Details
| Original language | English |
|---|---|
| Journal | UNCECOMP Proceedings |
| Volume | 2021 |
| Publication status | Published - 2021 |
| Event | 4th International Conference on Uncertainty Quantification in Computational Sciences and Engineering, UNCECOMP 2021 - online, Athens, Greece Duration: 28 Jun 2021 → 30 Jun 2021 Conference number: 4 |
Abstract
In order to describe spatially uncertain parameters by random fields, the underlying autocorrelation structure in engineering structures is usually not known.. The idea of imprecise random fields is to acknowledge this lack of knowledge by adding epistemic uncertainties. Within this contribution the influence of the correlation length is studied. In particular, it is shown that there exist bounds that limit the case of having no idea at all. This “absolutely no idea p-box” is defined by white noise and the random variable corresponding to the mean value and standard deviation of the imprecise random field. By this, the limits of having “absolutely no idea” can be described without the need of Karhunen-Loève expansion and random field propagation. Then, at least for linear problems, every response in between can be estimated by linear interpolation without any need for sampling.
Keywords
- Imprecise random fields, Interval valued correlation length, Karhunen-Loève expansion, Stochastic finite element method
ASJC Scopus subject areas
- Computer Science(all)
- Computational Theory and Mathematics
- Computer Science(all)
- Computer Science Applications
- Mathematics(all)
- Modelling and Simulation
- Mathematics(all)
- Statistics and Probability
- Mathematics(all)
- Control and Optimization
- Mathematics(all)
- Discrete Mathematics and Combinatorics
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: UNCECOMP Proceedings, Vol. 2021, 2021.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - Limit representations of imprecise random fields
AU - Dannert, Mona M.
AU - Häufler, Johannes L.
AU - Nackenhorst, Udo
N1 - Conference code: 4
PY - 2021
Y1 - 2021
N2 - In order to describe spatially uncertain parameters by random fields, the underlying autocorrelation structure in engineering structures is usually not known.. The idea of imprecise random fields is to acknowledge this lack of knowledge by adding epistemic uncertainties. Within this contribution the influence of the correlation length is studied. In particular, it is shown that there exist bounds that limit the case of having no idea at all. This “absolutely no idea p-box” is defined by white noise and the random variable corresponding to the mean value and standard deviation of the imprecise random field. By this, the limits of having “absolutely no idea” can be described without the need of Karhunen-Loève expansion and random field propagation. Then, at least for linear problems, every response in between can be estimated by linear interpolation without any need for sampling.
AB - In order to describe spatially uncertain parameters by random fields, the underlying autocorrelation structure in engineering structures is usually not known.. The idea of imprecise random fields is to acknowledge this lack of knowledge by adding epistemic uncertainties. Within this contribution the influence of the correlation length is studied. In particular, it is shown that there exist bounds that limit the case of having no idea at all. This “absolutely no idea p-box” is defined by white noise and the random variable corresponding to the mean value and standard deviation of the imprecise random field. By this, the limits of having “absolutely no idea” can be described without the need of Karhunen-Loève expansion and random field propagation. Then, at least for linear problems, every response in between can be estimated by linear interpolation without any need for sampling.
KW - Imprecise random fields
KW - Interval valued correlation length
KW - Karhunen-Loève expansion
KW - Stochastic finite element method
UR - http://www.scopus.com/inward/record.url?scp=85121105943&partnerID=8YFLogxK
U2 - 10.7712/120221.8024.19110
DO - 10.7712/120221.8024.19110
M3 - Conference article
AN - SCOPUS:85121105943
VL - 2021
JO - UNCECOMP Proceedings
JF - UNCECOMP Proceedings
T2 - 4th International Conference on Uncertainty Quantification in Computational Sciences and Engineering, UNCECOMP 2021
Y2 - 28 June 2021 through 30 June 2021
ER -