A Novel Two-Stage Genetic Algorithm for Image Reconstruction of Electrical Resistance Tomography

Abstract

In this paper, we present a combined GA-ERT method based on two-stage genetic algorithm for image reconstruction in electrical resistance tomography (ERT). Image reconstruction in ERT is an ill-posed inverse problem and we have replaced the reverse solver by a two-stage optimization algorithm. The first stage of GA-ERT is reach to an approximate shape and location of the object. Also in this stage, we proposed a new electrode arrangement for ERT forward solver to reduce the process time of the forward problem. In the second stage, the GA employs result of the first stage as an initial population instead of a random group. Therefore with the local zoom, the GA can be employed to obtain the shape and location of the object more precisely. Experimental results of numerically solved ERT by the GA are also presented and compared to those obtained by other more established inversion methods such as modified Newton-Raphson (mNR) and RES2DINV program which is a standard 2-D resistivity inversion program. Results show that the proposed method can efficiently improve the ill-posed condition of ERT image reconstruction problem and can superiorly enhance the quality of ERT images.

Research on Image Reconstruction Algorithms for Tuber Electrical Resistance Tomography System

“…MNR algorithm is a kind of iterative reconstruction algorithm with a perfect and precise characteristics and better practical application, but it is not ideal in most cases because of the ill conditioned Hessian matrix. In some related literature, the genetic algorithm was used to study the imaging reconstruction of ERT [8] [9] . But it has defects of premature and the small processing dimension, easy to reach the local optimal solution, and is difficult to achieve effective convergence with hundreds of split units.…”