Module 4 Estimation of Reliability Metrics

Lesson M04-04

Duration: 8 minutes

This exercise in this lesson gives you an opportunity to analyze a dataset and estimate some specified reliability statistics.  You also are asked to perform a sensitivity analysis be using an alternate model and compare the results. 

Module 4 Estimation of Reliability Metrics

Lesson M04-03

Duration: 46 minutes

In this lesson, we walk through a complete example (in Reliasoft) of estimating reliability metrics using models found via probability plotting.  We learn how to specify the model, how to obtain specific estimates for reliability statistics (including confidence intervals/bounds), and how to obtain the desired graphical output. 

Reliability Reference Textbook – Section 6, Pages 7-11

Module 4 Estimation of Reliability Metrics

Lesson M04-02

Duration: 16 minutes

Most reliability targets specify a confidence level that must be achieved in order to meet the target.  Here, we review what confidence intervals/bounds are and how they are used to when estimating reliability metrics.  We also discuss factors (like sample size) that affect the precision of the estimates.    

Reliability Reference Textbook – Section 6, Pages 5-6

Module 4 Estimation of Reliability Metrics

Lesson M04-01

Duration: 25 minutes

In this lesson, we introduce the key steps for estimating reliability metrics.  We also take a look at options for estimating the parameters of the chosen time-to-failure distribution.  Two main methods (that most software programs provide) are discussed conceptually (Maximum Likelihood Estimation and Rank Regression).  Recommendations for choosing a method are also provided.  

Reliability Reference Textbook – Section 6, Pages 1-4

Module 3 Assessing & Selecting Models

Lesson M03-07

Duration: 24 minutes

Following the exercise related to multiple failure modes, we discuss some other considerations for selecting distributions.

Module 3 Assessing & Selecting Models

Lesson M03-06

Duration: 41 minutes

When our dataset includes failures from more than one failure mode, it’s generally useful to select individual models for each failure mode and then combine the results to calculate the overall reliability.  In this lesson, we illustrate the process to fit models by failure mode.  We need to apply the concept of “competing risk” and appropriately right-censor the data at failure times for failure modes other than the one we are fitting the model for. 

Reliability Reference Textbook – Section 5, Pages 16-17

Module 3 Assessing & Selecting Models

Lesson M03-05

Duration: 18 minutes

Here, you have an opportunity to practice using Reliasoft to produce probability plots to a couple of datasets and interpret the results. 

Module 3 Assessing & Selecting Models

Lesson M03-04

Duration: 3 minutes

In this lesson, we simply extend the distribution fitting demonstration in Minitab to include right-censored data.  

Module 3 Assessing & Selecting Models

Lesson M03-03

Duration: 14 minutes

Now that we are familiar with the purpose and interpretation of probability plots, we dig a bit deeper to understand why and how they actually work.  Through an example, we see that the probability plot is simply a transformed (linearized) cumulative failure probability function that allows us to view significant departures of the data from an assumed model.  We also look how probability plots may be constructed without the use of statistical software.  

Reliability Reference Textbook – Section 5, Pages 5-15

Module 3 Assessing & Selecting Models

Lesson M03-02

Duration: 37 minutes

Next, we illustrate the use of Reliasoft software for constructing and interpreting probability plots.  

Module 3 Assessing & Selecting Models

Lesson M03-01

Duration: 11 minutes

In this lesson, we introduce the approach for selecting models that adequately describe the time to failure data.  Models selected in this step will be subsequently used to estimate reliability metrics of interest.  A graphical tool (Probability Plot) for assessing model fit is introduced.  While some details of constructing probability plots are introduced, the emphasis will be on applying this tool to determine models which adequately describe the data. 

Reliability Reference Textbook – Section 5, Pages 1-4

Module 2 Probability & Reliability Statistics

Lesson M02-07

Duration: 31 minutes

When dealing with pass/fail outcomes or count data, discrete distributions are necessary.  In this lesson, we introduce the binomial distribution which models the probability of observing a specified numberfailures from a sample size, given an assumed failure probability.  In addition to directly supporting probability calculations involving inspection data, the concepts will be very useful in understanding system probability calculations later in the course.  The Poisson distribution is also covered as it’s often useful in modeling the number of defects (where a particular unit may have more than 1 defect).  

Reliability Reference Textbook – Section 3, Pages 30-40

Module 2 Probability & Reliability Statistics

Lesson M02-06

Duration: 15 minutes

Successful completion of these exercises indicates you have a good grasp of the various reliability metrics and how they are related to the probability density function.  The exercises also cover the basic probability distributions and how they play a part in estimating reliability statistics.  

Module 2 Probability & Reliability Statistics

Lesson M02-05

Duration: 11 minutes

Here, we revisit conditional probability as applied to reliability estimation.  We present an example when burn-in is used to weed out defective units.  As illustrated in the example, burn-in is only effective when we are trying to strengthen a population that is subject to infant mortality failures.   

Reliability Reference Textbook – Section 3, Pages 41-46

Module 2 Probability & Reliability Statistics

Lesson M02-04

Duration: 46 minutes

When analyzing non-repairable systems or components, we typically find probability distributions that best describe/fit the available time-to-failure data.  This lesson introduces some of the common models (distributions) used in practice.  Although the Weibull model is emphasized somewhat due to its popularity and convenient properties, we should also consider alternate models when estimating reliability statistics.  

Reliability Reference Textbook – Section 3, Pages 13-29