论文部分内容阅读
花朵授粉算法是最近出现的一种新型元启发式群智能算法,已在无线传感网等应用领域取得了较好的成效,但也存在易陷入局部极值且演化后期收敛速度慢等缺陷,使其应用范围受到限制.针对该算法存在的不足,提出一种把复合形法的思想融入到花朵授粉算法中的混合算法.该算法首先计算当前种群的形心,然后依据形心将进化中最差的个体进行反射,把差的个体变成较好的个体,从而引导当前个体不断靠近最优解.通过10个标准测试函数的仿真实验,仿真结果表明,改进算法解的质量及收敛速度比基本的花朵授粉算法、蝙蝠算法及粒子群算法有较大幅度的提高.同时采用改进算法对非线性方程组问题进行求解,通过2个算例仿真实验,验证了改进算法的有效性,扩展了花朵授粉算法的应用领域.
The flower pollination algorithm is a new type of meta-heuristic swarm intelligence algorithm that has recently appeared. It has achieved good results in applications such as wireless sensor networks, but also has the defects of easy falling into local extremum and slow convergence in the late evolutionary stage. So that its application scope is limited.Aiming at the shortcoming of this algorithm, a hybrid algorithm is proposed to integrate the idea of complex method into the pollination algorithm of flowers.The algorithm first calculates the centroid of the current population, The worst individual is reflected, and the poor individual is changed into a better individual, thus leading the current individual to approach the optimal solution constantly.Through the simulation experiments of 10 standard test functions, the simulation results show that the quality of the improved algorithm and the convergence speed Compared with the basic flower pollination algorithm, the bat algorithm and the particle swarm algorithm, the improved algorithm is improved greatly. At the same time, the improved algorithm is used to solve the nonlinear equations, and the simulation results show that the improved algorithm is effective and extend Application of flower pollination algorithm.