Dynamic Parameter Adaptation Using Interval Type-2 Fuzzy Logic in Bio-Inspired Optimization Methods

In this paper we perform a comparison of the use of type-2 fuzzy logic in two bio-inspired methods: Ant Colony Optimization (ACO) and Gravitational Search Algorithm (GSA). Each of these methods is enhanced with a methodology for parameter adaptation using interval type-2 fuzzy logic, where based on some metrics about the algorithm, like the percentage of iterations elapsed or the diversity of the population, we aim at controlling their behavior and therefore control their abilities to perform a global or a local search. To test these methods two benchmark control problems were used in which a fuzzy controller is optimized to minimize the error in the simulation with nonlinear complex plants.