Comparison of response surface and neural network with other methods for structural reliability analysis

Gomes, Herbert Martins; Awruch, Armando Miguel

doi:10.1016/s0167-4730(03)00022-5

Cited by 255 publications

(118 citation statements)

References 14 publications

Supporting

Mentioning

111

Contrasting

Unclassified

Order By: Relevance

“…Many authors described and compared the traditional reliability methods such as MCS, MCIS, FORM, SORM, RSM or empirical method in conjunction with ANN-based reliability methods ( [26], [50], [51], [25], [52]). …”

Section: Comparison Of Ann-based Reliability Methodsmentioning

confidence: 99%

“…More details on different kind of networks and their architecture can be found in literature e.g. [28], [26].…”

Section: Ann Models For Limit State Function Approximationmentioning

confidence: 99%

“…Several studies have also been performed showing the accuracy and efficiency of the ANN-based response surface method for reliability assessment in comparison with the conventional response surface methods. Gomes and Awruch [26] indicated that the ANN approach is more efficient, however, the examples considered were relatively simple. More recently, Bucher and Most [24] have applied these approximation methods to several examples of nonlinear structural analysis concluding that the relative accuracy of the various approaches depends on the specific problem under consideration.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Review and application of Artificial Neural Networks models in reliability analysis of steel structures

et al. 2015

View full text Add to dashboard Cite

Section: Comparison Of Ann-based Reliability Methodsmentioning

confidence: 99%

“…More details on different kind of networks and their architecture can be found in literature e.g. [28], [26].…”

Section: Ann Models For Limit State Function Approximationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Review and application of Artificial Neural Networks models in reliability analysis of steel structures

et al. 2015

View full text Add to dashboard Cite

“…Other studies demonstrated the efficiency of NNs as a tool for estimating the limit-state function. [32,33] This present study defines the objective function as the total construction cost of the isolated structure, with the probability of failure serving as the constraint for the optimization problem. Protecting sensitive facilities in structures as one of the applications of seismic base isolation is chosen for desired performance of the structure.…”

Section: Introductionmentioning

confidence: 99%

Novel procedure for reliability-based cost optimization of seismically isolated structures for the protection of critical equipment: A case study using single curved surface sliders

Moeindarbari

Taghikhany

2017

Struct Control Health Monit

View full text Add to dashboard Cite

SummaryThe optimized reliability-based design of seismic isolated structures requires a consideration of the failure probability of the system, in addition to the optimization objectives. The stochastic nature of a given system (e.g., the probable input ground motion) must therefore be properly included in the analysis model. To address this challenge, a novel procedure is developed and examined on a 3-story isolated concrete building model, to minimize the total construction cost of the system with regards to protecting sensitive equipment located within the structure.In this procedure, the structure performance and reliability were first evaluated using time-consuming Monte Carlo simulations. We then employed artificial neural networks as a response surface to facilitate the prediction of the failure probability for the supposed structure. To simulate seismic excitations, we generated artificial ground motion combining random high-frequency and long-period components.Also, a newly developed sensitivity analysis method was used to identify the critical uncertain parameters of the system. Finally, by using a simulated annealing algorithm, we determined the optimal design variables of the structure and isolation system for a range of desired probabilities of failure.The optimal results indicate that, for different target failure probability ranges, some design variables are more significant than others. KEYWORDS base isolation, critical equipment protection, neural network, reliability based cost optimization, sensitivity analysis, spectral non-stationarity

show abstract

“…Em relação ao método de Monte Carlo, embora seja de fácil implementação e absolutamente geral, o grande número de simulações pode exigir um tempo de processamento elevado, o que pode tornar sua aplicação inviável. Esse problema tem sido resolvido através de técnicas de redução de variância (Papadrakakis et al, 1996e Papadrakakis & Lagaros, 2002.…”

Section: Introductionunclassified

Confiabilidade estrutural utilizando o método de Monte Carlo e redes neurais

Barbosa

Freitas

Neves

2005

Rem: Rev. Esc. Minas

View full text Add to dashboard Cite

A análise de confiabilidade estrutural em geral, por envolver um grande número de variáveis aleatórias ou exigir uma grande quantidade de simulações, se depara com a questão do custo computacional. Duas técnicas utilizadas para essa avaliação são o método de simulação de Monte Carlo e os métodos analíticos do tipo FORM/ SORM. Os métodos analíticos FORM e SORM podem apresentar problema de precisão no cálculo da probabilidade de falha. Em relação ao método de Monte Carlo, embora sejam de fácil implementação e absolutamente geral, o grande número de simulações pode exigir um tempo de processamento elevado, o que pode tornar sua aplicação inviável. Nesse trabalho, foi utilizada uma rede neural treinada para substituir a solução do problema estrutural necessário a cada simulação de Monte Carlo, com o objetivo de reduzir o custo computacional requerido na análise. As aplicações realizadas proporcionaram bons resultados, com baixo custo computacional, o que atesta a viabilidade de sua aplicação.

show abstract

Comparison of response surface and neural network with other methods for structural reliability analysis

Cited by 255 publications

References 14 publications

Review and application of Artificial Neural Networks models in reliability analysis of steel structures

Review and application of Artificial Neural Networks models in reliability analysis of steel structures

Novel procedure for reliability-based cost optimization of seismically isolated structures for the protection of critical equipment: A case study using single curved surface sliders

Confiabilidade estrutural utilizando o método de Monte Carlo e redes neurais

Contact Info

Product

Resources

About