The use of fuzzy mathematics in subjective uncertainty analysis
We have been investigating the applicability of fuzzy mathematics in safety assessments (PSAs). It is a very efficient approach, both in terms of methodology development time and program execution time. Most importantly, it processes subjective information subjectively, not as if it were based on measured data. One of the most useful results of this work is that we have shown the potential for significant differences (especially in perceived margin relative to a decision threshold) between fuzzy mathematics analysis and conventional PSA analysis. This difference is due to subtle factors inherent in the choice of probability distributions for modeling uncertainty. Since subjective uncertainty, stochastic variability, and dependence are all parts of most practical situations, a technique has been developed for combining the three effects. The methodology is based on hybrid numbers and on Frechet inequality dependency bounds analysis. Some new results have also been obtained in the areas of efficient disjoint set representations and constrained uncertainty and variability analysis.
- Research Organization:
- Sandia National Labs., Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- AC04-94AL85000
- OSTI ID:
- 240470
- Report Number(s):
- SAND--96-1137C; CONF-9606114--9; ON: DE96010554
- Country of Publication:
- United States
- Language:
- English
Similar Records
Hybrid processing of stochastic and subjective uncertainty data
Theoretical description of methodology in PHASER (Probabilistic hybrid analytical system evaluation routine)