Active learning for structural reliability: Survey, general framework and benchmark

Moustapha, Maliki; Marelli, Stefano; Sudret, Bruno

doi:10.1016/j.strusafe.2021.102174

Cited by 89 publications

(16 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Structural reliability analysis is often carried out to quantitatively assess the probability of structures' safe or failure state under the impact of uncertain factors in the environmental, structural and load parameters. Various structural reliability analysis methods, which can be broadly categorized into three main types: simulation-based methods, analytical methods or approximation methods, and meta-modeling methods, have been proposed over the past three decades [1,2].…”

Section: Akmentioning

confidence: 99%

AWK-TIS: An Improved AK-IS Based on Whale Optimization Algorithm and燭runcated Importance Sampling for Reliability Analysis

Qin¹,

Cao²,

Zhang³

2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

In this work, an improved active kriging method based on the AK-IS and truncated importance sampling (TIS) method is proposed to efficiently evaluate structural reliability. The novel method called AWK-TIS is inspired by AK-IS and RBF-GA previously published in the literature. The innovation of the AWK-TIS is that TIS is adopted to lessen the sample pool size significantly, and the whale optimization algorithm (WOA) is employed to acquire the optimal Kriging model and the most probable point (MPP). To verify the performance of the AWK-TIS method for structural reliability, four numerical cases which are utilized as benchmarks in literature and one real engineering problem about a jet van manipulate mechanism are tested. The results indicate the accuracy and efficiency of the proposed method.

show abstract

Section: Akmentioning

confidence: 99%

AWK-TIS: An Improved AK-IS Based on Whale Optimization Algorithm and燭runcated Importance Sampling for Reliability Analysis

Qin¹,

Cao²,

Zhang³

2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

show abstract

“…. In both the APCK-IS and the APCK-SuS, the Polynomial Chaos-Kriging (PCK) model [25] and the U learning function are adopted; the stopping condition is defined in terms of the bound of the estimated failure probability in 2 successive iterations, with the tolerance being -2 1 10  [13]; the sample size of each subset in the SuS is taken as 5 10 . For more details, the reader is referred to [13].…”

Section: Endmentioning

confidence: 99%

“…In both the APCK-IS and the APCK-SuS, the Polynomial Chaos-Kriging (PCK) model [25] and the U learning function are adopted; the stopping condition is defined in terms of the bound of the estimated failure probability in 2 successive iterations, with the tolerance being -2 1 10  [13]; the sample size of each subset in the SuS is taken as 5 10 . For more details, the reader is referred to [13]. In the standard PDEM, the sample size of representative points is taken as 2000, exactly equal to the initial representative point size of the AK-PDEMi; the AK-PDEM corresponds exactly to the first run of the AK process in the AK-PDEMi, which is denoted as the 0-th loop hereafter.…”

Section: Endmentioning

confidence: 99%

“…Active learning-based reliability methods [12,13] aim to reduce the overall computational costs of those above-mentioned reliability methods through the use of metamodels, a.k.a. surrogate models.…”

mentioning

confidence: 99%

“…The second one is defined based on the confidence bound of the estimated failure probability, considering the statistical uncertainty of surrogate predictions, such as [22,25]. The third one is defined according to the stabilization of the failure probability estimates within several consecutive iterations, such as [13,26].…”

mentioning

confidence: 99%

See 2 more Smart Citations

AK-PDEMi: A failure-informed enrichment algorithm for improving the AK-PDEM in reliability analysis

Zhou

Marelli

Sudret

et al. 2022

Mechanical Systems and Signal Processing

Self Cite

View full text Add to dashboard Cite

Optimizing the Microstructure and Processing Parameters for Lithium‐Ion Battery Cathodes: A Use Case Scenario with a Digital Manufacturing Platform

et al. 2022

View full text Add to dashboard Cite

With increasing electrification in the automotive field, lithium‐ion batteries are rapidly becoming an inseparable part of everyday life. To meet the various governmental goals regarding CO2 emissions, it has become imperative to rapidly optimize the manufacturing process to produce high‐quality batteries at the least possible emissions and cost. Model‐based methods provide a simple and efficient view on complex processes and on identifying best‐case scenarios for production, since they require minimal material and time expenditure. In the authors’ recently published work, by Thomitzek et al., a digital modeling framework is initially described. It uniquely combines process chain and battery cell models. Herein, this digital framework is utilized to set up a numerical optimization routine. The routine helps to identify the best possible microstructure parameters in an NMC 622 cathode to maximize the resulting discharge volumetric energy density. Furthermore, the minimal energy expenditure for processing is determined. With the findings herein, an inexpensive method for identifying optimal battery manufacturing scenarios is presented, with the goal of producing high‐quality battery cells at the lowest cost. The provided model framework and optimization routine is easily adaptable for other battery types and manufacturing lines.

show abstract

Active learning for structural reliability: Survey, general framework and benchmark

Cited by 89 publications

References 70 publications

AWK-TIS: An Improved AK-IS Based on Whale Optimization Algorithm and燭runcated Importance Sampling for Reliability Analysis

AWK-TIS: An Improved AK-IS Based on Whale Optimization Algorithm and燭runcated Importance Sampling for Reliability Analysis

AK-PDEMi: A failure-informed enrichment algorithm for improving the AK-PDEM in reliability analysis

Optimizing the Microstructure and Processing Parameters for Lithium‐Ion Battery Cathodes: A Use Case Scenario with a Digital Manufacturing Platform

Contact Info

Product

Resources

About