基于混合策略改进的鹈鹕优化算法

Pelican optimization algorithm improved based on hybrid strategy

针对鹈鹕优化算法求解精度低、稳定性不足、易陷入局部最优等问题,文章提出一种混合策略改进的鹈鹕优化算法(IPOA)。首先,为了增强种群的随机性和多样性,扩大种群的搜索范围,引入反向折射学习机制;其次,利用正余弦算法和鹈鹕算法融合,改进鹈鹕搜索猎物的方式,增强算法的局部搜索与全局搜索能力;然后,采用Levy飞行机制对鹈鹕位置进行更新,从而提高算法的搜索能力以寻找最优值;最后,引入自适应t分布变异算子,使用算法的迭代次数作为t分布的自由度参数来增强鹈鹕种群的多样性,避免算法陷入局部最优。通过12个标准测试函数对改进算法与海鸥优化算法、黑猩猩优化算法、鲸鱼优化算法、蛇群优化算法和基本鹈鹕优化算法进行测试比较,结果表明,IPOA具有更好的收敛速度和稳定性。最后将改进鹈鹕算法应用于压力容器设计优化问题,进一步证实改进后的算法具有较好的求解性能。

Aiming at the problems of low solving accuracy,insufficient stability,and easy to fall into local optimization of the pelican optimization algorithm,a improved pelican optimization algorithm(IPOA)with improved hybrid strategy is proposed.Firstly,in order to enhance the randomness and diversity of the population,expand the search range of the population,introduce the back-refraction learning mechanism.Secondly,the fusion of sine-cosine algorithm and pelican algorithm is used to improve the way of pelican search for prey,and enhance the local search and global search capabilities of the algorithm.Then,the Levy flight mechanism is used to update the position of the pelican,so as to improve the search ability of the algorithm to find the optimal value.Finally,an adaptive t-distribution variation operator is introduced,and the number of iterations of the algorithm is used as the degree-offreedom parameter of the t-distribution to enhance the diversity of pelican populations and avoid the algorithm falling into local optimum.The improved algorithm is compared with the seagull optimization algorithm,chimpanzee optimization algorithm,whale optimization algorithm,snake swarm optimization algorithm,and basic pelican optimization algorithm through 12 standard test functions,and the results show that IPOA has better convergence speed and stability.Finally,the improved Pelican algorithm is applied to the pressure vessel design optimization problem,which further proves that the improved algorithm has good solution performance.