
Research on the Man-machine Joint Calibration SWMM Based on BP Neural Networks
Han-liang GUI, Chun-ping ZHANG, Zhi-guo WU
Research on the Man-machine Joint Calibration SWMM Based on BP Neural Networks
In order to solve the problems of stormwater management model (SWMM) in calibration process, such as complex parameters and tedious process. This paper takes a certain block of Xining city as an example to establish SWMM model. Morris screening method is used to analyze the sensitivity of parameters, and artificial calibration is carried out according to the results of sensitivity analysis. In addition, BP neural network is used to calibrate the model, and parameter sensitivity is combined to optimize it. Through the analysis of three calibration schemes, the results show that the relative sensitivity of hydro-hydraulic module parameters is basically same, among which the more sensitive parameters are sub-catchment Area, Imperv and Destore-imperv. Moreover, the sensitivity of model parameters is different under different rainfall conditions. The optimized BP neural network parameter calibration method has the best simulation effect and the Nash coefficient is the largest. On the one hand, the method which combines with sensitivity to optimize BP neural network can improve the accuracy of BP neural network calibration, on the other hand, it can improve the efficiency of traditional artificial calibration.
SWMM / sensitivity analysis / Morris screening method / back propagation neural networks {{custom_keyword}} /
Tab.1 The characteristics of rainfall表1 降雨特征 |
序号 | 降雨 日期 | 降雨量/ mm | 降雨历时/ h | 平均雨强/ (mm·h-1) | 干期/ d |
---|---|---|---|---|---|
Rain1 | 07-01 | 33.5 | 15.0 | 2.33 | 7 |
Rain2 | 07-18 | 9.0 | 2.4 | 3.75 | 11 |
Tab.2 Range of calibration parameters of SWMM model表2 SWMM模型率定参数取值范围 |
类别 | 参数名称 | 物理意义 | 取值范围 | 人工 率定 | BP神经 网络 | 灵敏度优化 BP神经 网络率定 |
---|---|---|---|---|---|---|
子汇水区参数 | Area | 汇水单元面积 | GIS计算 | - | - | - |
Width | 特征宽度 | GIS计算 | - | - | - | |
Slope | 地表坡度 | GIS计算 | - | - | - | |
Imperv | 不透水区所占百分比 | GIS计算 | - | - | - | |
曼宁 粗糙率 | N-Imperv | 不透水区曼宁粗糙率 | 0.011~0.033 | 0.013 | 0.013 | 0.013 |
N-Perv | 透水区曼宁粗糙率 | 0.05~0.80 | 0.50 | 0.28 | 0.30 | |
Con-Roughness | 管道曼宁粗糙率 | 0.011~0.025 | 3.00 | 0.41 | 0.20 | |
蓄积量 参数 | Destore-Imperv | 不透水区洼地蓄积量/mm | 0.2~10.0 | 6.0 | 6.4 | 6.4 |
Destore-Perv | 透水区洼地蓄积量/mm | 2~10 | 0.013 | 0.013 | 0.013 | |
渗透 参数 | Max.Infil.Rate | Horton最大渗透率/% | 25~80 | 76.2 | 41.6 | 40.6 |
Min.Infil.Rate | Horton最小渗透率/% | 0~10 | 6.5 | 2.4 | 1.4 | |
Decay Constant | Horton渗透衰减系数 | 2~7 | 4.14 | 5.60 | 7.00 | |
Drying Time | 排干时间/d | 1~7 | 4.0 | 3.7 | 4.0 |
Tab.3 Sensitivity results of two rainfall events表3 两场降雨的灵敏度结果 |
类别 | 参数名称 | Rain 1 | Rain 2 | ||
---|---|---|---|---|---|
S灵敏度 | 灵敏度 等级 | S灵敏度 | 灵敏度 等级 | ||
子汇水区 参数 | Area | 0.908 | 灵敏 | 0.485 | 中度灵敏 |
Width | 0.001 | 不灵敏 | 0.010 | 不灵敏 | |
Slope | 0.002 | 不灵敏 | 0 | 不灵敏 | |
Imperv | 1.008 | 灵敏 | 0.529 | 中度灵敏 | |
曼宁 粗糙率 | N-Imperv | 0 | 不灵敏 | -0.016 | 不灵敏 |
N-Perv | -0.004 | 不灵敏 | -0.005 | 不灵敏 | |
Condit Roughness | -0.017 | 不灵敏 | -0.013 | 不灵敏 | |
