Decoupling uncertainty quantification from robust design optimization

Chatterjee, Tanmoy; Chowdhury, Rajib; Ramu, Palaniappan

doi:10.1007/s00158-018-2167-0

Cited by 17 publications

(8 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Originally the GP was developed as a spatial interpolation technique in the field of geostatistics [52]. GP is also known as Kriging in several disciplines [53,54,55,56]. Considering an independent variable x ∈ R d and function g(x) such that g : R d → R, a GP over g(x) with mean µ(x) and covariance function κ(x, x ; θ) can be defined as…”

Section: Gaussian Process Modellingmentioning

confidence: 99%

Gaussian process assisted stochastic dynamic analysis with applications to near-periodic structures

Chatterjee

Karličić

Adhikari

et al. 2021

Mechanical Systems and Signal Processing

Self Cite

View full text Add to dashboard Cite

Section: Gaussian Process Modellingmentioning

confidence: 99%

Gaussian process assisted stochastic dynamic analysis with applications to near-periodic structures

Chatterjee

Karličić

Adhikari

et al. 2021

Mechanical Systems and Signal Processing

Self Cite

View full text Add to dashboard Cite

“…The model building and MCS was removed from the optimization cycle successfully by Chatterjee et al (Chatterjee, Chowdhury, and Ramu 2019). However, only a single approximation layer was devised, which still required a considerable number of actual response evaluations to estimate the statistics.…”

Section: Meta-model Assisted Robust Design Optimizationmentioning

confidence: 99%

“…The primary objective of the present work is to address the above issues in metamodel assisted RDO frameworks. Note that the first issue regarding the accuracy of the meta-model has been addressed recently (Chatterjee, Chowdhury, and Ramu 2019) and therefore the same meta-models are adopted here. Thus, the focus here is more towards the improvement of the computational efficiency of meta-model assisted RDO.…”

Section: Introductionmentioning

confidence: 99%

“…As a result, no model building and MCS (points (i) and (ii)) have to be performed within the optimization routine. This yields optimal solutions in fewer actual response evaluations and results in improvement in terms of computational effort over recent approaches (Chatterjee, Chowdhury, and Ramu 2019) so that it can be readily applied to large-scale problems.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A global two-layer meta-model for response statistics in robust design optimization

Chatterjee

Friswell

Adhikari

et al. 2021

Engineering Optimization

Self Cite

View full text Add to dashboard Cite

Robust design optimization (RDO) of large-scale engineering systems is computationally intensive and requires significant CPU time. Considerable computational effort is still required within conventional meta-model assisted RDO frameworks. The primary objective of this paper is to further minimize the computational requirements of meta-model assisted RDO by developing a global two-layered approximation based RDO technique. The meta-model in the inner layer approximates the response quantity and the meta-model in the outer layer approximates the response statistics computed from the response meta-model. This approach eliminates both model building and Monte Carlo simulation from the optimization cycle, and requires considerably fewer actual response evaluations than a single layered approximation. To demonstrate the approach, two recently developed compressive sensing enabled globally refined Kriging models have been utilized. The proposed framework is applied to one test example and two real-life applications to clearly illustrate its potential to yield robust optimal solutions with minimal computational cost.

show abstract

“…This task forms a proposal for the multi-objective Testing Electromagnetic Analysis Methods (TEAM) benchmark problem for Pareto-optimal electromagnetic Accepted in Periodica Polytechnica Electrical Engineering and Computer Science, the paper will be published in https://pp.bme.hu/eecs devices [1][2][3]. TEAM problems offer a wide variety of test problems to benchmark the new partial differential equation and numerical solvers [1][2][3][4][5][6][7]. Moreover, these problems are openly accessible from the website of COM-PUMAG society [8].…”

Section: Introductionmentioning

confidence: 99%

Semi-Analytical Solution for a Multi-Objective TEAM Benchmark Problem

Karban¹,

Pánek²,

Orosz³

et al. 2020

Preprint

View full text Add to dashboard Cite

Benchmarking is essential for testing new numerical analysis codes. Their solution is crucial both for testing the partial differential equation solvers and both for the optimization methods. Especially, natureinspired optimization algorithm-based solvers, where is an important study is to use benchmark functions to test how the new algorithm may perform, in comparison with other algorithms or fine-tune the optimizer parameters. This paper proposes a novel semi-analytical solution of the multi-objective T.E.A.M benchmark problem. The goal of the benchmark problem is to optimize the layout of a coil and provide a uniform magnetic field in the given region. The proposed methodology was realized in the open-source robust design optimization framework rtap, and the precision of the solution is compared with the result of a fully hp-adaptive numerical solver: Agros-suite. The coil layout optimization was performed by derivative-free non-linear methods and the NSGA-II algorithm.

show abstract

Decoupling uncertainty quantification from robust design optimization

Cited by 17 publications

References 66 publications

Gaussian process assisted stochastic dynamic analysis with applications to near-periodic structures

Gaussian process assisted stochastic dynamic analysis with applications to near-periodic structures

A global two-layer meta-model for response statistics in robust design optimization

Semi-Analytical Solution for a Multi-Objective TEAM Benchmark Problem

Contact Info

Product

Resources

About