High-efficiency global optimization method using adaptive radial basis function based on fuzzy clustering

Abstract

The invention relates to a high-efficiency global optimization method using adaptive radial basis function based on fuzzy clustering, belonging to the technical field of modern engineering optimization designing. The method comprises the following steps: gradually constructing a proxy model of a complicated analysis model relating to an engineering design problem by the adaptive radial basis function; classifying the function values of a proxy model on a known mesh point aiming at the proxy model by adopting a fuzzy clustering method; searching a key area which is possibly saved to the global optimal point; and optimizing the proxy model by using the global optimizing algorithm in a small range in the key area until the optimal value of the engineering design problem is acquired. The optimization method overcomes the defect of time-consuming operation when the traditional global optimization method is used in the engineering design problem, can effectively reduce operation cost, improve optimization efficiency, is advantageous to shortening the period of engineering optimization design, and has the capability of global searching.

Description

technical field [0001] The invention relates to an efficient fuzzy clustering-based adaptive radial basis global optimization method, which belongs to the technical field of modern engineering optimization design. Background technique [0002] In order to improve the quality of engineering design, more and more methods and ideas of optimal design are applied to engineering design, such as aircraft optimal design, automobile optimal design, etc., and modern engineering design problems are becoming more and more complex. On the one hand, in order to improve the analysis accuracy and reliability, high-precision analysis models are widely used in engineering design, such as the finite element analysis (FEA) model used in structural analysis, computational fluid dynamics (CFD) analysis used in aerodynamic analysis model etc. While improving the accuracy and reliability of the analysis, the high-precision analysis model also brings the difficulty of time-consuming calculations. A...

AI Technical Summary

Problems solved by technology

[0055] The object of the present invention is to solve the problems of ARSM global optimization method, such as complex calculation, time-consuming calculation, and possible omission of optimal points, and proposes an efficient global optimization method using Adaptive RBF based on Fuzzy Clustering C1ustering, ARFC) method can be used for modern complex engineering optimization design problems, especially for the optimization field with huge amount of calculation in engineering design, such as structural optimization design with large-scale finite element analysis, aerodynamic optimization with high-precision computational fluid dynamics analysis Design, etc., can be widely used in the field of aerospace or related engineering optimization design

Images