摘要
粒子群优化算法(PSO)是一种群体智能算法,通过粒子间的竞争和协作以实现在复杂搜索空间中寻找全局最优点。但基本PSO算法存在进化后期收敛速度慢、易陷入局部最优点的缺点,提出了一种多向学习型的粒子群优化算法,该算法中粒子通过同时追随自己找到的最优解、随机的其他粒子同维度的最优解和整个群的最优解来完成速度更新,通过判别区域边界来完成位置优化更新,通过对全局最优位置进行小范围扰动,以增强算法跳出局部最优的能力。对几种典型函数的测试结果表明:改进后的粒子群算法明显改善了全局搜索能力,并且能够有效避免早熟收敛问题。算法使高维优化问题中全局最优解相对搜索空间位置的鲁棒性得到了明显提高,适合于求解同类问题,计算结果能满足实际工程的要求。
Particle Swarm Optimization（PSO） is a new globe optimization algorithm based on swarm intelligent search. It is an algorithm for searching the global optimum in the complex space through cooperation and competition among the individuals in a population of particle. But the basic PSO has some demerits, such as relapsing into local extremum, slow convergence velocity and low convergence precision in the late evolutionary. This paper proposes an improved Particle Swarm Optimization algorithm （PSO）; the algorithm completes the optimization through following the personal best solution of each particle, the best solution of same dimensions of other stochastic particle and the global best value of the whole swarm on speed update, through judging by area boundary on position update. The experiment demonstrates that the proposed improved method is efficient and valid to solve the related problems, and avoid the premature convergence problem effectively, so it is suitable to be applied in the engineering.
出处
《计算机工程与应用》
CSCD
2013年第6期23-28,共6页
Computer Engineering and Applications
基金
安徽省自然科学基金资助项目(No.1208085ME62)
合肥工业大学博士学位专项科研资助基金(No.2011HGBZ0935)
关键词
粒子群优化算法
优化
群智能
多向学习
自适应
Particle Swarm Optimization（PSO） algorithm
optimization
swarm intelligence
comprehensive learning
self-adaptive
