Improvement And Application Of Carnivorous Plant Optimization Algorithm

With the rapid development of modern industry,optimization problems in various fields have become more and more complex,so they cannot be solved efficiently by traditional methods.At the same time,the swarm intelligence optimization algorithms inspired by the behavior of biological groups in nature have gradually attracted the attention of scholars because of their high efficiency and easy scalability in solving large-scale problems.Besides,these algorithms have been widely used in many aspects.The carnivorous plant optimization algorithm is a kind of swarm intelligence optimization algorithm and it has achieved good results in solving problems such as state sequence search and robotic arm obstacle avoidance.But it still has some problems,for example,premature convergence,hard to keep a balance between global exploration and local exploitation,slow convergence,and so on.In this paper,two improved carnivorous plant optimization algorithms are proposed and applied to engineering design optimization and data clustering.The main research contents are as follows:(1)An opposition-based learning and neighborhood mutation based carnivorous plant optimization algorithm is proposed.In this method,an opposition-based learning strategy is added to the initialization of the population to improve the quality of the initial solution and speed up the convergence of the algorithm.When the algorithm falls into premature convergence,a neighborhood mutation mechanism will be introduced to generate new feasible solutions and help the algorithm effectively jump out of the local optimum.The proposed algorithm is compared with other 5 new swarm intelligence optimization algorithms on 10 standard test functions,and the results verify the good performance of the proposed algorithm.(2)A chaotic mapping and Levy flight based carnivorous plants optimization algorithm is proposed.This algorithm first performs chaotic mapping on the local optimal individuals in each iteration to enhance the diversity of the population and improve the global exploration ability.Then use the current global optimal individual to generate new Levy flight individuals to balance global exploration and local exploitation and obtain high-precision results.The proposed algorithm is compared with other 5 algorithms on 10 standard test functions,and the results show the effectiveness of the strategies.(3)To verify the practicability of the carnivorous plant algorithm and the proposed two improved algorithms,experiments are carried out on engineering-constrained optimization problems and data clustering problems.In terms of engineering design,three classic engineering optimization problems are used to test the performance of the algorithm;in terms of data clustering,five data sets are selected and three evaluation indicators are used to verify the competence of the algorithm.Experiments show that the proposed algorithms have certain application prospects in these two fields.