摘要
该文针对传统智能优化算法中虚拟碰撞而导致的全局搜索效率降低的问题,提出一种模糊非基因信息记忆的双克隆选择算法。该算法设计基于模糊非基因信息的搜索机制与克隆选择原理相结合,对抗体进化中的非基因信息进行采集、模糊化并保存到记忆库,运用这些信息引导该抗体后续的双克隆搜索过程,从而减少非优区域的虚拟碰撞,提高全局搜索效率。通过标准测试函数的仿真试验并与其他算法比较,新算法表现出更快的全局收敛速度和更高的全局收敛精度。
To provide a better solution for search efficiency reduction problem caused by pseudo collision in the traditional intelligent optimization algorithms, this paper proposes a double clonal selection algorithm based on fuzzy non-genetic information memory. By combing with clonal selection theory, the search mechanism based on fuzzy non-genetic information memory is well performed. The non-genetic information in antibody evolution is collected, fuzzified and stored in the memory. Using this information to guide the subsequent double cloning search process, it can reduce the pseudo collision in non-optimal area, thus the global search efficiency is improved greatly. Extensive simulations show that the proposed algorithm has fast global convergence rate and high global convergence accuracy. Comparative results further demonstrate that it performs better than existing algorithms.
作者
宋丹
樊晓平
文中华
黄大足
屈喜龙
SONG Dan FAN Xiaoping WEN Zhonghua HUANG Dazu QU Xilong(College of Computer and Communication, Hunan Institute of Engineering, Xiangtan 411104, China School of Information Science and Engineering, Central South University, Changsha 410083, China Department of Information Management, Hunan University of Finance and Economics, Changsha 410205, China)
出处
《电子与信息学报》
EI
CSCD
北大核心
2017年第2期255-262,共8页
Journal of Electronics & Information Technology
基金
国家自然科学基金(61272295
61673164
61402540)
湖南省自然科学基金(2016JJ6031
2016JJ2040)
湖南省教育厅科学研究项目(16A049
13A010)~~
关键词
克隆选择
智能记忆
模糊信息
数值优化
Clonal selection
Intelligent memory
Fuzzy information
Numerical optimization
