基于FFA-GRNN模型的土石坝溃坝洪峰流量预测

严新军; 王雪虎; 赵蕊婷; 庄培源; 王红徐; 马俊玲

doi:10.11988/ckyyb.20231271

PDF(6080 KB)

raybet体育在线院报 ›› 2025, Vol. 42 ›› Issue (3) : 99-106. DOI: 10.11988/ckyyb.20231271

水灾害

基于FFA-GRNN模型的土石坝溃坝洪峰流量预测

严新军 ¹^,² ,
王雪虎 ¹ ,
赵蕊婷 ¹ ,
庄培源 ¹ ,
王红徐 ¹ ,
马俊玲 ¹

作者信息 +

Predicting Peak Discharge at Earth Rock Dam Break Based on FFA-GRNN Model

Author information +

文章历史 +

摘要

为提高溃坝洪峰流量预测精度,提出了一种基于GRNN的预测模型,结合耳廓狐优化算法FFA进行超参数优化,实现对溃坝洪峰流量的预测。以国内外堤坝溃决数据库为基础,用溃口底部以上库容、溃口底部以上水深和溃口深度3种因子作为输入变量,构建FFA-GRNN溃坝洪峰流量预测模型。为验证模型在溃坝洪峰流量预测精确度和拟合度,与其他4种智能算法进行对比。结果表明:提出的FFA-GRNN模型相较于其他模型具有更低的RMSE、MAE和更高的拟合度R²,证明所建模型在整体上具有更好的计算精度与拟合效果。通过分析模型在溃坝洪峰流量预测中的适用性,可为溃坝分析提供技术支撑。

Abstract

The accuracy of predicting the peak flood flow at the breach of earth-rock dam is crucial for dam break analysis. To improve the prediction accuracy of the post-breach peak flood flow, this paper presents a prediction model based on the General Regression Neural Network (GRNN), optimized by the Fennec Fox Optimization (FFA) algorithm for hyperparameters, to forecast the peak flood flow caused by dam breaches. Using a database of domestic and international dam failure cases, the model selects three factors as input variables: the reservoir capacity above the breach bottom, the water depth above the breach bottom, and the breach depth, to build the FFA-GRNN prediction model. To evaluate the model’s precision and fitting accuracy in predicting peak flood discharge at dam break, we compared it with four other intelligent algorithms. Results show that the proposed FFA-GRNN model has a lower Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and a higher coefficient of determination (R²) than other models, indicating superior computational precision and fitting performance.

导出引用

严新军, 王雪虎, 赵蕊婷, 等. 基于FFA-GRNN模型的土石坝溃坝洪峰流量预测[J]. raybet体育在线院报. 2025, 42(3): 99-106 https://doi.org/10.11988/ckyyb.20231271

YAN Xin-jun, WANG Xue-hu, ZHAO Rui-ting, et al. Predicting Peak Discharge at Earth Rock Dam Break Based on FFA-GRNN Model[J]. Journal of Changjiang River Scientific Research Institute. 2025, 42(3): 99-106 https://doi.org/10.11988/ckyyb.20231271

中图分类号： TV122 (洪水)

参考文献

列表( 原文顺序 | 文献年度倒序 | 文中引用次数倒序 ) 可视化分析

[1]	水利部大坝安全管理中心. 垮坝登记册[R]. 南京: 水利部大坝安全管理中心, 2021. (Dam Safety Management Center of the Ministry of Water Resources. Nanjing: Dam Safety Management Center of the Ministry of Water Resources, 2021. (in Chinese)) 本文引用 [1]

[2]	WU W M. Earthen Embankment Breaching[J]. Journal of Hydraulic Engineering, 2011, 137(2): 1549-1564. 本文引用 [1]

[3]

姜治兵, 崔丹, 程子兵. 坝体溃决过程与溃坝洪水演进耦合数值模拟[J]. raybet体育在线院报, 2018, 35(5):63-67.

