Näytä suppeat kuvailutiedot

dc.contributor.authorMazumdar, Atanu
dc.contributor.authorBurkotová, Jana
dc.contributor.authorKrátký, Tomáš
dc.contributor.authorChugh, Tinkle
dc.contributor.authorMiettinen, Kaisa
dc.date.accessioned2024-08-15T11:28:27Z
dc.date.available2024-08-15T11:28:27Z
dc.date.issued2024
dc.identifier.citationMazumdar, A., Burkotová, J., Krátký, T., Chugh, T., & Miettinen, K. (2024). Handling simulation failures of a computationally expensive multiobjective optimization problem in pump design. <i>Engineering Applications of Artificial Intelligence</i>, <i>136</i>(Part A), Article 108897. <a href="https://doi.org/10.1016/j.engappai.2024.108897" target="_blank">https://doi.org/10.1016/j.engappai.2024.108897</a>
dc.identifier.otherCONVID_233288930
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/96620
dc.description.abstractSolving real-world optimization problems in engineering and design involves various practical challenges. They include simultaneously optimizing multiple conflicting objective functions that may involve computationally expensive simulations. Failed simulations introduce another practical challenge, as it is not always possible to set constraints a priori to avoid failed simulations. Failed simulations are typically ignored during optimization, which leads to wasting computation resources. When the optimization problem has multiple objective functions, failed simulations can also be misleading for the decision maker while choosing the most preferred solution. Utilizing data collected from previous simulations and enabling the optimization algorithm to avoid failed simulations can reduce the computational requirements. We consider data-driven multiobjective optimization of the diffusor of an axial pump and propose an approach to reduce the number of solutions that fail in expensive computational fluid dynamics simulations. The proposed approach utilizes Kriging surrogate models to approximate the objective functions and is inexpensive to evaluate. We utilize a probabilistic selection approach with constraints in a multiobjective evolutionary algorithm to find solutions with better objective function values, lower uncertainty, and lower probability of failing. Finally, a domain expert chooses the most preferred solution using one’s preferences. Numerical tests show significant improvement in the ratio of feasible solutions to all the available solutions without special treatment of failed simulations. The solutions also have a higher quality (hypervolume) and accuracy than the other tested approaches. The proposed approach provides an efficient way of reducing the number of failed simulations and utilizing offline data in multiobjective design optimization.en
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherElsevier
dc.relation.ispartofseriesEngineering Applications of Artificial Intelligence
dc.rightsCC BY 4.0
dc.subject.othersimulation-based optimization
dc.subject.othergaussian process
dc.subject.otherconstraint handling
dc.subject.otherdata-driven optimization
dc.subject.othercomputational cost
dc.subject.othercomputational fluid dynamics simulations
dc.titleHandling simulation failures of a computationally expensive multiobjective optimization problem in pump design
dc.typearticle
dc.identifier.urnURN:NBN:fi:jyu-202408155504
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.type.urihttp://purl.org/eprint/type/JournalArticle
dc.type.coarhttp://purl.org/coar/resource_type/c_2df8fbb1
dc.description.reviewstatuspeerReviewed
dc.relation.issn0952-1976
dc.relation.numberinseriesPart A
dc.relation.volume136
dc.type.versionpublishedVersion
dc.rights.copyright© 2024 The Authors. Published by Elsevier Ltd.
dc.rights.accesslevelopenAccessfi
dc.subject.ysomonitavoiteoptimointi
dc.subject.ysoalgoritmit
dc.subject.ysolaskennallinen tiede
dc.subject.ysogaussiset prosessit
dc.subject.ysosimulointi
dc.subject.ysooptimointi
dc.subject.ysopumput
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p32016
jyx.subject.urihttp://www.yso.fi/onto/yso/p14524
jyx.subject.urihttp://www.yso.fi/onto/yso/p21978
jyx.subject.urihttp://www.yso.fi/onto/yso/p38750
jyx.subject.urihttp://www.yso.fi/onto/yso/p4787
jyx.subject.urihttp://www.yso.fi/onto/yso/p13477
jyx.subject.urihttp://www.yso.fi/onto/yso/p16383
dc.rights.urlhttps://creativecommons.org/licenses/by/4.0/
dc.relation.datasethttps://github.com/amrzr/CKP-RVEA
dc.relation.doi10.1016/j.engappai.2024.108897
jyx.fundinginformationThis research is related to the thematic research area DEMO (Decision Analytics utilizing Causal Models and Multiobjective Optimization, jyu.fi/demo) of the University of Jyväskylä. This research was also supported by Ministry of Education, Youth and Sports of the Czech Republic under the project CZ.02.1.01/0.0/0.0/17_049/0008400 “Hydrodynamic design of pumps”. Computational resources were supplied by the project “e-Infrastruktura CZ” (e-INFRA CZ LM2018140) supported by the Ministry of Education, Youth and Sports of the Czech Republic . The revision process of the paper is supported by Artificial Intelligence for Urban Low-Emission Autonomous Traffic (AIforLessAuto) , which is funded under the Green and Digital transition call from the Academy of Finland (project number: 347199).
dc.type.okmA1


Aineistoon kuuluvat tiedostot

Thumbnail

Aineisto kuuluu seuraaviin kokoelmiin

Näytä suppeat kuvailutiedot

CC BY 4.0
Ellei muuten mainita, aineiston lisenssi on CC BY 4.0