基于SSA-CNN模型的双排开孔圆筒防波堤透射系数预测  

Prediction of transmission coefficient of double-row perforated cylinder breakwater based on SSA-CNN model

作　　者：邓斌[1,2,4] 王玲 何军[3] 尹龙斌[1] 蒋昌波 陈杰[1,2] 伍志元 Deng Bin;Wang Ling;He Jun;Yin Longbin;Jiang Changbo;Chen Jie;Wu Zhiyuan(School of Hydraulic and Environmental Engineering,Changsha University of Science&Technology,Changsha 410114,China;Key Laboratory of Water-Sediment Sciences and Water Disaster Prevention of Hunan Province,Changsha 410114,China;CCCC Water Transportation Consultants Co.,Ltd.,Beijing 100007,China;State Key Laboratory of Hydraulic Engineering Intelligent Construction and Operation,Tianjin 300072,China)

机构地区：[1]长沙理工大学水利与环境工程学院,湖南长沙410114 [2]水沙科学与水灾害防治湖南省重点实验室,湖南长沙410114 [3]中交水运规划设计院有限公司,北京100007 [4]水利工程智能建设与运维全国重点实验室,天津300072

出　　处：《海洋学报》2024年第4期122-132,共11页

基　　金：国家重点研发项目(2021YFB2601100);国家自然科学基金项目(51979015,51839002);水利工程仿真与安全国家重点实验室开放基金项目(HESS-2114);湖南省科技创新计划项目(2020RC3037,20hnkj019)。

摘　　要：双排开孔圆筒防波堤是一种新型环境友好型防波堤,对其消浪特性的研究具有重要工程意义。随着人工智能的发展,基于机器学习技术求解防波堤水动力学问题成了一种新的研究范式。本文提出基于麻雀搜索算法(Sparrow Search Algorithm,SSA)优化卷积神经网络(Convolutional Neural Network,CNN)模型,实现对双排开孔圆筒防波堤透射系数的智能优化预测。结果表明:(1)确定波高、波周期、波长、波速、排间距、开孔率、水深为影响透射系数的关键因子;(2)当SSA-CNN模型的种群数量为10时,对波浪透射系数预测的R2值达到0.9909,平均相对误差相比单一的CNN模型降低了5.07%。研究成果为利用神经网络研究波浪透射问题提供了一种新的优化预测模型。The double-row perforated cylinder breakwater is a new type of environment-friendly breakwater,and the research on its wave absorbing characteristics is of great engineering significance.With the development of artificial intelligence,solving the water dynamics problem of breakwater based on machine learning technology has become a new research paradigm.This paper proposes a Convolutional Neural Network(CNN) model based on Sparrow Search Algorithm(SSA) to achieve intelligent optimization prediction of transmission coefficient of doublerow perforated cylindrical breakwater.The results show that:(1) wave height,wave period,wavelength,wave velocity,row spacing,hole rate and water depth are identified as the key factors affecting the transmission coefficient.(2) When the population size of the SSA-CNN model is 10,the R2 value of the wave transmission coefficient prediction reaches 0.990 9,and the average relative error is reduced by 22.24% compared with the single CNN model.The research results provide a new optimal prediction model for the study of wave transmission by using neural networks.

关 键 词：双排开孔圆筒防波堤 消浪特性 麻雀搜索算法 卷积神经网络 透射系数 

分 类 号：P753[交通运输工程—港口、海岸及近海工程]