University of Twente Student Theses


Automatic Inference of Fault Trees using Reinforcement Learning

Gilbers, Jander (2022) Automatic Inference of Fault Trees using Reinforcement Learning.

[img] PDF
Abstract:Fault Tree analysis is a widely used method for dependability evaluation of systems. Fault Trees (FTs) are graphical representations of a system that show how failures of individual parts of a system can cause system failure. To avoid the costly and error-prone manual creation of FTs by human experts, we present the algorithm FT-RL. FT-RL uses Reinforcement Learning (RL) to automatically infer FTs from data. In this theses, we present how FT inference can be formulated as a RL problem, and show that while this method is effective, it is currently not better than the existing state-of-the-art methods. We show where the problems with FT-RL lie and how they may be improved in the future.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science MSc (60300)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page