基于改进麻雀搜索算法的北疆春玉米产量预测方法  

Prediction method of spring maize yield in Northern Xinjiang based on improved sparrow search algorithm

作　　者：崔兴华 靳晟[1] CUI Xing-hua;JIN Sheng(Department of Computer and Information Engineering,Xinjiang Agricultural University,Urumqi 830052,China)

机构地区：[1]新疆农业大学计算机与信息工程学院,新疆乌鲁木齐830052

出　　处：《计算机工程与设计》2023年第8期2531-2540,共10页Computer Engineering and Design

基　　金：新疆高技术研究发展计划基金项目(2015X0102);新疆农业信息化工程技术研究中心基金项目(2520HXKT2)。

摘　　要：针对新疆北疆地区在玉米生产中存在的生产效率低下问题,提出一种基于改进麻雀搜索算法的北疆春玉米产量预测方法。为改善麻雀搜索算法全局搜索能力弱的缺陷,加入Kent映射丰富初始种群的多样性,结合反向学习策略调整跟随者位置更新策略;为增强易麻雀搜索算法跳出局部极值点的能力,引入融合柯西变异和高斯变异的食物源机制。通过数值实验将改进后的麻雀搜索算法与4种相关算法对比,结果表明,改进后的麻雀搜索算法在收敛速度及精度上更具优势。将改进的麻雀搜索算法与径向基神经网络结合构建玉米产量预测模型,并设计仿真实验验证了模型的有效性。Aiming at the low production efficiency in maize production in Northern Xinjiang,a prediction method of spring maize yield in Northern Xinjiang based on improved sparrow search algorithm was proposed.To improve the weak global search ability of sparrow search algorithm,Kent mapping was added to enrich the diversity of initial population,and the follower position update strategy was adjusted combined with opposition-based learning.The food source mechanism integrating Cauchy variation and Gaussian variation was introduced to enhance the ability of algorithm to jump out of local extreme points.In the numerical experiment,the improved sparrow search algorithm was compared with four related algorithms.The results show that the improved sparrow search algorithm has more advantages in convergence speed and accuracy.The improved sparrow search algorithm was combined with radial basis function neural network to construct the maize yield prediction model,and the effectiveness of the model was verified by simulation experiment.

关 键 词：玉米 麻雀搜索算法 Kent映射 反向学习策略 食物源机制 径向基神经网络 产量预测 

分 类 号：TP389.1[自动化与计算机技术—计算机系统结构]