https://doi.org/10.11988/ckyyb.20171175

摘要

研究坝体的溃决过程与溃坝洪水演进对于处置由溃坝引起的洪水灾害、提升水利安全具有重要的意义。鉴于目前大多模型均将坝体溃决过程与溃坝洪水演进分别进行模拟,不能反映土体与水流相互耦合的特点,模拟结果精度有限。基于对土体有限抗冲能力的考虑,选取双曲线型冲蚀速率表达式描述坝体冲蚀、采用简化Bishop法搜索临界滑裂面描述溃口边坡坍塌和具有总变差不增特性的MacCormack有限体积法离散控制方程,建立了坝体溃决过程与溃坝洪水演进耦合的平面二维数值模型。实际算例表明模型合理地模拟了溃口的发展过程与洪水演进过程,在溃口急缓流转换区展现了较强稳定性,守恒性良好,可作为溃坝洪水风险评估与洪灾预报的有力工具。

(JIANG

Zhi-bing

, CUI

Dan

, CHENG

Zi-bing

. Numerical Simulation Coupling Dam Break Process and Flood Routing[J]. Journal of Yangtze River Scientific Research Institute, 2018, 35(5): 63-67. (in Chinese))

https://doi.org/10.11988/ckyyb.20171175

本文引用 [1] 摘要

The study of dam break process and dam break flood routing is of great significance for dealing with flood disasters caused by dam break and improving water security. Most models at present could not reflect the interaction between soil and water flow by only simulating dam break process or flood routing, hence resulting in a limited accuracy. In this article, a 2-D numerical model coupling dam break process and flood routing was established in consideration of the finite erosion resistance of soil. The erosion rate expressions of hyperbolic type was employed to describe the rate of dam erosion; simplified Bishop method was adopted to search the critical slip surface for describing slope collapse at breach; and the Mac-Cormack finite volume method with total variation diminishing was adopted to discrete the control equations. A computation example demonstrates that the model could reasonably simulate the process of breach development and the flood routing process with strong stability and good conservativeness in breach transition zone from rapid flow to slow flow. The model can be used as a powerful tool for flood risk assessment and flood disaster forecast.

[4]	梅胜尧, 钟启明, 陈生水, 等. 堰塞体溃决流量与溃口形态演化数值模拟[J]. 地球科学, 2023, 48(4):1634-1648. (MEI Sheng-yao, ZHONG Qi-ming, CHEN Sheng-shui, et al. Numerical Simulation of Breach Hydrograph and Morphology Evolution during Landslide Dam Breaching[J]. Earth Science, 2023, 48(4):1634-1648. (in Chinese)) 本文引用 [1]

[5]	马利平, 侯精明, 张大伟, 等. 耦合溃口演变的二维洪水演进数值模型研究[J]. 水利学报, 2019, 50(10):1253-1267. (MA Li-ping, HOU Jing-ming, ZHANG Da-wei, et al. Study on 2-D Numerical Simulation Coupling with Breach Evolution in Flood Propagation[J]. Journal of Hydraulic Engineering, 2019, 50(10): 1253-1267. (in Chinese)) 本文引用 [1]

[6]	陈生水, 钟启明, 任强. 土石坝漫顶破坏溃口发展数值模型研究[J]. 水利水运工程学报, 2009(4): 53-58. (CHEN Sheng-shui, ZHONG Qi-ming, REN Qiang. Numerical Model Study on Break Development Due to Overtopping Failure for Earth-Rock Dam[J]. Hydro-Science and Engineering, 2009(4): 53-58. (in Chinese)) 本文引用 [1]

[7]

陈生水, 陈祖煜, 钟启明. 土石坝和堰塞坝溃决机理与溃坝数学模型研究进展[J]. 水利水电技术, 2019, 50(8):27-36.

(CHEN

Sheng-shui

, CHEN

Zu-yu

, ZHONG

Qi-ming

. Progresses of Studies on Failure Mechanism and Numerical Dam Failure Model of Earth-Rockfill Dam and Landslide Dam[J]. Water Resources and Hydropower Engineering, 2019, 50(8): 27-36. (in Chinese))

本文引用 [1]

[8]	PIERCE M W, THORNTON C I, ABT S R. PredictingPeak Outflow from Breached Embankment Dams[J]. Journal of Hydrologic Engineering, 2010, 15(5): 338-349. 本文引用 [1]

[9]	DE LORENZO G, MACCHIONE F. Formulas for the Peak Discharge from Breached Earthfill Dams[J]. Journal of Hydraulic Engineering, 2014, 140(1): 56-67. 本文引用 [1]

