ACTIVE-LEARNING METHOD BASED ON ALK MODEL AND SUBSET SIMULATION

LIU ZeQing; CHENG Xin; YANG XuFeng

doi:10.16579/j.issn.1001.9669.2024.01.013

您当前的位置：

首页 >

文章列表页 >

ACTIVE-LEARNING METHOD BASED ON ALK MODEL AND SUBSET SIMULATION

更新时间：2024-04-18

- ACTIVE-LEARNING METHOD BASED ON ALK MODEL AND SUBSET SIMULATION
- Journal of Mechanical Strength Vol. 46, Issue 1, Pages: 96-106(2024)
- 作者机构：
  
  1. 西南交通大学机械工程学院
- 作者简介：
- 基金信息：
- DOI：10.16579/j.issn.1001.9669.2024.01.013
  CLC： TB114.3
- Published：15 February 2024，
- 稿件说明：
移动端阅览
LIU ZeQing, CHENG Xin, YANG XuFeng. ACTIVE-LEARNING METHOD BASED ON ALK MODEL AND SUBSET SIMULATION. [J]. Journal of Mechanical Strength 46(1):96-106(2024)
DOI：

LIU ZeQing, CHENG Xin, YANG XuFeng. ACTIVE-LEARNING METHOD BASED ON ALK MODEL AND SUBSET SIMULATION. [J]. Journal of Mechanical Strength 46(1):96-106(2024) DOI： 10.16579/j.issn.1001.9669.2024.01.013.

摘要

针对主动学习Kriging（Active Learning Kriging，ALK）模型在评估小失效概率时遇到的候选样本过多、计算耗时的问题，提出了一种结合ALK 模型与子集模拟（Subset Simulation，SS）的双阶段代理模型方法——ALK-SS

。首先在第1阶段基于构建的极限状态函数代理模型，采用较少数量的SS最后一层样本作为候选样本完成极限状态面的粗略近似，然后在第2阶段选择更大样本量的SS最后一层样本来细化第1阶段的极限状态函数代理模型，以获得更高的精度。此外，考虑到传统ALK 模型的收敛准则太过于保守，在ALK-SS

评估的失效概率基础上，提出了一种更高效的基于失效概率误差的收敛标准，进一步提高了该方法的效率。通过4个算例的测试以及同类方法的对比，证明其具有较高的计算精度和计算效率，适用于处理小失效概率问题和耗时的隐式功能函数问题。

Abstract

When estimating very small failure probability

the methods based on active learning Kriging (ALK) model usually need too many candidate points and time-consuming calculation. To address this problem

this paper proposes a two-stage surrogate model method

ALK-SS

which combines the ALK model and subset simulation(SS). Firstly

based on the constructed surrogate model in the first stage

the method uses a small number of SS last layer samples as candidate samples to complete the rough approximation of the limit state surface

and then in the second stage

it selects the SS last layer samples witha

larger sample size to refine the surrogate model in the first stage

so as to obtain higher accuracy. In addition

considering the conventional stopping criteria are too conservative. based on the failure probabilitv evaluated by ALK-SS

a new stopping criterion based on failure probability error is proposed

which further improves the efficiency of the method. From the investigation of four examples and the comparison with relative methods

it is proved that the proposed method has high calculation accuracy and efficiency

and is suitable for dealing with small failure probability problems and time-consuming implicit function problems.

关键词

可靠性分析主动学习Kriging模型子集模拟

Keywords

Reliability analysisActive learningKriging modelSubset simulation

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

RELIABILITY ANALYSIS ON HYBRID SURROGATE MODEL OF RADIAL BASIS FUNCTION AND SPARSE POLYNOMIAL CHAOS EXPANSION (MT)

RELIABILITY ANALYSIS OF INDUSTRIAL ROBOT USING T-S FUZZY FAULT TREE

STRUCTURE RELIABILITY CALCULATION METHOD BASED ON IMPROVED NEURAL NETWORK

STOCHASTIC FINITE ELEMENT MODEL UPDATING BASED ON POLYNOMIAL CHAOTIC EXPANSION AND KL DIVERGENCE

RESEARCH ON COOLING PERFORMANCE OF HIGH POWER POWER BATTERY PACK BASED ON MULTI-OBJECTIVE GENETIC ALGORITHM

Related Author

WU ZePing

OUYANG Heng

ZHANG DeQuan

ZHAO ZiDa

ZHANG ChuanHui

ZHOU Ce

ZHANG JunYi

BAI Bin

Related Institution

College of Aerospace Science and Engineering, National University of Defense Technology

Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Mechanical Engineering,Hebei University of Technology

School of Mechanical Engineering, Hebei University of Technology

Hunan Sany Polytechnic College

School of Locomotive and Rolling Stock Engineering,Dalian Jiaotong University

⁰