you to plot the results from multiple data sets together in the same plot. This can be an effective visual tool for comparing different data sets or analysis methods.
The Side-by-Side Plots utility allows you to view (and print) multiple plots for a given data set side-by-side. For example, you may want to show the cumulative number of failures, MTBF vs. time and failure intensity vs. time plots for a given analysis together in the same window. Alternatively, you may wish to compare the MTBF vs. time plots for a given data set when analyzed with different RGA models.
RGA provides the option to use Monte Carlo simulation for generating data sets that can be analyzed directly in a standard folio. You can also use the SimuMatic® utility to automatically analyze a large number of data sets that have been created via simulation. These simulated data sets and calculated results can be used to perform a wide variety of reliability tasks, such as:
Designing reliability growth tests.
Obtaining simulation-based confidence bounds.
Experimenting with the influences of sample sizes and data types on analysis methods.
Evaluating the impact of allocated test time.
Like all Synthesis applications, RGA offers several powerful tools for custom analysis and reporting.
If you need a quick way to perform additional calculations that are associated with a particular analysis, you can insert any number of General Spreadsheets into any RGA standard folio.
If you want to create a custom analysis or report that integrates results from different analysis folios, you now have the choice to use an Analysis Workbook (with functionality similar to Microsoft Excel®) or a new Word Report Template (with functionality similar to Microsoft Word®).
All three tools allow you to use the Function Wizard to automatically insert calculated results based on selected data sheets. With the workbooks and report templates, you also have the option to configure the functions to use generically numbered "data sources" instead of named data sheets. This makes it easy to use the same template again for different data sets.
The Quick Statistical Reference frees you from tedious lookups in tables by quickly returning results for commonly used statistical functions. Results include Median Ranks, Chi-Squared Values, Cumulative Binomial Probability, and many more. There is also a Polynomial Interpolation Function that allows you to enter known data points and then calculate Y for any given X value.
© 1992-2015. ReliaSoft Corporation. ALL RIGHTS RESERVED.