[1]李梦真,莫愿斌.融合多策略的改进黏菌算法及工程应用[J].计算机技术与发展,2024,34(02):214-220.[doi:10. 3969 / j. issn. 1673-629X. 2024. 02. 031]
 LI Meng-zhen,MO Yuan-bin.Improved Slime Mould Algorithm with Fusion of Multiple Strategies and Engineering Application[J].,2024,34(02):214-220.[doi:10. 3969 / j. issn. 1673-629X. 2024. 02. 031]
点击复制

融合多策略的改进黏菌算法及工程应用()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
34
期数:
2024年02期
页码:
214-220
栏目:
新型计算应用系统
出版日期:
2024-02-10

文章信息/Info

Title:
Improved Slime Mould Algorithm with Fusion of Multiple Strategies and Engineering Application
文章编号:
1673-629X(2024)02-0214-07
作者:
李梦真莫愿斌
广西民族大学 人工智能学院,广西 南宁 530006
Author(s):
LI Meng-zhenMO Yuan-bin
School of Artificial Intelligence,Guangxi Minzu University,Nanning 530006,China
关键词:
黏菌算法Sine 混沌映射自适应 t 分布黄金正弦算法工程优化问题
Keywords:
slime mould algorithmSine chaotic mapadaptive t distributiongolden sine algorithmengineering optimization problem
分类号:
TP18
DOI:
10. 3969 / j. issn. 1673-629X. 2024. 02. 031
摘要:
黏菌优化算法(Slime Mould Algorithm,SMA)是根据黏菌个体振荡捕食行为提出的一种新型元启发式算法,因其原理简单被应用于多种复杂的优化问题中,基本的 SMA 在处理一些较为复杂的问题时仍然存在收敛速度较慢、精度不足、鲁棒性差等劣势。 为克服这些缺点,提升原算法性能,提出一种融合 Sine 混沌映射、 t 分布以及黄金正弦策略的改进黏菌算法( GTSMA) 。 首先,引入 Sine 混沌序列初始化种群,提高算法在初始迭代过程中黏菌种群个体的多样性;其次,在黏菌个体更新位置过程中将自由度参数 t 与基本 SMA 融合,增加算法跳出局部最优的概率;最后,通过与黄金正弦算法相结合,挑选更优秀的黏菌个体,输出最优解。 利用基准测试函数、CEC2021 测试集将 GTSMA 与其他算法进行对比,实验结果表明 GTSMA 在测试过程中鲁棒性、寻优精度和收敛性能都优于其他算法。 将 GTSMA 应用于工程优化问题,进一步验证了 GTSMA 在处理实际优化问题上的优越性。
Abstract:
Slime mould algorithm ( SMA) is a new meta heuristic algorithm based on the oscillatory predatory behavior of slime mouldindividuals. Because of its simple principle,SMA has been applied to a variety of complex optimization problems. The basic SMA stillhas disadvantages such as slow rate of convergence,insufficient accuracy,and poor robustness when dealing with some more complexproblems. To overcome these shortcomings and improve the performance of the original algorithm,we propose an improved slime mouldalgorithm ( GTSMA)?
that integrates sine chaotic mapping, t -distribution,and golden sine strategy. Firstly,the Sine chaotic sequence isintroduced to initialize the population and improve the diversity of the slime mould population during the initial iteration process of the algorithm. Secondly,in the process of updating the position of slime mould individuals,the degree of freedom parameter?
t is fused with thebasic SMA to increase the probability of the algorithm jumping out of local optima. Finally, by combining with the golden sinealgorithm,better slime mould individuals are selected to output the optimal solution. The benchmark test function and CEC2021 test setwere used to compare the test results of GTSMA with other algorithms. Experimental results show that GTSMA has better robustness,optimization accuracy and convergence performance than that of other algorithms during the test. Applying GTSMA to engineeringoptimization problems further validates its superiority in handling practical optimization problems.
更新日期/Last Update: 2024-02-10