Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297833059> ?p ?o ?g. }
- W4297833059 endingPage "100059" @default.
- W4297833059 startingPage "100059" @default.
- W4297833059 abstract "We consider the problem of optimizing the design of a heat sink used for cooling an insulated gate bipolar transistor (IGBT) power module. The thermal behavior of the heat sink is originally estimated using a high-fidelity computational fluid dynamics (CFD) simulation, which renders numerical optimization too computationally demanding. To enable optimization studies, we substitute the CFD simulation model with an inexpensive polynomial surrogate model that approximates the relation between the device’s design features and a relevant thermal quantity of interest. The surrogate model of choice is a data-driven polynomial chaos expansion (DD-PCE), which learns the aforementioned relation by means of polynomial regression. Advantages of the DD-PCE include its applicability in small-data regimes and its easily adaptable model structure. To address the issue of model-form uncertainty and model robustness in view of limited training and test data, ensembles of DD-PCEs are generated based on data re-shuffling. Then, using the full ensemble of surrogate models, the surrogate-based predictions are accompanied by uncertainty metrics such as mean value and variance. Once trained and tested in terms of accuracy and robustness, the ensemble of DD-PCE surrogates replaces the high-fidelity simulation model in optimization algorithms aiming to identify heat sink designs that optimize the thermal behavior of the IGBT under geometrical and operational constraints. Optimized heat sink designs are obtained for a computational cost much smaller than utilizing the original model in the optimization procedure. Due to ensemble modeling, the optimization results can also be assessed in terms of uncertainty and robustness. Comparisons against alternative surrogate modeling techniques illustrate why the DD-PCE should be preferred in the considered setting." @default.
- W4297833059 created "2022-10-01" @default.
- W4297833059 creator A5003631344 @default.
- W4297833059 creator A5013517565 @default.
- W4297833059 date "2022-01-01" @default.
- W4297833059 modified "2023-10-01" @default.
- W4297833059 title "Power module heat sink design optimization with ensembles of data-driven polynomial chaos surrogate models" @default.
- W4297833059 cites W1133323860 @default.
- W4297833059 cites W1863376475 @default.
- W4297833059 cites W1963846586 @default.
- W4297833059 cites W1965093639 @default.
- W4297833059 cites W1967989271 @default.
- W4297833059 cites W1980635834 @default.
- W4297833059 cites W1984943006 @default.
- W4297833059 cites W1986595352 @default.
- W4297833059 cites W2013695155 @default.
- W4297833059 cites W2018159038 @default.
- W4297833059 cites W2018516445 @default.
- W4297833059 cites W2019722786 @default.
- W4297833059 cites W2045355467 @default.
- W4297833059 cites W2049774453 @default.
- W4297833059 cites W2054757562 @default.
- W4297833059 cites W2056558085 @default.
- W4297833059 cites W2060794175 @default.
- W4297833059 cites W2063978378 @default.
- W4297833059 cites W2070147180 @default.
- W4297833059 cites W2077780148 @default.
- W4297833059 cites W2083042020 @default.
- W4297833059 cites W2083415217 @default.
- W4297833059 cites W2083545545 @default.
- W4297833059 cites W2088990166 @default.
- W4297833059 cites W2089123494 @default.
- W4297833059 cites W2090171599 @default.
- W4297833059 cites W2093229042 @default.
- W4297833059 cites W2111959010 @default.
- W4297833059 cites W2118340938 @default.
- W4297833059 cites W2126105956 @default.
- W4297833059 cites W2164452299 @default.
- W4297833059 cites W2166849702 @default.
- W4297833059 cites W2167566180 @default.
- W4297833059 cites W2168170318 @default.
- W4297833059 cites W2299367673 @default.
- W4297833059 cites W2321957512 @default.
- W4297833059 cites W2344110434 @default.
- W4297833059 cites W2376314300 @default.
- W4297833059 cites W2543580944 @default.
- W4297833059 cites W2564963919 @default.
- W4297833059 cites W2597578662 @default.
- W4297833059 cites W2696437456 @default.
- W4297833059 cites W2753125409 @default.
- W4297833059 cites W2768868668 @default.
- W4297833059 cites W2776810973 @default.
- W4297833059 cites W2784141616 @default.
- W4297833059 cites W2784834815 @default.
- W4297833059 cites W2786232134 @default.
- W4297833059 cites W2884165914 @default.
- W4297833059 cites W2887205128 @default.
- W4297833059 cites W2908541468 @default.
- W4297833059 cites W2954325526 @default.
- W4297833059 cites W2962852715 @default.
- W4297833059 cites W3021613070 @default.
- W4297833059 cites W3039084241 @default.
- W4297833059 cites W3100128089 @default.
- W4297833059 cites W3102703068 @default.
- W4297833059 cites W3124114587 @default.
- W4297833059 cites W3155144294 @default.
- W4297833059 cites W4207004565 @default.
- W4297833059 cites W4250955649 @default.
- W4297833059 cites W748734575 @default.
- W4297833059 doi "https://doi.org/10.1016/j.prime.2022.100059" @default.
- W4297833059 hasPublicationYear "2022" @default.
- W4297833059 type Work @default.
- W4297833059 citedByCount "0" @default.
- W4297833059 crossrefType "journal-article" @default.
- W4297833059 hasAuthorship W4297833059A5003631344 @default.
- W4297833059 hasAuthorship W4297833059A5013517565 @default.
- W4297833059 hasBestOaLocation W42978330591 @default.
- W4297833059 hasConcept C104317684 @default.
- W4297833059 hasConcept C105795698 @default.
- W4297833059 hasConcept C11413529 @default.
- W4297833059 hasConcept C119857082 @default.
- W4297833059 hasConcept C126255220 @default.
- W4297833059 hasConcept C127413603 @default.
- W4297833059 hasConcept C131675550 @default.
- W4297833059 hasConcept C146978453 @default.
- W4297833059 hasConcept C1633027 @default.
- W4297833059 hasConcept C185592680 @default.
- W4297833059 hasConcept C186937647 @default.
- W4297833059 hasConcept C19499675 @default.
- W4297833059 hasConcept C197656079 @default.
- W4297833059 hasConcept C33923547 @default.
- W4297833059 hasConcept C41008148 @default.
- W4297833059 hasConcept C55493867 @default.
- W4297833059 hasConcept C63479239 @default.
- W4297833059 hasConcept C78519656 @default.
- W4297833059 hasConceptScore W4297833059C104317684 @default.
- W4297833059 hasConceptScore W4297833059C105795698 @default.
- W4297833059 hasConceptScore W4297833059C11413529 @default.