Array failure correction with a genetic algorithm

A flexible approach using the genetic algorithm (GA) is proposed for array failure correction in digital beamforming of arbitrary arrays. In this approach, beamforming weights of an array are represented directly by a vector of complex numbers. The decimal linear crossover is employed so that no binary coding and decoding is necessary. Three mating schemes, adjacent-fitness-paring (AFP), best-mate-worst (BMW), and emperor-selective (EMS), are proposed and their performances are studied. Near-solutions from other analytic or heuristic techniques may be injected into the initial population to speed up convergence. Numerical examples of single- and multiple-element failure correction are presented to show the effectiveness of the approach.