基于遗传算法的农田灌溉管网分布优化模型构建  

Optimization model construction of farmland irrigation network distribution based on genetic algorithm

作　　者：赵彦琳[1] 张宇峰[1] ZHAO Yanlin;ZHANG Yufeng(Yangling Vocational Technical College,Yangling Shaanxi 712100,China)

机构地区：[1]杨凌职业技术学院,陕西杨凌712100

出　　处：《自动化与仪器仪表》2020年第9期186-189,195,共5页Automation & Instrumentation

基　　金：杨凌职业技术学院自然科学类研究基金项目“陕西省山丘区规模化灌溉管网系统的数值模拟研究”(No.A2018006)。

摘　　要：针对当前农田灌溉管网建设中的总投资与灌溉合理分布问题,提出一种组合遗传算法的农田灌溉管网的两级优化模型。在第1级中,针对传统遗传算法迭代缓慢的问题,采用Kruskal算法和Dijkstra对种群进行优化,从而提高迭代效率;在第2级管径优化中,针对传统二进制编码存在的问题,采用整数编码的方式对最小投资额小的最佳管径进行优化。最后采用MATLAB6.7仿真软件,设置遗传算法的相关参数,对上述方案进行验证。结果表明,构建的改进遗传算法迭代次数为5次的时候,即可求解最优解,同时迭代整体次数在100次。同时工程实例应用表明,构建的组合遗传算法在总投资额上要小于遗传算法,可节约8.4%的投资成本。由此,结果表明本算法的科学性。Aiming at the problem of total investment and rational distribution of irrigation in the construction of farmland irrigation network,a two-level optimization model of farmland irrigation network based on combined genetic algorithm is proposed.In the first stage,aiming at the problem of slow iteration of traditional genetic algorithm,Kruskal algorithm and Dijkstra are used to optimize the population,so as to improve the iteration efficiency;in the second stage,aiming at the problems of traditional binary coding,integer coding is used to optimize the optimal pipe diameter with the smallest investment.Finally,matlab6.7 simulation software is used to set the parameters of the genetic algorithm to verify the above scheme.The results show that when the number of iterations of the improved genetic algorithm constructed in this paper is 5,the optimal solution can be solved,and the overall number of iterations is 100.At the same time,the application of the project example shows that the total investment of the combined genetic algorithm is smaller than that of the genetic algorithm,which can save 8.4% of the investment cost.The results show that the algorithm is scientific.

关 键 词：单亲遗传算法 灌溉管网 目标函数 迭代 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]