Evolutionary algorithms, homomorphous mappings, and constrained parameter optimization
Evolutionary Computation
Self-adaptive fitness formulation for constrained optimization
IEEE Transactions on Evolutionary Computation
Knowledge and Information Systems
Arc-elasticity and hierarchical exploration of the neighborhood of solutions in mechanical design
Advanced Engineering Informatics
A distributed agent-based approach for simulation-based optimization
Advanced Engineering Informatics
Advanced Engineering Informatics
Hi-index | 0.00 |
Application of genetic algorithms to optimization of complex problems can lead to a substantial computational effort as a result of the repeated evaluation of the objective function(s) and the population-based nature of the search. This is often the case where the objective function evaluation is costly, for example, when the value is obtained following computationally expensive system simulations. Sometimes a substantially large number of generations might be required to find optimum value of the objective function. Furthermore, in some cases, genetic algorithm can face convergence problems. In this paper, a hybrid optimization algorithm is presented which is based on a combination of the neural network and the genetic algorithm. In the proposed algorithm, a back-propagation neural network is used to improve the convergence of the genetic algorithm in search for global optimum. The efficiency of the proposed computational methodology is illustrated by application to a number of test cases. The results show that, in the proposed hybrid method, the integration of the neural network in the genetic algorithm procedure can accelerate the convergence of the genetic algorithm significantly and improve the quality of solution.