Workshop 04: Component Reliability Analysis

Workshop 04: Component Reliability Analysis#

This workshop was assigned on GitHub, and can be accessed via this link. This workshop was not submitted for a grade/feedback.

Instructions for the assignment are provided below (based on the README.md file from the repository).

The solution is provided here in the following three sub-pages, and is a subset of what was included in the repository:

  • Report: the Markdown report with questions about the analysis

  • Analysis: the Jupyter notebook where calculations were made (includes additional explanation)

Instructions (README.md)#

The purpose of this assignment is to illustrate two commonly used algorithms for finding the failure probability of a component (component reliability problem).

Context

This workshop will apply component reliability analysis to an equation describing stability of a beam. The context to keep in mind is that you are responsible for designing the beam to withstand a specific loading situation; the challenge is that several aspects of the problem are uncertain (the random variables). Fortunately someone has already prepared several key ingredients for you: the random variables, multivariate distribution and limit-state function. Your job is to carry out the analysis for finding failure probability.

Instructions:

  • work through the notebook Analysis.ipynb

  • answer the questions in the file Report.md

  • commit your files back to the repository

Even though you do not have to turn in this assignment (see below), we recommend you add answers to the Report.md so you can refer back to this in the future, or to collaborate with your group members.

To complete this assignment you will need the following packages: numpy, matplotlib, scipy and openturns. Remember to activate it before starting your Jupyter session (e.g., conda activate mude).

If you are creating Python virtual environments (as presented in week 3), the key steps are summarized on the unit website.

Grading#

This assignment is not graded; you do not have to turn it in. However, we recommend you clone the repository and push your changes back to GitHub to save and track your work; especially if you are working with other students. In addition, if you need to contact Robert for help outside of class, you should include the URL link to your repository in an email.

Contents