Direkt zum Inhalt springen
login.png Login join.png Register    |
de | en
MyTUM-Portal
Technical University of Munich

Technical University of Munich

up   Back to  News Board    previous   Browse in News  next    

Analyzing technical reliability using step-stress accelerated life tests

Master Thesis in Mathematical Statistics

03.11.2021, Diplomarbeiten, Bachelor- und Masterarbeiten

In this Master thesis, your aim is to develop an extension of a two-stage step-stress model and derive inference methods for the unknown parameters of the new model. You will then also implement the whole approach in the R programming language. In the end you will write an R package containing the code you developed.

Background
When safeguarding electrical and electronic components with regard to service life and reliability, the effects of various environmental factors must be
analyzed. These include in particular thermal, mechanical and electrical influencing variables as well as humidity.
In order for test knowledge to be taken into account in development without jeopardizing a project start, the test duration plays a decisive role. For this reason, a so-called "step-stress method" is to be used to reduce the test time, in which the load is increased step by step.

Task
In this Master thesis, your aim is to develop an extension of the two-stage step-stress model of Wang et al. (2012) and derive inference methods for the unknown parameters of the new model. You will then also implement the whole approach in the R programming language. In the end you will write an R pack-age containing the code you developed.


Required Skills
• Strong statistics background (recommended courses: Fundamentals of Mathematical Statistics, GLM)
• Good knowledge about programming in R, preferably also experience in writing R packages

Industry partner
You will gain insights into the industry from the very beginning and work at the company EVOMOTIV GmbH.
EVOMOTIV is an engineering company in the automotive and aerospace sec-tors, with a focus on development, testing and project management.

References
[1] Balakrishnan, N. and Cramer E. (2014). The Art of Progressive Censoring. Springer
[2] Wang, F. K., Wang, Y. F. and Lu, W. L. (2012). Partially Accelerated Life Tests for the Weibull Distribution Under Multiply Censored Data. Communications in Statistics – Simulation and Computation, 41: 1667-1678.

Kontakt: haug@tum.de

Todays events

no events today.

Calendar of events