基于改进鹈鹕优化算法的土壤污染预测  

Prediction of soil pollution based on improved pelican optimization algorithm

作　　者：高玉超 王占刚[1] GAO Yu-chao;WANG Zhan-gang(School of Information and Communication Engineering,Beijing Information Science and Technology University,Beijing 100101,China)

机构地区：[1]北京信息科技大学信息与通信工程学院,北京100101

出　　处：《计算机工程与设计》2024年第9期2852-2858,共7页Computer Engineering and Design

基　　金：国家重点研发计划基金项目(2018YFC1800203);北京市科技创新服务能力建设基金项目(PXM2019_014224_000026)。

摘　　要：针对传统污染扩散模型结构复杂、无法验证等问题,提出一种基于多策略改进鹈鹕优化算法的土壤污染扩散模型。引入拟蒙特卡罗序列优化鹈鹕优化算法初始种群位置,提出一种非线性收敛的e指数余弦因子改进位置更新方式,结合t-分布变异扰动策略提升算法局部寻优能力。利用改进的鹈鹕优化算法优化高斯扩散模型,构建土壤污染扩散模型。选取某地为研究区域,所构建的土壤污染扩散模型的平均绝对误差与均方根误差最低,验证该模型可以有效应用于土壤污染预测。To address the complex structure and the inability to verify traditional pollution diffusion models,a soil pollution diffusion model based on multi-strategy improved pelican optimization algorithm was proposed.A quasi Monte-Carlo sequence was introduced to optimize the initial population position of the pelican optimization algorithm.A nonlinear convergent e-index cosine factor was proposed to improve the position update method,and it was combined with a t-distribution mutation perturbation strategy to enhance the algorithm’s local optimization ability.The improved pelican optimization algorithm was used to optimize the Gaussian diffusion model and a soil pollution diffusion model was constructed.The average absolute error and root mean square error of the soil pollution diffusion model constructed in a certain area are the lowest,which verifies that the model can be effectively applied to the prediction of soil pollution.

关 键 词：鹈鹕优化算法 拟蒙特卡罗序列 e指数余弦因子 T-分布 高斯扩散模型 土壤污染预测 参数优化 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]