A Surrogate Modeling Technique for Electromagnetic Scattering Analysis of 3-D Objects With Varying Shape

Abstract

A surrogate modeling technique for electromagnetic scattering analysis of 3-D objects with varying shape is presented by means of Gaussian process regression (GPR) and Bayesian committee machine (BCM). The technique based on GPR and BCM constructs surrogate models of 3-D objects with varying shape to reduce the expensive computational resource consumption of the electromagnetic scattering analysis. Based on the resample method, several subsets of training data are selected from the total training data set, and several subsurrogate models can be constructed by GPR with these subsets. The predicted values from each subsurrogate model for a test input can be fused by BCM to obtain the final predicted output with a high accuracy. For a series of test inputs on the varying geometric dimensions of objects, the uncertainty analysis of 3-D objects with varying shape will be achieved efficiently through a statistical analysis. Numerical results demonstrate the effectiveness of the proposed method.