A Hybrid Evolutionary Algorithm to Solve Function Optimization

This paper proposes a rapid evolutionary algorithm to solve function optimization, by introducing compound crossover operator, make the search for the most favorable direction, and avoid the blind search; adopt no playback maximum select strategy and mutation operation which combines Gauss mutation with Cauchy mutation and introduce a non-linear fitness function which dynamically adjusts with evolution generation; particularly, through introducing a adaptive sub-space technology of search, accelerate the population convergence. Experimental results indicate that the algorithm is simple and efficient to seek the function optimal solution, especially for to-peak or low-dimensional function.