Multilevel surrogate modeling approach for optimization problems with polymorphic uncertain parameters

被引：0

作者：

Freitag, Steffen ^{[1
]}

Edler, Philipp ^{[1
]}

Kremer, Katharina ^{[1
]}

Meschke, Günther ^{[1
]}

机构：

[1] Institute for Structural Mechanics, Ruhr University Bochum, Universitätsstr. 150, Bochum,44801, Germany

来源：

International Journal of Approximate Reasoning | 2020年 / 119卷

关键词：

The solution of optimization problems with polymorphic uncertain data requires combining stochastic and non-stochastic approaches. The concept of uncertain a priori parameters and uncertain design parameters quantified by random variables and intervals is presented in this paper. Multiple runs of the nonlinear finite element model solving the structural mechanics with varying a priori and design parameters are needed to obtain a solution by means of iterative optimization algorithms (e.g. particle swarm optimization). The combination of interval analysis and Monte Carlo simulation is required for each design to be optimized. This can only be realized by substituting the nonlinear finite element model by numerically efficient surrogate models. In this paper; a multilevel strategy for neural network based surrogate modeling is presented. The deterministic finite element simulation; the stochastic analysis as well as the interval analysis are approximated by sequentially trained artificial neural networks. The approach is verified and applied to optimize the concrete cover of a reinforced concrete structure; taking the variability of material parameters and the structural load as well as construction imprecision into account. © 2019 Elsevier Inc;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

引用

页码：81 / 91

共 50 条

[1] Multilevel surrogate modeling approach for optimization problems with polymorphic uncertain parameters
Freitag, Steffen
Edler, Philipp
Kremer, Katharina
Meschke, Guenther
INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2020, 119 : 81 - 91
[2] A new pragmatic approach to solve the problems of vector optimization with uncertain parameters
Reizlin, V. I.
Nefedova, A. A.
INTERNATIONAL CONFERENCE ON MECHANICAL ENGINEERING, AUTOMATION AND CONTROL SYSTEMS 2015 (MEACS2015), 2016, 124
[3] Enhanced Simulation-Optimization Approach Using Surrogate Modeling for Solving Inverse Problems
Mirghani, Baha Y.
Zechman, Emily M.
Ranjithan, Ranji S.
Mahinthakumar, G.
ENVIRONMENTAL FORENSICS, 2012, 13 (04) : 348 - 363
[4] AN APPROACH TO ESTIMATION PROBLEMS CONTAINING UNCERTAIN PARAMETERS
JACKSON, A
PHYSICS OF THE EARTH AND PLANETARY INTERIORS, 1995, 90 (3-4) : 145 - 156
[5] Robustness versus Performance - Nested Inherence of Objectives in Optimization with Polymorphic Uncertain Parameters
Schietzold, F. Niklas
Leichsenring, Ferenc
Goetz, Marco
Graf, Wolfgang
Kaliske, Michael
ADVANCES IN ENGINEERING SOFTWARE, 2021, 156
[6] Evolutionary optimization of computationally expensive problems via surrogate modeling
Ong, YS
Nair, PB
Keane, AJ
AIAA JOURNAL, 2003, 41 (04) : 687 - 696
[7] Evolutionary optimization of computationally expensive problems via surrogate modeling
Ong, Y.S. (asysong@ntu.edu.sg), 1600, American Inst. Aeronautics and Astronautics Inc. (41):
[8] A genetic algorithm approach to optimization problems in an uncertain environment
Tamaki, H
Arai, T
PROGRESS IN CONNECTIONIST-BASED INFORMATION SYSTEMS, VOLS 1 AND 2, 1998, : 436 - 439
[9] Global optimization by interval analysis: Application to problems with uncertain parameters
Campos, Pedro G.
Valdés-González, Héctor M.
Informacion Tecnologica, 2006, 17 (05):
[10] A machine learning approach for the surrogate modeling of uncertain distributed process engineering models
Mora-Mariano, Dante
Flores-Tlacuahuac, Antonio
CHEMICAL ENGINEERING RESEARCH & DESIGN, 2022, 186 : 433 - 450

← 1 2 3 4 5 →