Electromagnetic imaging of buried perfectly conducting cylinder targets using the dynamic differential evolution

Abstract

Dynamic differential evolution (DDE) for shape reconstruction of perfect conducting cylinder buried in a half-space is presented. Assume that a conducting cylinder of unknown shape is buried in one half-space and scatters the field incident from another half-space where the scattered filed is measured. Based on the boundary condition and the measured scattered field, a set of nonlinear integral equations is derived and the imaging problem is reformulated into an optimization problem. The inverse problem is resolved by an optimization approach, and the global searching scheme DDE is then used to search the parameter space. Numerical results demonstrate that even when the initial guess is far away from the exact one, good reconstruction can be obtained by using DDE both with and without the additive Gaussian noise.

Accurate and robust inversion of buried objects based on the linear sampling method and differential evolution

“…Contrast source inversion (CSI) [21] is one of the most reliable non‐linear inversion techniques and has been revised to extend its application range [22, 23]. In addition to gradient methods, intellectual optimisation algorithms, such as differential evolution (DE) algorithm [24, 25] and particle swarm optimisation [9] are also competent candidates for solving optimisation problems. Furthermore, with the development of artificial intellectual, especially breakthroughs in deep learning, the deep neural network shows great potential in solving inverse scattering problems [26, 27] after sufficient training by specific data sets.…”

Electromagnetic scattering∼of metallic cylinders of arbitrary shape by using asynchronous particle swarm optimization and non-uniform steady state genetic algorithm

“…In general, they tend to get trapped in local minima when the initial trial solution is far away from the exact one. Thus, some population-based stochastic methods, such as genetic algorithms (GAs) [10,12,13,[17][18][19][20][21], differential evolution (DE) [11,[22][23][24][25][26][27], particle swarm optimization (PSO) [26][27][28][29], subspace-based optimization method [32], Neural network [33] and level-set algorithm [34] are proposed to search the global extreme of the inverse problems to overcome the drawback of the deterministic methods.…”

CLEAN Technique to Classify and Detect Objects in Subsurface Imaging

“…In the literature, some deterministic and stochastic approaches have been proposed for solving this problem. Stochastic approaches are global optimization methods and are usually based on populationbased solutions such as genetic algorithm, ant colony optimization, and particle swarm optimization, which are optimization methods used in electromagnetics for image reconstruction [10][11][12][13][14][15][16][17]. It is still a quite difficult task to develop effective reconstruction procedures, and better algorithms are still required.…”