Performance, cost, and risk
What are the performance, cost, and risk impacts of implementing this product?
- Performance: Automatically generate Failure Trees for an analyzed system, which can then be used for improved decision-making (e.g., 3.4, 4.2).
- Cost: Although the product is more computationally efficient than others, scalability can be improved. Calculation of the FT is still computationally costly for large datasets.
- Risk: Noise data is not currently handled by the model, which may cause issues if used in a scenario with noisy data.
Implementation requirements
What capabilities would a business/organization/institution need to have to implement this product?
- Processes: Data acquisition and management.
- Resources: Dataset of both individual item failures and system states for the analyzed system.
- Competences: Extensive knowledge of the input data to transform it into a format that the FT models can use.
- Technologies: Python and MATLAB.
Related works
- Jimenez-Roa (2021). Fault Trees, Decision Trees, and Binary Decision Diagrams: A Systematic Comparison.
- Jimenez-Roa, Heskes, Tinga, and Stoelinga (2022). Automatic Inference of Fault Tree Models Via Multi-Objective Evolutionary Algorithms.
- Jimenez-Roa, Volk, and Stoelinga (2022). Data-Driven Inference of Fault Tree Models Exploiting Symmetry and Modularization.
- Jimenez-Roa, Rusnac, Volk, and Stoelinga (2024). Fault Tree Inference Using Multi-objective Evolutionary Algorithms and Confusion Matrix-Based Metrics.
Contact information
For further inquiries regarding this product, feel free to get in touch with:
- Tom Heskes, Radboud Universiteit. tom [dot] heskes [at] ru [dot] nl
- Mariëlle Stoelinga, University of Twente. m [dot] i [dot] a [dot] stoelinga [at] utwente [dot] nl
- Tiedo Tinga, University of Twente. t [dot] tinga [at] utwente [dot] nl
- Matthias Volk, Eindhoven University of Technology. m [dot] volk [at] tue [dot] nl
