基于GWO-ELM算法模型的水体含沙量预测
DOI:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

P338+.5

基金项目:

陕西省自然科学基础研究计划项目(NO.2019JQ-206);陕西省教育厅科学研究项目 (NO.17JK0346)


Prediction of water sediment concentration based on GWO-ELM algorithm model
Author:
Affiliation:

Fund Project:

Basic research program of Natural Science in Shaanxi Province(NO.2019JQ-206);Scientific research project of Shaanxi Provincial Department of Education(NO.17JK0346)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    泥沙含量的演变受多种因素的影响,为了快速、准确的对水中泥沙含量进行高精度预测,为泥沙治理以及合理利用水土资源提供理论依据,提出了一种基于GWO-ELM算法模型的水体含沙量预测方法。首先,将影响泥沙含量的8种原始影响因子赋予权重,利用主成分分析(Principal Component Analysis,PCA)法提取出4个主成分影响因子,避免维数灾难;然后,将提取出来的因子作为极限学习机(Extreme Learning Machine,ELM)算法模型的输入,进行泥沙含量的预测,并使用灰狼优化算法(Grey Wolf Optimizer,GWO)更新预测模型的最优参数;最后,以长江口北槽监测数据进行了仿真验证。结果表明:本文所提方法有效的降低了维数灾难,且提高了在相同隐含层神经元节点数情况下的预测准确率,预测值与实际值拟合效果较好,预测精度较高。本研究说明了GWO-ELM模型可用于对泥沙含量的预测,为相关决策部门提供了一定的借鉴经验。

    Abstract:

    The evolution of sediment content is affected by many factors. In order to quickly and accurately predict the sediment content in water with high precision, and to provide theoretical basis for sediment management and rational utilization of water and soil resources, a prediction method of water sediment content based on GWO-ELM algorithm model was proposed. Firstly, eight original influencing factors of sediment content were weighted, and four Principal Component factors were extracted by Principal Component Analysis (PCA) to avoid dimensional disaster. Then, the extracted factors were used as the input of the Extreme Learning Machine (ELM) algorithm model to predict the sediment content, and Grey Wolf Optimizer (GWO) was used to update the optimal parameters of the prediction model. Finally, the simulation verification is carried out based on the monitoring data of the north channel of the Changjiang Estuary. The results show that the method proposed in this paper can effectively reduce the dimensional disaster, and improve the prediction accuracy under the same number of hidden layer neurons. The predicted value has a good fitting effect with the actual value, and the prediction accuracy is high. This study shows that GWO-ELM model can be used to predict sediment content, which provides some reference experience for relevant decision-making departments.

    参考文献
    相似文献
    引证文献
引用本文

何洋,李丽敏,温宗周,等. 基于GWO-ELM算法模型的水体含沙量预测[J]. 科学技术与工程, 2022, 22(3): 910-917.
He Yang, Li Limin, Wen Zongzhou, et al. Prediction of water sediment concentration based on GWO-ELM algorithm model[J]. Science Technology and Engineering,2022,22(3):910-917.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-05-23
  • 最后修改日期:2021-10-27
  • 录用日期:2021-08-31
  • 在线发布日期: 2022-01-27
  • 出版日期:
×
律回春渐,新元肇启|《科学技术与工程》编辑部恭祝新岁!
亟待确认版面费归属稿件,敬请作者关注