[1]叶汶建,王冰,王一荻.融合精英反向学习与纵横交叉的蛇优化算法[J].计算机技术与发展,2025,(10):148-157.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0135]
　YE Wen-jian,WANG Bing,WANG Yi-di.Snake Optimization Algorithm Combining Elite Inverse Learning and Crisscross Strategy[J].,2025,(10):148-157.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0135]
点击复制

融合精英反向学习与纵横交叉的蛇优化算法

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

卷:
期数:
2025年10期
页码:
148-157
栏目:
人工智能
出版日期:
2025-10-10

文章信息/Info

Title:
Snake Optimization Algorithm Combining Elite Inverse Learning and Crisscross Strategy
文章编号:
1673-629X(2025)10-0148-10
作者:
叶汶建1; 2; 王冰1; 2; 王一荻1; 2
1. 牡丹江师范学院 数学科学学院,黑龙江牡丹江 157011; 2. 牡丹江师范学院应用数学研究所,黑龙江牡丹江 157011
Author(s):
YE Wen-jian1; 2; WANG Bing1; 2; WANG Yi-di1; 2
1. School of Mathematical Sciences,Mudanjiang Normal University,Mudanjiang 157011,China; 2. Institute of Applied Mathematics,Mudanjiang Normal University,Mudanjiang 157011,China
关键词:
蛇优化算法; 精英反向学习; 纵横交叉策略; 函数优化问题; 工程优化问题
Keywords:
snake optimization algorithm;  elite inverse learning;  crisscross strategy;  function optimization problem;  engineering optimization problem
分类号:
TP301.6
DOI:
10.20165/j.cnki.ISSN1673-629X.2025.0135
摘要:
蛇优化算法(SO)是模拟自然界中蛇的习性而形成的一种元启发式算法。针对标准蛇优化算法在寻优时存在收敛速度慢且易陷入局部最优等问题,提出一种融合精英反向学习与纵横交叉的蛇优化算法(EILSO)。首先,通过变异精英反向学习策略初始化种群,利用精英个体生成高质量初始种群个体,加快算法收敛速度;其次,将振荡因子追随策略引入个体位置更新过程中,从而增强算法的探索能力、提高算法跳出局部最优的能力;最后,引入纵横交叉策略,其中,横向交叉增强算法的全局搜索能力、纵向交叉避免算法过早收敛,两种交叉相继进行共同提高算法的寻优性能。利用13个基准函数进行仿真测试,将EILSO与其他多种优化算法进行对比,证明EILSO收敛速度更快、求解精度更高、不易陷入局部最优。为了验证EILSO在实际问题中的可行性,将EILSO应用于齿轮系设计问题中,并与其他算法进行对比,结果显示EILSO在解决实际问题上具有一定的优越性。
Abstract:
The snake optimization algorithm (SO) is a meta-heuristic algorithm inspired by the behavior of snakes in nature. To address issues such as slow convergence and susceptibility to local optima in the standard SO,an enhanced snake optimization algorithm with elite inverse learning and crisscross strategy (EILSO) has been proposed. Firstly,initialize the population through a mutation-based elite inverse learning strategy,utilizing elite individuals to enhance the quality of the initial population,thereby accelerating the convergence speed of the algorithm. Secondly,an oscillation factor following strategy is incorporated into the process of updating individual positions,which enhances the algorithm's exploration capabilities and increases its ability to escape from local optima. Lastly,a cross-strategy that includes both lateral and longitudinal crossovers is introduced,lateral crossover strengthens the global search capability of the algorithm, while longitudinal crossover prevents premature convergence,these two types of crossovers are performed consecutively to improve the overall optimization performance of the algorithm. Simulation tests were conducted using 13 benchmark functions,comparing the EILSO against various other optimization algorithms. The results havedemonstrated that EILSO converges faster, achieves higher solution accuracy,and is less likely to get trapped in local optima. To validate the feasibility of EILSO in practical applications,it was applied to a gear system design problem and compared with other algorithms,the outcomes indicated that EILSO exhibits certain advantages in solving real-world problems.

相似文献/References:

[1]胡树斌,魏霖静.基于混合策略改进的麻雀搜索算法[J].计算机技术与发展,2023,33(04):146.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 022]
　HU Shu-bin,WEI Lin-jing.Improved Sparrow Search Algorithm Based on Hybrid Strategy[J].,2023,33(10):146.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 022]
[2]张 羽,何 庆.基于窦性变异的改进人工蜂群白骨顶鸡算法及应用[J].计算机技术与发展,2024,34(04):162.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 024]
　ZHANG Yu,HE Qing.Improved Artificial Bee Colony Coot Algorithm Based on Cosine Mutation and Its Application[J].,2024,34(10):162.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 024]
[3]权浩迪,刘勇国*,傅翀,等.多策略改进的蛇优化算法[J].计算机技术与发展,2024,34(05):117.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0049]
　QUAN Hao-di,LIU Yong-guo*,FU Chong,et al.Improved Snake Optimizer of Multi-strategy[J].,2024,34(10):117.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0049]

更新日期/Last Update: 2025-10-10