基于遗传-细菌觅食组合算法的非线性模型优化

doi:10.16180/j.cnki.issn1007-7820.2019.05.004

摘要/Abstract

摘要：

文中提出一种遗传-细菌觅食组合优化算法以解决非线性模型优化问题。该方法先使用遗传算法进行全局搜索,并缩小最优解的搜索范围;再使用细菌觅食优化算法在该局部范围内执行局部搜索。这种组合搜索策略可以增强算法的收敛性,并能有效地均衡全局搜索和局部搜索。文中利用单峰、多峰和复杂多峰等非线性函数模型验证所提算法的性能。实验结果表明,组合算法的计算精度和效率分别比遗传算法和细菌觅食优化算法提高了30%和50%,表明该组合算法具有更快的收敛速度,更高的求解精度,适用于大规模多极值的非线性问题。

关键词: 遗传优化, 细菌觅食优化, 组合算法, 全局搜索, 局部搜索, 非线性模型

Abstract:

A combination of genetic algorithm and bacterial foraging optimization algorithm (GA-BFO) was presented to solve the nonlinear model optimization problems. Firstly, GA-BFO employed genetic algorithm to conduct global search and reduce the exploiting range of global optimum. Secondly, GA-BFO employed the bacterial foraging optimization algorithm to conduct local search in the reduced range. This combined search strategy could both enhance the convergence of GA-BFO and balance global search and local search. Three typical nonlinear function models including unimodal, multi-peak and complex multi-peak models were used to test the performance of the proposed algorithm. Experimental results showed that GA-BFO could achieve 30% and 50% precision improvements for GA and BFO respectively. Above results indicated the combined optimization approach had faster convergence speed and higher calculation precision, and it was more suitable for solving large-scale nonlinear problems with multiple optima.

Key words: genetic algorithm, bacterial foraging optimization, combination algorithm, global search, local search, nonlinear model

中图分类号:

TP18

李亚品,邹德旋,段纳. 基于遗传-细菌觅食组合算法的非线性模型优化[J]. 电子科技, 2019, 32(5): 16-20.

LI Yapin,ZOU Dexuan,DUAN Na. Optimization of Nonlinear Model Based on GA-BFO Combination Algorithm[J]. Electronic Science and Technology, 2019, 32(5): 16-20.

