一种改进的混合蛙跳算法及其在水浴牵伸控制中的应用  

An Improved Shuffled Frog Leaping Algorithm for Solving Controlled Optimization Problems of Water Bath Stretching Slot

作　　者：肖纯材[1] 郝矿荣[1,2] 丁永生[1,2] 

机构地区：[1]东华大学信息科学与技术学院,上海201620 [2]数字化纺织服装技术教育部工程研究中心,上海201620

出　　处：《华东理工大学学报（自然科学版）》2014年第1期102-106,共5页Journal of East China University of Science and Technology

基　　金：国家自然科学基金重点项目(61134009);长江学者和创新团队发展计划(IRT1220);上海市优秀学术带头人计划项目(11XD1400100);上海领军人才专项资金;上海市科学技术委员会重点基础研究项目(13JC1407500;11JC1400200);中央高校基本科研业务费专项资金

摘　　要：针对基本混合蛙跳算法的收敛速度慢、容易陷入局部最优的缺点,提出了一种基于细胞通信策略的改进算法,该算法通过修改更新策略,从而增加了种群的多样性,产生更多靠近优质解的个体。用典型测试函数对基本蛙跳算法和改进的蛙跳算法及其他算法进行对比实验,仿真结果表明改进的蛙跳算法能较大幅度提高收敛精度。将改进的蛙跳算法应用于碳纤维生产过程水浴牵伸控制系统的优化,仿真结果表明其具有较好的优化控制效果。Basic shuffled frog leaping algorithm （SFLA） easily traps into local minimum and has slower convergence. To overcome these shortcomings, this paper proposes an improved SFI.A, which combines the cell communication mechanism. By modifying the update formula, the improved algorithm can maintain the population diversity and enhance the convergence velocity and precision. The comparison with several kinds of optimization algorithms are made for four benchmark test functions. Experimental results show that the improved SFLA is effective and robust. Finally, the improved algorithm is applied to the optimization of the water bath stretching slot control system in carbon fiber production, which further demonstrates the effectiveness of the improved SFLA.

关 键 词：混合蛙跳算法 细胞通信策略 优化控制 碳纤维 水浴牵伸 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]