|
基于BP神经网络的黄河下游洪水水位预测
|
Abstract:
按照黄河下游东平湖流域防御洪水调度方案要求,当东平湖水位高于汛限水位时,需向黄河分滞洪水,为了探寻更加符合本阶段防洪要求的预报方法,提高预报精度,构建了黄河下游孙口断面和艾山断面水位预报的BP神经网络模型。模型评定和检验表明,该方法计算效率高,对汛期日平均流量预测相对误差为5.1%,确定性系数为0.95,能为防汛调度提供决策依据和新的技术工具。
According to the requirements of the flood control plan of the Dongping Lake basin in the lower reaches of the Yellow River, when the water level of Dongping Lake is higher than the flood limit level, it is necessary to divert the flood to the Yellow River, in order to explore a forecast method that is more in line with the flood control requirements at this stage and improve the forecast accuracy, a BP neural network model for water level prediction of Sunkou section and Aishan section in the lower reaches of the Yellow River was constructed. The model evaluation and test show that the method has high computational efficiency, the relative error of the daily average flow prediction during the flood period is 5.1%, and the certainty coefficient is 0.95, which can provide a decision-making basis and new technical tools for flood control scheduling.
[1] | 西蒙·海金. 神经网络原理(第二版) [M]. 叶世伟, 史忠植, 译. 北京: 机械出版社, 2004. |
[2] | 温忠辉, 廖资生. 用神经网络模型预测济宁市地下水水位变化规律[J]. 水文地质工程地质, 1995(5): 16-18. |
[3] | 冯国章, 李佩成. 人工神经网络结构对径流预报精度的影响分析[J]. 自然资源学报, 1998, 13(2): 169-174. |
[4] | 洪小康. 渭河下游洪水预报的人工神经网络模型研究[J]. 西北农林科技大学学报(自然科学版), 2001(4): 93-96. |
[5] | 赵延涛, 姜宝良. 基于BP神经网络的地下水水位预测[J]. 勘察科学技术, 2001(4): 7-10. |
[6] | 李鑫, 刘艳丽, 朱士江, 等. 基于新安江模型和BP神经网络的中小河流洪水模拟研究[J]. 中国农村水利水电, 2022(1): 93-97. |
[7] | 郭秀秀. 基于BP神经网络工程造价预测模型分析[J]. 电子测试, 2022, 36(8): 38-40. |