图/表 10

图1

图2

表1

图3

图4

表2

图5

图6

表3

图7

参考文献 16

[1]	Passino K M . Biomimicry of bacterial foraging for distributed optimization and control[J]. IEEE Control Systems Magazine, 2002(22):52-67.
[2]	邹彦艳, 吴宇轩, 宋振宇 , 等. 基于改进遗传算法的模糊控制器设计[J]. 自动化技术与应用, 2013,32(11):6-10.
	Zou Yanyan, Wu Yuxuan, Song Zhenyu , et al. Design of fuzzy controllers based on improved genetic algorithms[J]. Techniques of Automation and Applications, 2013,32(11):6-10.
[3]	王婷, 符小卫, 高晓光 . 基于改进遗传算法的异构多无人机任务分配[J]. 火力与指挥控制, 2013,38(5):37-41.
	Wang Ting, Fu Xiaowei, Gao Xiaogauang . Cooperative task a-ssignment for heterogeneous Multi-UAVs based on improved genetic algorithm[J]. Fire Control & Command Control, 2013,38(5):37-41.
[4]	祝慧灵, 计明军 . 集装箱船舶全航线配载优化模型与改进遗传算法[J]. 交通运输工程学报, 2014,14(5):59-67.
	Zhu Huiling, Ji Mingjun . Optimal model and improved genetic algorithm of containership stowage on full route[J]. J-ournal of Traffic and Transportation Engineering, 2014,14(5):59-67.
[5]	雷伟军, 程筱胜, 戴宁 , 等. 基于改进遗传算法的多模型加工路径规划[J]. 机械工程学报, 2014,50(11):153-161.
	Lei Weijun, Cheng Xiaosheng, Dai Ning , et al. Multi model machining path planning based on improved genetic algorithm[J]. Journal of Mechanical Engineering, 2014,50(11):153-161.
[6]	任乃飞, 于璐 . 基于混合遗传算法的协同制造系统调度研究[J]. 电子科技, 2016,29(6):29-33.
	Ren Naifei, Yu Lu . Research on scheduling for collaborative manufacturing system based on hybrid genetic algorithm[J]. Electronic Science and Technology, 2016,29(6):29-33.
[7]	王丽萍, 王渤权, 李传刚 , 等. 基于均匀自组织映射遗传算法的梯级水库优化调度[J]. 系统工程理论与实践, 2017,37(4):1072-1079.
	Wang Liping, Wang Boquan, Li Chuangang , et al. Optimiz-ation operation of cascade reservoirs by uniform self-organizing map-genetic algorithm[J]. Systems Engineering-Th-eory & Practice, 2017,37(4):1072-1079.
[8]	王飞平, 洪慧 . 基于改进型遗传算法的动态更新TTCAN系统技术[J]. 电子科技, 2017,30(8):40-43.
	Wang Feiping, Hong Hui . Dynamic update TTCAN system technique based on improved genetic algorithm[J]. Electronic Science and Technology, 2017,30(8):40-43.
[9]	郑史雄, 朱进波, 唐煜 , 等. 基于遗传混合算法的二维耦合颤振方法[J]. 西南交通大学学报, 2018,53(1):64-71.
	Zheng Shixiong, Zhu Jinbo, Tang Yu , et al. Two dimension-nal coupled flutter method based on genetichybrid algorithm[J]. Journal of Southwest Jiaotong University, 2018,53(1):64-71.
[10]	王振东, 陈峨霖, 胡中栋 . 混沌优化细菌觅食算法的传感器节点部署策略[J]. 传感技术学报, 2018,31(1):110-118.
	Wang Zhendong, Chen Elin, Hu Zhongdong . Sensor no-de deployment strategy of chaotic optimization of bacterial foraging algorithm[J]. Chinese Journal of Sensors and Actuators, 2018,31(1):110-118.
[11]	李珺, 党建武, 王垚 , 等. 多目标细菌觅食优化算法[J]. 计算机应用研究, 2018(7):1-2.
	LI Jun, Dang Jianwu, Wang Yao , et al. Multi-objec-tive bacteria foraging optimization algorithm[J]. Application Research of Computers, 2018(7):1-2.
[12]	张翼鹏, 葛丽娜, 王红 , 等. 基于改进细菌觅食算法的舆情热点话题发现[J]. 计算机工程与设计, 2017,38(10):2832-2837.
	Zhang Yipeng, Ge Lina, Wang Hong , et al. Cluster of p-eople opinion analysis based on improved bacterial f-oraging optimization[J]. Computer Engineering and Design, 2017,38(10):2832-2837.
[13]	马溪原, 吴耀文, 方华亮 , 等. 采用改进细菌觅食算法的风/光/储混合微电网电源优化配置[J]. 中国电机工程学报, 2011,31(25):17-25.
	Ma Xiyuan, Wu Yaowen, Fang Hualiang , et al. Optimal sizing of hybrid solar-wind distributed generation in an islanded microgrid using improved bacterial for aging algorithm[J]. Proceedings of the CSEE, 2011,31(25):17-25.
[14]	姜建国, 周佳薇, 郑迎春 , 等. 一种自适应细菌觅食优化算法[J]. 西安电子科技大学学报, 2015,42(1):75-81.
	Jiang Jianguo, Zhou Jiawei, Zheng Yingchun , et al. Adaptive bacterial foraging optimization algorithm[J]. Journal of Xidian University, 2015,42(1):75-81.
[15]	Kim D H, Cho J H. Adaptive tuning of PID controller for multivariable system using bacterial foraging based optimization[C]. Lodz:Advances in Web Intelligence Third International Atlantic Web Intelligence Conference,AWIC, 2005.
[16]	Kim D H, Cho J H . A biologically inspired intelligent PID controller tuning for AVR systems[J]. International Journal of Control,Automation and Systems, 2006,4(5):624-636.

算法	最优值	误差	代数	x₁	x₂	用时/s
GA	-173.131	7.26%	60	-0.862 7	-1.381	43
BFO	-184.961	0.93%	7	-0.908 3	-1.422 5	84
GA-BFO	-186.684	0.01%	14+3	-0.795 5	-1.422 5	24
真实值	-186.7			-0.800 3	-1.425 1

算法	最优值	误差	代数	x	y	用时/s
GA	1.983 8	7.77%	54	±0.417 7	±0.396 3	17
BFO	1.841 2	0.02%	10	±0.418 4	±0.448 7	33
GA-BFO	1.840 9	0.005%	26+2	±0.463 8	±0.464 2	12
真实值	1.840 8			±0.469 1	±0.464 4

算法	最优值	误差	代数	x	y	用时/s
GA	35.584 2	8.4%	77	9.321 4	5.144 0	17
BFO	33.641 0	13.4%	4	8.228 8	5.076 1	45
GA-BFO	36.844 6	5.7%	52+3	11.119 3	5.104 4	28
真实值	38.850 0			11.626 0	5.725 1