Multi-parent Crossover Algorithm Based on Dynamics
Tang Ming-duan · Jisuanji fangzhen · 2008
Multi-parent Crossover Algorithm selects some individuals to form a space and then do searching in this space.This algorithm has strong ability to find the solutions of the problem,and it also run quickly compared with other traditional algorithms.Dynamical Evolutionary Algorithm based on Statistical Mechanics simulates the movement of the particles in space.A new select mechanism was proposed in it.The numerical experiments show that Dynamical Evolutionary Algorithm is effective.A new Multi-parent Crossover Algorithm based on Dynamics unites the select mechanism of the Dynamical Evolutionary Algorithm with the evolutionary operations of Multi-parent Crossover was proposed.The algorithm also changed the replace strategy of the Multi-parent Crossover,and this change improved the algorithm's searching ability.Numerical experiments show that the convergence of the new algorithm is good,and the optimal solution can be found within a shorter period of time by using this new algorithm.