Assessing fire safety using complex numerical models with a Bayesian multi-fidelity approach

Stroh, Rémi; Bect, Julien; Demeyer, Séverine; Fischer, Nicolas; Marquis, Damien; Vázquez, Emmanuel

doi:10.1016/j.firesaf.2017.03.059

Cited by 10 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One technique for surrogate model development that has been successful across a range of applications from fire safety to additive manufacturing [18,19] is Gaussian process modelling [20], also known as kriging. This technique requires the user to have a set of results of the full model at a set of known values of the input quantities, called the training set.…”

Section: What Still Needs Doing?mentioning

confidence: 99%

How to tell the difference between a model and a digital twin

Wright

Davidson

2020

Adv. Model. and Simul. in Eng. Sci.

362

164

View full text Add to dashboard Cite

Digital twin is a term that is being used for a wide range of things across a wide range of applications, from high value manufacturing and personalised medicines to oil refinery management and risk identification and mitigation for city planning. For some of the definitions, the reason why "twin" is used has been lost. The danger of this variety and vagueness is that a poor definition and explanation of a digital twin may lead people to reject it as just hype, so that once the hype and the inevitable backlash are over the final level of interest and use (the "plateau of productivity", see Fig. 1) may fall well below the maximum potential of the technology.

show abstract

Section: What Still Needs Doing?mentioning

confidence: 99%

How to tell the difference between a model and a digital twin

Wright

Davidson

2020

Adv. Model. and Simul. in Eng. Sci.

362

164

View full text Add to dashboard Cite

show abstract

“…Specific indexes are safety risk assessment cycle (A10), perfectness ratio of safety management system (A11), and number of emergency plans (A12). The safety risk assessment cycle is negatively correlated with the perfectness ratio of port safety facilities but is positively related to probability of safety accidents [19]. An improvement in safety management system can clarify division of responsibility and simplify safety management [20].…”

Section: Methodsmentioning

confidence: 99%

Port Safety Assessment based on Entropy Weight Matter-Element model

Fu¹

2017

JESTR

View full text Add to dashboard Cite

Frequently port safety accidents have resulted in port safety problems becoming the focus of increasing attention. Port safety assessment is an important basis in preventing port safety accidents. Owing to complicated influencing factors of port safety, assessing port safety effectively has been a key research topic in the industry and academe. To determine port safety assessment indexes reasonably and acquire practical assessment results, the port safety assessment index system based on 5M (man, machine, material, management, and milieu) was established first. Then, weights of all assessment indexes were determined by the entropy weight method, and the port safety assessment model was constructed by matterelement theory. Finally, the assessment model was verified by ports in Zhejiang Province of China. Results demonstrate that the material factor presents the highest average weight among all evaluation indexes. The accident rate of goods and qualified rate of pollution control are two indexes with the highest weights. The port safety assessment results based on the entropy weight matter-element model conform to practical situations. Thus, the port safety assessment model based on entropy weight matter-element theory can measure port safety level effectively and evaluate its feasibility in practical cases. The model offsets shortcomings of single theory assessment and provides a new idea and decision-making method for port safety assessment.

show abstract

“…In this section, we present the model proposed in [6]. The output Z at x, t is assumed conditionally Gaussian…”

Section: Multi-fidelity Gaussian Processmentioning

confidence: 99%

“…Consequently, we assume [6] a strong correlation between log-noise variances, which is set to c = 99%. This assumption helps to estimate noise variance on the levels with few observations.…”

Section: Dealing With Hyper-parametersmentioning

confidence: 99%

See 1 more Smart Citation

Integrating hyper-parameter uncertainties in a multi-fidelity Bayesian model for the estimation of a probability of failure

Stroh

Bect

Demeyer

et al. 2018

Series on Advances in Mathematics for Applied Sciences

View full text Add to dashboard Cite

A multi-fidelity simulator is a numerical model, in which one of the inputs controls a trade-off between the realism and the computational cost of the simulation. Our goal is to estimate the probability of exceeding a given threshold on a multi-fidelity stochastic simulator. We propose a fully Bayesian approach based on Gaussian processes to compute the posterior probability distribution of this probability. We pay special attention to the hyper-parameters of the model. Our methodology is illustrated on an academic example.

show abstract

Assessing fire safety using complex numerical models with a Bayesian multi-fidelity approach

Cited by 10 publications

References 16 publications

How to tell the difference between a model and a digital twin

How to tell the difference between a model and a digital twin

Port Safety Assessment based on Entropy Weight Matter-Element model

Integrating hyper-parameter uncertainties in a multi-fidelity Bayesian model for the estimation of a probability of failure

Contact Info

Product

Resources

About