首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于PCA-ESN模型的潘家口水库水位预测研究
引用本文:龚莎,彭宏玉.基于PCA-ESN模型的潘家口水库水位预测研究[J].唐山学院学报,2020,33(3):37-41,67.
作者姓名:龚莎  彭宏玉
作者单位:西南交通大学 唐山研究生院, 唐山 河北 063000,唐山学院 计算机科学与技术系, 唐山 河北 063000
基金项目:西南交通大学合作智慧水务项目(1200305);唐山市室内定位重点实验室建设项目(210050202)
摘    要:选择河北省潘家口水库为研究对象,采用PCA算法对数据进行预处理,选取新的主成分作为输入变量,再通过ESN模型对水库水位进行预测。实验结果表明,历史水位、降水量2个因素的变化对水位有较大的影响;ESN预测模型能较好地预测水位变化趋势,误差小,精度高,应用在水位预测上具有可行性和有效性。

关 键 词:潘家口水库  回声状态网络模型  主成分分析法  水位预测

Research on Water Level Forecast Based on PCA-ESN Model
GONG Sha and PENG Hong-yu.Research on Water Level Forecast Based on PCA-ESN Model[J].Journal of Tangshan College,2020,33(3):37-41,67.
Authors:GONG Sha and PENG Hong-yu
Institution:Graduate School of Tangshan, Southwest Jiaotong University;Tangshan 063000, China and Department of Computer Science and Technology, Tangshan University, Tanghan 063000, China
Abstract:With Panjiakou Reservoir in Hebei Province as the research object, the PCA algorithm is used to preprocess the data. Then, the new principal component is selected as the input variable, and the water level of this reservoir is forecast through the PCA-ESN model. The experimental results show that the two factors of historical water level and the rainfall have a great impact on the water level. The ESN model can better forecast the trend of the water level changes with small errors and high accuracy, which is feasible and effective in the forecast of water level.
Keywords:Panjiakou Reservoir  Echo State Network(ESN)model  Principal Component Analysis(PCA)  water level forecast
点击此处可从《唐山学院学报》浏览原始摘要信息
点击此处可从《唐山学院学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号