多策略蜂群算法及在数字系统建模中的应用

发布时间：2018-04-25 08:59

本文选题：人工蜂群算法 + 全局优化　；参考：《控制工程》2017年01期

【摘要】：为提高人工蜂群算法的全局搜索能力,提出一种多策略蜂群算法(multi-strategy based artificial bee colony algorithm:m ABC)。该算法设计一种基于最优蜜源的位置计算策略,然后与经典蜜源位置计算策略合作,在引领蜂阶段,以随机进化模式对蜜源进行更新,在跟随蜂阶段,以组合进化模式对蜜源进行更新。同时,设计一种基于差分进化算子的侦察蜂进化模式。对10个经典测试函数和2个数字系统建模问题进行实验仿真,实验结果表明,相比标准蜂群算法,m ABC算法模式有能效地平衡算法的探索和开发能力,提高收敛速度和最优解的精度,具有良好全局搜索效率,是一种有效的求解全局优化问题的方法。
[Abstract]:In order to improve the global search ability of artificial bee colony algorithm, a multi-strategy based artificial bee colony algorithm:m ABC algorithm is proposed. The algorithm designs a location calculation strategy based on the optimal honey source, and then collaborates with the classical nectar source location calculation strategy to update the honey source in the leading-bee stage with the random evolution model, and then updates the honey source in the following bee stage. The nectar source was updated by combinatorial evolution model. At the same time, a reconnaissance bee evolution model based on differential evolution operator is designed. Ten classical test functions and two digital system modeling problems are simulated. The experimental results show that compared with the standard bee colony algorithm, the model of m ABC algorithm has the ability to explore and develop the energy efficient balance algorithm. It is an effective method to solve the global optimization problem by improving the convergence rate and the accuracy of the optimal solution and has a good global search efficiency.
【作者单位】：上海工程技术大学机械工程学院;上海第二工业大学工学部;化工过程先进控制和优化技术教育部重点实验室;
【基金】：上海高校青年教师培养资助计划(ZZgcd14002) 上海市科委地方高校能力建设项目(14110501200)
【分类号】：TP18

【参考文献】