The article develops a multi-criteria optimization method based on parallel modifications of single-criteria evolutionary algorithms, including Genetic, Grey Wolf Optimization, Particle Swarm Optimization. It is proposed to use two-component relative importance coefficients. An algorithm for normalizing the first component of coefficients based on solving a system of equations using Interval contractors has been developed. A multicomponent software package has been developed that allows implementing the developed optimization method and algorithm using parallel computing. Using the developed software package, the method was tested to solve the problem of optimizing the geometric parameters of a 3-DOF parallel robot.
Algorithm for Multi-criteria Optimization of Robot Parameters for Fruit Harvesting Based on Evolutionary Methods, Taking into Account the Importance of Criteria
Malyshev D.
;
2024-01-01
Abstract
The article develops a multi-criteria optimization method based on parallel modifications of single-criteria evolutionary algorithms, including Genetic, Grey Wolf Optimization, Particle Swarm Optimization. It is proposed to use two-component relative importance coefficients. An algorithm for normalizing the first component of coefficients based on solving a system of equations using Interval contractors has been developed. A multicomponent software package has been developed that allows implementing the developed optimization method and algorithm using parallel computing. Using the developed software package, the method was tested to solve the problem of optimizing the geometric parameters of a 3-DOF parallel robot.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
