欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
径流预测历来是水利部门的一项重要工作,本文基于支持向量机（SVM）方法建立河川径流中长期预测模型,通过对1976-1994年黄河上游兰州站径流量历史数据分析处理后,得到年径流量增长的时间序列,利用所建模型对该序列值进行仿真模拟。在仿真实验后,用1995-1996年的增长量进行模型检验,并与RBF网络模型、BP神经网络模型预测结果进行对比,结果表明,应用SVM模型对年径流量进行预测,预测精度更高、效果更好。
英文摘要：
Runoff prediction is an important responsibility of water conservancy departments. The support vector machine （SVM） model of mid-long term prediction of runoff in stream is established in this paper. By processing the statistic data of runoff from 1976 to 1994, the temporal sequence of increments of annual runoff is obtained. Using the model simulated on the statistic data, the learning and training simulation experiments are completed, the model is established and verified by use of runoff increments from 1995 to 1996. Comparing with the RBF network model and the BP neural network model, the SVM model is more precise and effective in annual runoff prediction.
同期刊论文项目
同项目期刊论文
期刊信息
位置：