University of Twente Student Theses
Improving the Performance of Multi-Objective Evolutionary Algorithms for Fault Tree Inference
Rusnac, Nicolae (2023) Improving the Performance of Multi-Objective Evolutionary Algorithms for Fault Tree Inference.
|
PDF
3MB |
| Abstract: | Fault trees (FTs) are models frequently used in risk management to identify potential failures and improve a system’s reliability. They are typically created manually in consultation with domain experts, which is time-consuming and prone to human error. Existing multi-objective evolutionary algorithms optimise this process by using failure data sets generated by a system for inferring a FT. These algorithms are known to be inefficient and, in some cases unable to find an optimal solution. In this research, the focus has been placed on identifying better metrics for the existing genetic algorithm. Multiple metrics were identified and analyzed such as random segmentation accuracy, basic event impact vector distance and confusion matrix metrics. The results show that by adding metrics from the confusion matrix, significant improvements can be achieved in both the convergence time of the algorithm and the number of generations it takes to converge. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Awards: | Best paper award |
| Link to this item: | https://purl.utwente.nl/essays/96004 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page