Box-Type Boom Design Using Surrogate Modeling: Introducing an Industrial Optimization Benchmark

Philipp Fleck; Doris Entner; Clemens Münzer; Michael Kommenda; Thorsten Prante; Martin Schwarz; Martin Hächl; Michael Affenzeller

doi:10.1007/978-3-319-89890-2_23

Box-Type Boom Design Using Surrogate Modeling: Introducing an Industrial Optimization Benchmark

Philipp Fleck, Doris Entner, Clemens Münzer, Michael Kommenda, Thorsten Prante, Martin Schwarz, Martin Hächl, Michael Affenzeller

Research output: Chapter in Book/Report/Conference proceedings › Chapter › peer-review

5 Citations (Scopus)

Abstract

Simulation-based optimization problems are often an inherent part in engineering design tasks. This paper introduces one such use case, the design of a box-type boom of a crane, which requires a time consuming structural analysis for validation. To overcome high runtimes for optimization approaches with numerous calls to the structural analysis tool, we here present several ways of approximating the structural analysis results using surrogate models. Results show a strong correlation between certain statics input and output parameters, and that various surrogate modeling approaches yield similar results in terms of accuracy and impact of the predictors on the output. The box-type boom use case together with the surrogate models shall serve as an industrial optimization benchmark for comparing various algorithms on this simulation-based optimization problem.

Original language	English
Title of host publication	Computational Methods in Applied Sciences
Publisher	Springer
Pages	355-370
Number of pages	16
ISBN (Print)	978-3-319-89890-2
DOIs	https://doi.org/10.1007/978-3-319-89890-2_23
Publication status	Published - 2019

Publication series

Name	Computational Methods in Applied Sciences
Volume	49
ISSN (Print)	1871-3033

Access to Document

10.1007/978-3-319-89890-2_23

Cite this

Fleck, P., Entner, D., Münzer, C., Kommenda, M., Prante, T., Schwarz, M., Hächl, M., & Affenzeller, M. (2019). Box-Type Boom Design Using Surrogate Modeling: Introducing an Industrial Optimization Benchmark. In Computational Methods in Applied Sciences (pp. 355-370). (Computational Methods in Applied Sciences; Vol. 49). Springer. https://doi.org/10.1007/978-3-319-89890-2_23

@inbook{793a962fb87e457a89a314932c481c7a,

title = "Box-Type Boom Design Using Surrogate Modeling: Introducing an Industrial Optimization Benchmark",

abstract = "Simulation-based optimization problems are often an inherent part in engineering design tasks. This paper introduces one such use case, the design of a box-type boom of a crane, which requires a time consuming structural analysis for validation. To overcome high runtimes for optimization approaches with numerous calls to the structural analysis tool, we here present several ways of approximating the structural analysis results using surrogate models. Results show a strong correlation between certain statics input and output parameters, and that various surrogate modeling approaches yield similar results in terms of accuracy and impact of the predictors on the output. The box-type boom use case together with the surrogate models shall serve as an industrial optimization benchmark for comparing various algorithms on this simulation-based optimization problem.",

author = "Philipp Fleck and Doris Entner and Clemens M{\"u}nzer and Michael Kommenda and Thorsten Prante and Martin Schwarz and Martin H{\"a}chl and Michael Affenzeller",

note = "Funding Information: Acknowledgements This work was carried out within the COMET K-Project #843551 “Advanced Engineering Design Automation (AEDA)” and the COMET K-Project #843532 “Heuristic Optimization in Production and Logistics (HOPL)”, both funded by the Austrian Research Promotion Agency FFG. Funding Information: This work was carried out within the COMET K-Project #843551 “Advanced Engineering Design Automation (AEDA)” and the COMET K-Project #843532 “Heuristic Optimization in Production and Logistics (HOPL)”, both funded by the Austrian Research Promotion Agency FFG. Publisher Copyright: {\textcopyright} 2019, Springer International Publishing AG, part of Springer Nature.",

year = "2019",

doi = "10.1007/978-3-319-89890-2_23",

language = "English",

isbn = "978-3-319-89890-2",

series = "Computational Methods in Applied Sciences",

publisher = "Springer",

pages = "355--370",

booktitle = "Computational Methods in Applied Sciences",

address = "Germany",

}

TY - CHAP

T1 - Box-Type Boom Design Using Surrogate Modeling: Introducing an Industrial Optimization Benchmark

AU - Fleck, Philipp

AU - Entner, Doris

AU - Münzer, Clemens

AU - Kommenda, Michael

AU - Prante, Thorsten

AU - Schwarz, Martin

AU - Hächl, Martin

AU - Affenzeller, Michael

N1 - Funding Information: Acknowledgements This work was carried out within the COMET K-Project #843551 “Advanced Engineering Design Automation (AEDA)” and the COMET K-Project #843532 “Heuristic Optimization in Production and Logistics (HOPL)”, both funded by the Austrian Research Promotion Agency FFG. Funding Information: This work was carried out within the COMET K-Project #843551 “Advanced Engineering Design Automation (AEDA)” and the COMET K-Project #843532 “Heuristic Optimization in Production and Logistics (HOPL)”, both funded by the Austrian Research Promotion Agency FFG. Publisher Copyright: © 2019, Springer International Publishing AG, part of Springer Nature.

PY - 2019

Y1 - 2019

N2 - Simulation-based optimization problems are often an inherent part in engineering design tasks. This paper introduces one such use case, the design of a box-type boom of a crane, which requires a time consuming structural analysis for validation. To overcome high runtimes for optimization approaches with numerous calls to the structural analysis tool, we here present several ways of approximating the structural analysis results using surrogate models. Results show a strong correlation between certain statics input and output parameters, and that various surrogate modeling approaches yield similar results in terms of accuracy and impact of the predictors on the output. The box-type boom use case together with the surrogate models shall serve as an industrial optimization benchmark for comparing various algorithms on this simulation-based optimization problem.

AB - Simulation-based optimization problems are often an inherent part in engineering design tasks. This paper introduces one such use case, the design of a box-type boom of a crane, which requires a time consuming structural analysis for validation. To overcome high runtimes for optimization approaches with numerous calls to the structural analysis tool, we here present several ways of approximating the structural analysis results using surrogate models. Results show a strong correlation between certain statics input and output parameters, and that various surrogate modeling approaches yield similar results in terms of accuracy and impact of the predictors on the output. The box-type boom use case together with the surrogate models shall serve as an industrial optimization benchmark for comparing various algorithms on this simulation-based optimization problem.

UR - http://www.scopus.com/inward/record.url?scp=85053004023&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-89890-2_23

DO - 10.1007/978-3-319-89890-2_23

M3 - Chapter

SN - 978-3-319-89890-2

T3 - Computational Methods in Applied Sciences

SP - 355

EP - 370

BT - Computational Methods in Applied Sciences

PB - Springer

ER -

Box-Type Boom Design Using Surrogate Modeling: Introducing an Industrial Optimization Benchmark

Abstract

Publication series

Access to Document

Other files and links

Fingerprint

Cite this