蓄积量 参数 | Destore-Imperv | -0.213 | 灵敏 | -0.526 | 灵敏 |
Destore-Perv | -0.002 | 不灵敏 | -0.002 | 不灵敏 | |
Horton 入渗参数 | Max.Infil.Rate | -0.003 | 不灵敏 | -0.004 | 不灵敏 |
Min.Infil.Rate | -0.013 | 不灵敏 | -0.003 | 不灵敏 | |
Decay Constant | 0.003 | 不灵敏 | 0.004 | 不灵敏 | |
Drying Time | 0 | 不灵敏 | 0 | 不灵敏 |
Tab.4 Comparison of fitting results of three calibration methods表4 3种率定方法拟合计算结果对比 |
率定方法 | NSE | 工作量 | |
---|---|---|---|
Rain 1 | 灵敏度人工率定 | 0.532 | 较多 |
BP神经网络率定 | 0.745 | 较少 | |
灵敏度优化BP神经网络率定 | 0.861 | 较少 | |
Rain 2 | 灵敏度人工率定 | 0.487 | 较多 |
BP神经网络率定 | 0.851 | 较少 | |
灵敏度优化BP神经网络率定 | 0.872 | 较少 |
1 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
2 |
赵冬泉,陈吉宁,佟庆远,等.基于GIS构建SWMM城市排水管网模型[J].中国给水排水,2008(7):88-91.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
3 |
李德龙,程先云,杨 浩,等.人工智群算法在水文模型参数优化率定中的应用研究[J].水利学报,2013,44(增2):95-101.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
4 |
周思斯,杜鹏飞,逄 勇.城市暴雨管理模型应用研究进展[J].水利水电科技进展,2014,34(6):89-97.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
5 |
李春林,胡远满,刘 淼,等.SWMM模型参数局部灵敏度分析[J].生态学杂志,2014,33(4):1 076-1 081.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
6 |
周云峰,周永潮,郑春华,等.采用Sobol方法的暴雨径流管理模型参数灵敏度分析[J].浙江大学学报(工学版),2019,53(2):347-354.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
7 |
王 磊,周玉文.微粒群多目标优化率定暴雨管理模型(SWMM)研究[J].中国给水排水,2009,25(5):70-74.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
8 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
9 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
10 |
李宗礼,孙 伟,王中根,等.基于人机联合优化的SWAT模型参数率定方法研究[J].水力水电学报,2013,32(5):77-82.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
11 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
12 |
谭明豪,姚娟娟,张 智,等.基于Morris的SWMM水质参数灵敏度分析与应用[J].水资源与水工程学报,2015,26(6):117-122.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
13 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
14 |
黄金良,杜鹏飞,何万谦,等.城市降雨径流模型的参数局部灵敏度分析[J].中国环境科学,2007(4):549-553.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
15 |
林 杰,黄金良,杜鹏飞,等.城市降雨径流水文模拟的参数局部灵敏度及其稳定性分析[J].环境科学,2010,31(9):2 023-2 028.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
16 |
刘 飞,胡 斌,宋 丹,等.基于BP神经网络和均匀设计的边坡灵敏性分析[J].水电能源科学,2014,32(10):113-115.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
17 |
崔 巍,顾冉浩,陈奔月,等.BP与LSTM神经网络在福建小流域水文预报中的应用对比[J].人民珠江,2020,41(2):74-84.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
18 |
王浩昌,杜鹏飞,赵东泉,等.城市降雨径流模型参数全局灵敏度分析[J].中国环境科学,2008,28(8):725-729.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
19 |
王 竹,杨 旭,张 静,等.基于BP神经网络的大伙房水库洪水预报[J].水电能源科学,2016,34(4):31-34.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
20 |
熊剑智.城市雨洪模型参数灵敏度分析与率定[D].济南:山东大学,2016.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
21 |
马彦斌,盛 旺,李江云,等.基于遗传算法的SWMM模型参数率定研究[J].中国农村水利水电,2020(7):46-49,53.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
22 |
王中根,夏 军,刘昌明,等.分布式水文模型的参数率定及敏感性分析探讨[J].自然资源学报,2007(4):649-655.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
23 |
赵冬泉,陈吉宁,王浩正,等.城市降雨径流污染模拟的水质参数局部灵敏度分析[J].环境科学学报,2009,29(6):1 170-1 177.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |