Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Electromagnetics
Genetic Algorithms in Electromagnetics
Introduction to Genetic Algorithms
Introduction to Genetic Algorithms
A fast and elitist multiobjective genetic algorithm: NSGA-II
IEEE Transactions on Evolutionary Computation
| Hi-index | 0.00 |
The paper presents a novel application of non-dominated sorting genetic algorithms NSGA-II to optimise the performance of plate-type electrostatic separator; an environmental friendly technique for selective sorting of conductive from nonconductive constituents of a granular mixture. As several decision variables control detachment of the particles from the plate; hence the separator's selectivity, NSGA-II is applied to determine their optimal values subject to simultaneous satisfaction of two proposed objective functions. These functions aim to maximise the separation distances, while maintaining the detachment fields, for different species. A GA-optimised charge simulation algorithm was developed to enable computations of detachment fields and positions of the particles. Two extreme solutions encompassing the other Pareto results are examined and analysed. The study illustrates the applicability of NSGA-II in solving the complex multiobjective optimisation problem of electrostatic separators in order to facilitate new development and designs of this environmental friendly technology.