Show simple item record

dc.contributor.authorWang, Yongen
dc.contributor.authorYin, Da-Qingen
dc.contributor.authorYang, Shengxiangen
dc.contributor.authorSun, Guangyongen
dc.date.accessioned2018-02-28T12:30:40Z
dc.date.available2018-02-28T12:30:40Z
dc.date.issued2018-03-29
dc.identifier.citationWang, Y., Yin, D-Q. Yang, S. and Sun, G. (2018) Global and local surrogate-assisted differential evolution for expensive constrained optimization. IEEE Transactions on Cybernetics, 49 (5), pp. 1642-1656en
dc.identifier.issn2168-2267
dc.identifier.issn2168-2275
dc.identifier.urihttp://hdl.handle.net/2086/15303
dc.descriptionThe file attached to this record is the author's final peer reviewed version.en
dc.description.abstractFor expensive constrained optimization problems, the computation of objective function and constraints is very time-consuming. This paper proposes a novel global and local surrogate-assisted differential evolution for solving expensive constrained optimization problems with inequality constraints. The proposed method consists of two main phases: global surrogate-assisted phase and local surrogate-assisted phase. In the global surrogate-assisted phase, differential evolution serves as the search engine to produce multiple trial vectors. Afterward, the generalized regression neural network is used to evaluate these trial vectors. In order to select the best candidate from these trial vectors, two rules are combined. The first is the feasibility rule, which at first guides the population toward the feasible region, and then toward the optimal solution. In addition, the second rule puts more emphasis on the solution with the highest predicted uncertainty, and thus alleviates the inaccuracy of the surrogates. In the local surrogate-assisted phase, the interior point method coupled with radial basis function is utilized to refine each individual in the population. During the evolution, the global surrogate-assisted phase has the capability to promptly locate the promising region and the local surrogate-assisted phase is able to speed up the convergence. Therefore, by combining these two important elements, the number of fitness evaluations can be reduced remarkably. The proposed method has been tested on numerous benchmark test functions from three test suites and two real-world cases. The experimental results demonstrate that the performance of the proposed method is better than that of other state-of-the-art methods.en
dc.language.isoen_USen
dc.publisherIEEE Pressen
dc.subjectExpensive constrained optimization problemsen
dc.subjectsurrogate modelen
dc.subjectglobal searchen
dc.subjectlocal searchen
dc.subjectdifferential evolutionen
dc.titleGlobal and local surrogate-assisted differential evolution for expensive constrained optimizationen
dc.typeArticleen
dc.identifier.doihttps://dx.doi.org/10.1109/TCYB.2018.2809430
dc.researchgroupCentre for Computational Intelligenceen
dc.peerreviewedYesen
dc.funderEPSRC (Engineering and Physical Sciences Research Council)en
dc.funderEU Horizon 2020 Marie Sklodowska-Curie Individual Fellowshipsen
dc.funderNational Natural Science Foundation of Chinaen
dc.projectidEP/K001310/1en
dc.projectid661327en
dc.projectid61673397en
dc.projectid61673331en
dc.cclicenceCC-BY-NCen
dc.date.acceptance2018-02-21en
dc.researchinstituteInstitute of Artificial Intelligence (IAI)en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record