论文部分内容阅读
社会学习优化算法范型(Social Learning Optimization Algorithm Paradigm,SLO)是一种模拟人类社会智能演化过程的新型群体智能算法,该算法由三层协同进化的空间(微空间、学习空间、信仰空间)构成,其三个协同演化空间形成一个完整的闭环,符合人类社会智能演化的自然规律.SLO算法的模拟对象是具有最高智能水平的人类社会,具有较好的优化机理.然而,目前还不存在用于求解函数优化问题的SLO算法,针对这一问题,本文设计了面向函数优化问题的操作算子(主要包括交叉变异操作、模仿学习操作、观察学习操作),形成了面向函数优化问题的算法(F-SLO).最后,通过标准的测试函数与其他智能算法进行了比较,实验结果表明,本文所提出的面向函数优化的F-SLO算法在求解函数优化问题时具有较好的性能.
Social Learning Optimization Algorithm Paradigm (SLO) is a novel swarm intelligence algorithm that simulates the process of human social intelligent evolution. The algorithm consists of three levels of co-evolving space (micro-space, learning space, belief space) , And its three co-evolutionary spaces form a complete closed-loop, in line with the natural law of human society’s intelligent evolution.SLO algorithm simulation object is the highest intelligent level of human society, has a better optimization mechanism.However, there is no existing use In order to solve the problem of function optimization, aiming at this problem, this paper designs operation operators (including crossover mutation operation, imitation learning operation, observation and operation operation) oriented to function optimization problems, F-SLO) .Finally, the standard test function is compared with other intelligent algorithms. The experimental results show that the F-SLO algorithm proposed in this paper has better performance in solving the function optimization problem.