In this study, the objective of the optimization of a double-suction pump is theudmaximization of its hydraulic efficiency. The optimization is performed, by means of theudmodeFRONTIER optimization platform, in steps. At first, by means of a DOE (Design ofudExperiments) strategy, the design space is explored, using a parameterized CAD representationudof the pump. Suitable metamodels (surrogates or Response Surfaces), which represent anudeconomical alternative to the more expensive 3D CFD model, are built and tested. Amonguddifferent metamodels, the evolutionary design, radial basis function and the stepwise regressionudmodels seem to be the most promising ones. Finally, the stepwise regression model, trained onuda set of 200 designs and constructed with only five the most influential input design parameters,udwas chosen as a potentially applicable metamodel.
展开▼