[10]	AZIMI R, VATANKHAH A R, KOUCHAKZADEH S. Predicting Peak Discharge from Breached Embankment Dams[C]// E-Proceedings of the 36th IAHR World Congress. Hague, The Netherlands,June 28-July 3, 2015:831-835. 本文引用 [1]

[11]	梅世昂, 陈生水, 钟启明, 等. 土石坝溃坝参数模型研究[J]. 工程科学与技术, 2018, 50(2): 60-66. (MEI Shi-ang, CHEN Sheng-shui, ZHONG Qi-ming, et al. Parametric Model for Breaching Analysis of Earth-Rock Dam[J]. Advanced Engineering Sciences, 2018, 50(2): 60-66. (in Chinese)) 本文引用 [2]

[12]

葛盼猛, 陈波, 陈伟楠, 等. 基于OWOA-RFWSVR-DLM的高寒区混凝土坝变形预测模型[J]. raybet体育在线院报, 2023, 40(5): 153-159, 165.

https://doi.org/10.11988/ckyyb.20211348

摘要

对于寒冷地区的混凝土大坝,由于表层保温层的影响,其内部温度往往滞后于气温变化。当内部温度计缺失时,使用水力-季节-时间(HST)模型进行大坝预测时存在较大的误差,且即使利用内部温度计进行多元回归(MR)模型的建模也无法反映温度与变形的非线性关系。因此,针对现阶段对高寒区变形预测精度低的问题,提出利用反向学习后的鲸群(OWOA)算法对RReliefF因子加权支持向量机(RFWSVR)与分布滞后线性模型(DLM)的温度因子的超参数进行寻优,以构建缺乏内部温度计的寒区混凝土大坝变形预测模型。结果表明:通过对所建立的变形预测模型与传统统计模型和其余常用机器学习算法的性能比较,证明所建立模型具有较高的预测精度,能更好地反映保温混凝土大坝的工作特点。

(GE

Pan-meng

, CHEN

Wei-nan

, et al. An OWOA-RFWSVR-DLM-based Model for Predicting Dam Deformation in the Alpine Region[J]. Journal of Changjiang River Scientific Research Institute, 2023, 40(5):153-159, 165. (in Chinese))

本文引用 [1]

[13]	陈珺, 黄燕华, 洪朋, 等. 基于机器学习模型的河道水位预测[J]. 水利水电科技进展, 2023, 43(3): 9-14. (CHEN Jun, HUANG Yan-hua, HONG Peng, et al. Prediction of River Water Level Based on Machine Learning Model[J]. Advances in Science and Technology of Water Resources, 2023, 43(3): 9-14. (in Chinese)) 本文引用 [1]

[14]	PEKTAS A O, ERDIK T. Peak Discharge Prediction Due to Embankment Dam Break by Using Sensitivity Analysis Based ANN[J]. KSCE Journal of Civil Engineering, 2014, 18(6): 1868-1876. 本文引用 [2]

[15]	HOOSHYARIPOR F, TAHERSHAMSI A, GOLIAN S. Application of Copula Method and Neural Networks for Predicting Peak Outflow from Breached Embankments[J]. Journal of Hydro-Environment Research, 2014, 8(3):292-303. 本文引用 [2]

[16]	AHMADISHARAF E, KALYANAPU A J, THAMES B A, et al. A Probabilistic Framework for Comparison of Dam Breach Parameters and Outflow Hydrograph Generated by Different Empirical Prediction Methods[J]. Environmental Modelling & Software, 2016, 86: 248-263. 本文引用 [2]

[17]	SAMMEN S S, MOHAMED T A, GHAZALI A H, et al. An Evaluation of Existent Methods for Estimation of Embankment Dam Breach Parameters[J]. Natural Hazards, 2017, 87(1): 545-566. 本文引用 [2]

[18]	SAMMEN S S, MOHAMED T A, GHAZALI A H, et al. Generalized Regression Neural Network for Prediction of Peak Outflow from Dam Breach[J]. Water Resources Management, 2017, 31(1): 549-562. 本文引用 [4]

[19]	VIDYA S, SRIEVIDHYA JANANI E. Tabu Search Algorithm Based General Regression Neural Network for Long Term Wind Speed Predictions[J]. Automatika, 2020, 61(4): 657-669. 本文引用 [1]

[20]

SPECHT

D F

. A General Regression Neural Network[J]. IEEE Transactions on Neural Networks, 1991, 2(6):568-576.

https://www.ncbi.nlm.nih.gov/pubmed/18282872

本文引用 [1] 摘要

A memory-based network that provides estimates of continuous variables and converges to the underlying (linear or nonlinear) regression surface is described. The general regression neural network (GRNN) is a one-pass learning algorithm with a highly parallel structure. It is shown that, even with sparse data in a multidimensional measurement space, the algorithm provides smooth transitions from one observed value to another. The algorithmic form can be used for any regression problem in which an assumption of linearity is not justified.

