Accuracy analysis of satellite antenna panel expansion based on BP neural network

The pivotal problem in reliability analysis is how to use as few actual assessments as possible to obtain an accurate failure probability. Although adaptive Kriging provides a viable method to address this problem, unsatisfied Kriging surrogate accuracy and reliability modeling samples often lead to an unacceptable computing burden. In this paper, an adaptive optimized Kriging combining efficient sampling (AOK‐ES) is proposed: first, to enhance the Kriging approximation ability, a high‐fidelity optimized Kriging model (OKM) is established; further, to ensure the samples quality of OKM modeling and reliability calculation, an improved Latin hypercube sampling method and an optimized importance sampling approach are developed correspondingly. Six different types of case studies demonstrate the superiority of the proposed AOK‐ES. The analysis results demonstrate that the proposed AOK‐ES holds the potential to reduce computing cost while ensuring accuracy.

Section: Optimization Algorithmmentioning

confidence: 99%

“…[3][4][5] Reliability analysis is an effective technique to quantify uncertainty, which is of great significance to the reliable operation of complex equipment systems. [6][7][8][9] The key of reliability analysis is to evaluate the failure probability P f , i.e., to solve the following integral:…”

Section: Introductionmentioning

confidence: 99%

AOK‐ES: Adaptive optimized Kriging combining efficient sampling for structural reliability analysis

Huang,

Zhang,

Wang

et al. 2024

“…To address this issue, the Kriging metamodel is utilized in this study to decrease the computational effort involved in the analysis. 39,40 A Kriging model is modeling based on the Gaussian process interpolation formulated as:…”

Section: Kriging Metamodelmentioning

confidence: 99%

Fatigue reliability assessment of offshore catenary risers conveying internal slug flow

Liu

Kang

et al. 2023

This paper proposes a fatigue reliability assessment method of offshore steel catenary risers (SCRs) caused by internal slug flow. Offshore risers subject to slug flow are modeled first by employing a finite element method scheme. Subsequently, a combination of Kriging metamodel and Monte Carlo simulation (MCS) is established to assess the fatigue reliability of SCRs conveying internal slug flow. An explanatory example of a 16-inch SCR is presented to validate the performance of the proposed method and the results indicate that the failure rates of the SCR are significantly affected by the frequency of slug flow. Moreover, the accuracy and feasibility of the present method are validated by a comprehensive comparison with the existing experiments and numerical results. The present method contributes to the design and maintenance of offshore risers with internal slug flow.

“…Commonly used methods include the Kriging function, [6][7][8] support vector machine, 27,28 and neural network. 29,30 There is no clear conclusion on which method is better than others for all problems. It is preferable to choose a method with a broader applicability range when the nonlinear characteristics of the actual problem are uncertain.…”

Section: Introductionmentioning

confidence: 98%

“…Surrogate model 26 is an effective method to improve the computational efficiency of MCS, and its accuracy and efficiency depend on the model type and sampling strategy. Commonly used methods include the Kriging function, 6–8 support vector machine, 27,28 and neural network 29,30 . There is no clear conclusion on which method is better than others for all problems.…”

Section: Introductionmentioning

confidence: 99%

Action reliability analysis under random‐interval hybrid uncertainty of chain conveyor based on adaptive intelligent extremum surrogate model

Wen,

Hou,

Lin

et al. 2023

The action responses of controlled mechanisms are often multiparametric, nonlinear, and uncertain. Complex dynamics and limited uncertain information pose difficulties for action reliability analysis. This paper develops an adaptive intelligent extremum surrogate model (AIESM) method for the action reliability under random‐interval hybrid uncertainty of a chain conveyor. First, a dynamic model of the chain conveyor is established, which considers the impact and frictional effects within the mechanical system, the regulating effects of the control system, and the external disturbances of the system. After that, a hybrid kernel extreme learning machine optimized by the sparrow search algorithm is employed as an intelligent surrogate model to construct the initial surrogate model from the hybrid uncertain variables to the limit state function (LSF) response and the extremum surrogate model (ESM) from the random variables to the LSF extremum response. An adaptive infilling strategy combining active learning and opposition‐based learning is applied to improve the accuracy and efficiency of the ESM and reduce the estimation error of action reliability. Finally, the action reliability interval bounds are obtained by Monte Carlo simulation based on the ESM. Two numerical examples are presented to illustrate the validity of the AIESM method. The action reliability interval of the chain conveyor provided by the proposed method is [0.9706, 0.9923].