A new active learning method based on the learning function U of the AK-MCS reliability analysis method

Zheng, Pengfei; Ming, Wang Chien; Zong, Zhouhong; Wang, Liqi

doi:10.1016/j.engstruct.2017.06.038

Cited by 93 publications

(21 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, it is not easy to quantify the accuracy of these models in terms of error in calculation of failure probability. ( Fauriat and Gayton, 2014 ; Huang et al, 2016b ; Peijuan et al, 2017 ; Bichon et al, 2008 ; Zhu et al, 2020 ) Outcrossing Methods Simulating the reduction/increase in the strength/stress using stochastic processes and calculating the probability of the first passage of the stochastic process from the predefined threshold Different closed-form formula for outcrossing of stochastic processes Accurately predict the failure probability by realistic simulation of structural strength evolutions. If the closed-form solution exists, the method is easy to implement and very accurate.…”

Section: Reliability Analysis Of the Integrated Systemmentioning

confidence: 99%

Reliability of multi-purpose offshore-facilities: Present status and future direction in Australia

Aryai

Abdussamie

Salehi

et al. 2021

Process Safety and Environmental Protection

View full text Add to dashboard Cite

Sustainable use of the ocean for food and energy production is an emerging area of research in different countries around the world. This goal is pursued by the Australian aquaculture, offshore engineering and renewable energy industries, research organisations and the government through the “Blue Economy Cooperative Research Centre”. To address the challenges of offshore food and energy production, leveraging the benefits of co-location, vertical integration, infrastructure and shared services, will be enabled through the development of novel Multi-Purpose Offshore-Platforms (MPOP). The structural integrity of the designed systems when being deployed in the harsh offshore environment is one of the main challenges in developing the MPOPs. Employing structural reliability analysis methods for assessing the structural safety of the novel aquaculture-MPOPs comes with different limitations. This review aims at shedding light on these limitations and discusses the current status and future directions for structural reliability analysis of a novel aquaculture-MPOP considering Australia’s unique environment. To achieve this aim, challenges which exist at different stages of reliability assessment, from data collection and uncertainty quantification to load and structural modelling and reliability analysis implementation, are discussed. Furthermore, several solutions to these challenges are proposed based on the existing knowledge in other sectors, and particularly from the offshore oil and gas industry. Based on the identified gaps in the review process, potential areas for future research are introduced to enable a safer and more reliable operation of the MPOPs.

show abstract

Section: Reliability Analysis Of the Integrated Systemmentioning

confidence: 99%

Reliability of multi-purpose offshore-facilities: Present status and future direction in Australia

Aryai

Abdussamie

Salehi

et al. 2021

Process Safety and Environmental Protection

View full text Add to dashboard Cite

show abstract

“…In reliability analysis of concrete‐filled steel tube arch bridge, its functional function is highly implicit, which makes it difficult to directly use algorithms such as first order second moment method (FORM), second order second moment method (SORM), and direct integration. Direct Monte Carlo simulation (MCS) 1 is suitable for solving the reliability of the implicit function, and the calculation accuracy is higher. But in order to guarantee the accuracy, the MCS method requires the sampling frequency is very large.…”

Section: Introductionmentioning

confidence: 99%

Reliability evaluation of concrete‐filled steel tube arch bridge based on DBN‐PSOSA hybrid algorithm

Hong

et al. 2021

Structural Concrete

View full text Add to dashboard Cite

When traditional response surface method is used to evaluate the reliability of concrete-filled steel tubular arch bridge, due to its complex structure and highly nonlinear implicit function, the response surface fitting accuracy is not high, and the reliability accuracy is difficult to meet the requirements of design specifications. In order to solve the above problems, this paper chooses dynamic Bayesian networks (DBN) which is suitable for solving the problem of multiple state unit or system uncertainty to build implicit function of the response surface function. And this paper combines DBN and particle swarm optimization algorithm based on simulated annealing algorithm (PSOSA) to improve efficiency of model parameter optimization. It can make the construction of implicit function simulate the real structure of the limit state function. Then this paper verifies the suitability for this kind of complex structure reliability assessment of DBN-PSOSA hybrid algorithm. A numerical example is given to demonstrate the effectiveness of the proposed method, and the reliability of a concrete filled steel tube arch bridge project is evaluated. The results show that this method improves the calculation accuracy and efficiency.

show abstract

“…The added complexity of time-variant reliability analysis is indicative of the importance of AK, and in particular, of efficient metamodeling approaches. Other examples of the application of the Kriging models for practical structural engineering problems can be found in [19][20][21][22][23][24][25].…”

Section: Introductionmentioning

confidence: 99%

Reliability assessment with density scanned adaptive Kriging

Teixeira

Nogal

O’Connor

et al. 2020

Reliability Engineering & System Safety

View full text Add to dashboard Cite

Reliability assessment with adaptive Kriging has gained notoriety due to the Kriging capability of accurately replacing the performance function while performing as a self-improving function for learning procedures.Recent works on adaptive Kriging pursued to improve the efficiency of the active learning through the application of distinct learning functions, sampling methods, or frameworks to assess the learning space. Within this context, the present work exploits three innovative applications of density scanning to improve the efficiency of the adaptive Kriging. Density scanning has significant synergies with adaptive Kriging implementation. For most learning criteria, candidate points occur in dense clusters. This is due to the fact that the most efficient learning strategies pursue to improve predictions near the failure region, or when the prediction uncertainty is large.Identifying dense clusters of points, and fomenting exploitation of these, parallelizing computations, and limiting the generation of dense clusters in the design of experiments are examples of learning frameworks that can be achieved with density scanning. Three reference examples are researched in the present work, a complex function, a series system, and a relatively high dimension engineering problem. For all the cases, the application of density scanning is identified to improve the active learning efficiency.

show abstract

A new active learning method based on the learning function U of the AK-MCS reliability analysis method

Cited by 93 publications

References 37 publications

Reliability of multi-purpose offshore-facilities: Present status and future direction in Australia

Reliability of multi-purpose offshore-facilities: Present status and future direction in Australia

Reliability evaluation of concrete‐filled steel tube arch bridge based on DBN‐PSOSA hybrid algorithm

Reliability assessment with density scanned adaptive Kriging

Contact Info

Product

Resources

About