Module 11 Introduction

Lesson M11-00

So far in this course we have been dealing with non-repairable systems where we model the time to the (first) failure.  Repairable systems analysis is concerned with understanding and modeling the time between failures (over time).  The terminology and models are different than the non-repairable case.  In this module we provide an overview of analysis of repairable systems.  

Reliability Reference Textbook – Section 11

Module 10 Introduction

Lesson M10-00

Duration: 3 minutes

This module covers modeling for summarized data resulting from pass/fail (binary) assessments.  That is, the unit either fails or doesn’t fail when exposed to some stress for a specified period of time.  In these problems similar methods are used, but often the probability of survival or failure is estimated as a function of stress level rather than time.  

Module 9 Introduction

Lesson M09-00

Duration: 5 minutes

This module introduces a method of quantifying risk by calculating failure probabilities based on a characterization of a stress distribution and a strength distribution.  A failure occurs when a unit randomly encounters a stress that exceeds its inherent strength.  The theory for normally distributed distributions is discussed and an example is worked through.  We also discuss the option of using simulation to estimate failure probabilities as well as Reliasoft software. This is especially useful when either the stress or strength distribution is not well described by the normal model.

Module 8 Introduction

Lesson M08-00

Duration: 8 minutes

This module covers the planning and analysis of Accelerated Life Tests (ALT).  ALT is a useful methodology for obtaining failure information in less time than it takes for tests performed at normal use conditions.  Quantitative ALTs allow the estimation of reliability statistics at normal use conditions based on failures observed at various stress conditions.  While more complex than regular reliability tests, they can yield useful information in significantly less time.  

Module 7 Introduction

Lesson M07-00

Duration: 6 minutes

Reliability testing is a key component for ensuring that Reliability targets are achieved.  Planning for reliability tests is important to ensure that the results are likely to be useful.  In this module, we look at planning for both reliability estimation tests and reliability demonstration tests.  Essentially, we must test enough units for long enough to be able to adequately estimate reliability or demonstrate that targets are met.

Module 6 Introduction

Lesson M06-00

Duration: 6 minutes

Reliability Reference Textbook – Section 13, Pages 2-11

The models developed to analyze time-to-failure data may be used to develop forecasts of the number of failures that may be expected over time.  This is useful for estimating warranty costs, estimating spare part requirements, and reacting to emerging field concerns.  In this module, we learn how to use conditional failure probability to predict the number of failures during the forecast period. 

Module 5 Introduction

Lesson M05-00

Duration: 8 minutes

Reliability Reference Textbook – Section 4

In Module 5, we extend the estimation of component reliability to the reliability estimation of a system composed of multiple components.  The system reliability depends both on the component reliabilities as well as their configuration.  Redundant components allow the system reliability to achieve levels that exceed the component reliabilities.  We explore the basic series and parallel structures as well as k-out-of-n parallel systems.  We also introduce more complex systems and various aspects of system reliability including reliability importance and reliability allocation.

Module 4 Introduction

Lesson M04-00

Duration: 5 minutes

Reliability Reference Textbook – Sections 6,7

This module is the core of life data analysis.  We start by providing an overview of the common methods for estimating the distribution parameters (e.g. Maximum Likelihood Estimation) and provide guidance for choosing a method.  Since quantifying uncertainty in our estimates is critical, we review the use of confidence intervals (or bounds) for this purpose.  Applying the concepts introduced previously, we learn how to utilize selected distributions to estimate reliability statistics of interest.  Treatment of censored data and multiple failure modes follow.  We also look at comparing multiple groups with respect to overall reliability performance.  Finally, we briefly look at nonparametric estimation which does not require any distribution assumption.  

Module 3 Introduction

Lesson M03-00

Duration: 6 minutes

Reliability Reference Textbook – Section 5

Module 3 focuses on how we determine appropriate models for describing the time-to-failure data.  We introduce Probability plots and goodness-of-fit statistics that assist in determining which distributions may provide a good fit to the data.  We also learn how to handle censoring and multiple failure modes when attempting to find reasonable models for the data.