融合黎曼流量子学习ChOA算法的三维航迹规划
Three-dimension track planning based on Riemann flow sub learning chimp optimization algorithm
杨寅 1董大明2
作者信息
- 1. 山西职业技术学院智能制造工程(人工智能)系,山西太原 030006
- 2. 山西工程科技职业大学计算机工程学院,山西晋中 030619
- 折叠
摘要
针对传统方法的不足,提出一种融合黎曼流量子学习黑猩猩优化算法的三维航迹规划方法.为提高黑猩猩算法的寻优精度,引入非线性收敛因子均衡算法全局搜索与局部开发,设计自适应惯性权重提升算法全局搜索能力,融入黎曼流量子学习提高种群活跃度,避免生成局部最优解.建立三维航迹规划的约束模型和多目标代价函数,将航迹规划转化为多维函数优化问题,利用改进黑猩猩算法进行求解.实验结果表明,改进算法搜索精度更高,规划航迹能够规避所有威胁,具有更小的航迹代价.
Abstract
A three-dimensional path planning method integrating Riemann flow sub learning chimp optimizer was proposed for the shortage of traditional methods.For improving optimizing accuracy of chimp optimizer,the global search and local development of the equilibrium algorithm based on the adjustment mechanism of nonlinear convergence factor was introduced,and an adaptive inertia weight was designed to improve the global search capability of the algorithm.The Riemann flow sub learning was incorpo-rated to improve the population activity and to avoid the local optimum.A constraint model and multi-objective cost function of three-dimensional path planning were established,in which the path planning was transformed into a multi-dimensional function optimization problem.And the improved chimpanzee algorithm was used to solve the problem.The results show that the im-proved algorithm has higher search accuracy,whose planned track can avoid all threats and has less track cost.
关键词
航迹规划/黑猩猩算法/收敛因子/惯性权重/黎曼流/量子学习/航迹代价Key words
track planning/chimp algorithm/convergence factor/inertia weight/Riemann flow/sub learning/track cost引用本文复制引用
基金项目
教育部科技发展中心中国高校产学研创新基金-北创助教基金项目(2021BCE02013)
出版年
2024
NETL
NSTL
万方数据