Comparison among Methods of Modeling Epistemic Uncertainty in Reliability Estimation
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Epistemic uncertainty, the lack of knowledge, is often more important than aleatory uncertainty, variability, in estimating reliability of a system. While the probability theory is widely used for modeling aleatory uncertainty, there is no dominant approach to model epistemic uncertainty. Different approaches have been developed to handle epistemic uncertainties using various theories, such as probability theory, fuzzy sets, evidence theory and possibility theory. However, since these methods are developed from different statistics theories, it is difficult to interpret the result from one method to the other. The goal of this paper is to compare different methods in handling epistemic uncertainty in the view point of calculating the probability of failure. In particular, four different methods are compared; the probability method, the combined distribution method, interval analysis method, and the evidence theory. Characteristics of individual methods are compared in the view point of reliability analysis.
Abstract
Epistemic uncertainty, the lack of knowledge, is often more important than aleatory uncertainty, variability, in estimating reliability of a system. While the probability theory is widely used for modeling aleatory uncertainty, there is no dominant approach to model epistemic uncertainty. Different approaches have been developed to handle epistemic uncertainties using various theories, such as probability theory, fuzzy sets, evidence theory and possibility theory. However, since these methods are developed from different statistics theories, it is difficult to interpret the result from one method to the other. The goal of this paper is to compare different methods in handling epistemic uncertainty in the view point of calculating the probability of failure. In particular, four different methods are compared; the probability method, the combined distribution method, interval analysis method, and the evidence theory. Characteristics of individual methods are compared in the view point of reliability analysis.
참고문헌 (10)
- Dempster, A. P., "Upper and Lower Probabilities Induced by a Multi-valued Mapping", Ann. Mather. Stat., 38(2), pp.325~339 (1967)
- Ferson, S., "Summary from the Epistemic Uncertainty Workshop: Consensus Amid Diversity", Reliab. Eng. & Syst. Saf, 85(1), pp.355~369 (2004)
- Helton, J. C., "Calculation of Reactor Accident Safety Goals", Reliab. Eng. & Syst. Saf., 39, pp.129~158 (1993)
- Representation of Analysis Results Involving Aleatory and Epistemic Uncertainty, "Helton, J.C", Sandia National Laboratories, ~, pp.Technical Report SAND 2008-4379 (2008)
- Kari, S., "Probabilistic Bounding Analysis in the Quantification of Margins and Uncertainties", eliab. Eng. & Syst., Saf., 96(9), pp.1126~1136 (2011)
- Park, C. Y., "How Coupon and Element Tests Reduce Conservativeness in Element Failure Prediction", Reliab. Eng. & Syst. Saf., 123, pp.123~136 (2014)
- Shafer, G., "FA mathematical theory of evidence" (1976), Princeton University Press
- Swiler, L.P., "Epistemic Uncertainty Quantification Tutorial", Proceedings of the 27th International Modal Analysis Conference (2009)
- U.S. Department of Defense, "Guidelines for Property Testing of Composites", Composite Materials Handbook MIL-HDBK-17, ~ (2002)
- Zadeh, L. A., "Fuzzy Sets as a Basis for a Theory of Possibility", Fuzzy Sets & Syst., 100, pp.9~23 (1999)