Wing structural optimization using adaptive metamodels based on fuzzy clustering

For design problems involving computation-intensive analysis or simulation processes, approximation models are usually introduced to reduce computation time. An efficient global optimization method using adaptive radial basis function (RBF) based on fuzzy clustering (ARFC) is proposed. In this method, a novel algorithm of maximin Latin hypercube design (LHD) using successive local enumeration (SLE) is employed to obtain sample points with good performance in both space-filling and projective uniformity properties, which does a great deal of good to metamodels accuracy. RBF method is adopted for constructing the metamodels, whose features guarantee the metamodels accuracy with the increasing the number of sample points. The sample points in previous iterations are all inherited for constructing new metamodels. The fuzzy c-means clustering method is applied to identify attractive regions in the original design space. The numerical application examples are used for validating the performance of ARFC. Based on which a wing structure design optimization is carried out. Finally a set of optimal wing structural sizing and material properties parameters is obtained. Through the comparison with wing deformation under same mass before optimization, a more reasonable stiffness and mass distribution is obtained to achieve the minimal deformation.