| 摘要 |
Systems and methods of consuming radial basis function (RBF) based meta-models are described. In one aspect, a product is to be designed and optimized with a set of design variables, objectives and constraints. A number of design of experimentals (DOE) points are identified. Each of the DOE points represents a particular or unique combination of design variables. Computer-aided engineering (CAE) analysis/analyses is/are then performed for each of the DOE points. A RBF based meta-model is created to approximate the CAE analysis results at all of the DOE points. A crowding distance is calculated for each DOE point. The DOE points are sorted accordingly in a predetermined criterion such as descending order, from which a predefined number of the DOE points are chosen as RBF neuron centers. RBF parameters such as function type, width and weight factor are adjusted so that the meta-model can substantially match the CAE analysis results.
|