[21]	TROJOVSKÁ E, DEHGHANI M, TROJOVSKÝ P. Fennec Fox Optimization: A New Nature-inspired Optimization Algorithm[J]. IEEE Access, 2022, 10:84417-84443. 本文引用 [1]

[22]	WANG B, LIU W, ZHANG J, et al. Enhancement of Semi-theoretical Models for Predicting Peak Discharges in Breached Embankment Dams[J]. Environmental Fluid Mechanics, 2020, 20(4): 885-904. 本文引用 [1]

[23]

朱勇辉, 周建银. 堤坝漫溃机理、模型及溃决洪水模拟技术与应用[J]. raybet体育在线院报, 2023, 40(5): 1-8.

https://doi.org/10.11988/ckyyb.20220979

摘要

为提升堤坝溃决险情处置和溃决灾害防御能力,多年来raybet体育在线河流研究所采用物理模型试验、水槽试验、理论分析、数值模拟等方法研究了堤坝漫溢溃决的机理、模型与模拟技术。其主要成果包括:揭示了堤坝漫溢溃决机理,解析了“溯源陡坎冲刷”在堤坝溃决过程中的作用,提出了溯源陡坎冲刷模式和堤坝漫溢溃决模式;基于物理机制,研发了溯源陡坎冲刷二维数学模型和堤坝漫溢溃决数学模型;发展了适应溃坝水流急变特征的一、二、三维溃坝洪水运动模拟技术及地形处理方法,并初步探索了溃坝水流的三维流场与动压特性;总结评述了相关领域的研究进展。研究成果成功应用于唐家山、白格等历次堰塞湖溃决险情的应急处置和决策制定,并为今后堤坝(含堰塞坝)溃决险情的科学应对提供了技术参考和经验借鉴。

(ZHU

Yong-hui

, ZHOU

Jian-yin

. Embankment Breach Due to Overflowing: Mechanism, Models, Flood Simulation Technologies, and Their Applications[J]. Journal of Changjiang River Scientific Research Institute, 2023, 40(5): 1-8. (in Chinese))

本文引用 [1]

[24]

钟启明, 陈生水, 曹伟, 等. 考虑心墙不同破坏模式的黏土心墙坝漫顶溃坝过程数学模型[J]. 中国科学:技术科学, 2017, 47(9):992-1000.

(ZHONG

Qi-ming

, CHEN

Sheng-shui

, CAO

Wei

, et al. Numerical Model for Clay Core Dam Breach Process Due to Overtopping Considering Different Failure Modes of Core Wall[J]. Scientia Sinica (Technologica), 2017, 47(9): 992-1000. (in Chinese))

本文引用 [1]

[25]	HOOD K, PEREZ R A, CIEPLINSKI H E, et al. Development of an Earthen Dam Break Database[J]. JAWRA Journal of the American Water Resources Association, 2019, 55(1): 89-101. 本文引用 [1]

[26]	MOGLEN G E, HOOD K, HROMADKA T V II. Examination of Multiple Predictive Approaches for Estimating Dam Breach Peak Discharges[J]. Journal of Hydrologic Engineering, 2019, 24(2): 04018065. 本文引用 [1]

[27]	FROEHLICH D C. Predicting Peak Discharge from Gradually Breached Embankment Dam[J]. Journal of Hydrologic Engineering, 2016, 21(11): 04016041. 本文引用 [1]

[28]	周建银, 姚仕明, 王敏, 等. 土石坝漫顶溃决及洪水演进研究进展[J]. 水科学进展, 2020, 31(2):287-301. (ZHOU Jian-yin, YAO Shi-ming, WANG Min, et al. Review on Overtopping Failure and Flood Evolution of Earth-Rock Dams[J]. Advances in Water Science, 2020, 31(2): 287-301. (in Chinese)) 本文引用 [1]