基于卷积神经网络的涵洞式直立堤波浪透射预测
PREDICTION OF WAVE TRANSMISSION OF CULVERT BREAKWATER BASED ON CNN
-
摘要: 涵洞式直立堤是一种具有特殊用途的海岸工程结构物,对其透浪特性的研究具有重要工程意义. 然而,目前众多学者对于涵洞式直立堤波浪透射问题的研究主要以理论分析、实验模拟及数值计算为主.随着机器学习技术的发展, 传统水动力学问题迎来了新的求解理念.机器学习算法可根据训练数据集自主学习相应的规律,以数据映射的方式建立水动力学特征预测模型,在实际应用中无需对流体运动控制方程进行求解, 具有较高的计算效率. 因此,本文基于卷积神经网络(convolutional neural network, CNN),对不同开孔条件下的涵洞式直立堤透浪特征进行预测.首先利用模型试验验证计算流体力学(computational fluid dynamics, CFD)模型的有效性,然后基于CFD模型生成相应的训练数据集, 通过训练卷积神经网络模型,建立相应的波浪透射结果之间的数据映射关系,实现在新的工况下对波浪透射系数以及透射波波形等特征的快速预测. 结果表明,经过训练的卷积神经网络可在极短时间内计算得到相应的结果, 并具有较高的准确性.研究成果可为波浪与海岸结构物相互作用的问题提供新的求解理念.Abstract: Culvert breakwater is a common coastal engineering structure. At the same time, the wave energy can also be transmitted into the harbor through the culvert, which will affect the hydrodynamic characteristics and mooring stability of the harbor. The study of its wave transmission characteristics is closely related to the safety of relevant production equipment and the corresponding engineering economic cost. However, many scholars mainly focus on theoretical analysis, experimental simulation and numerical calculation for wave transmission of culvert type vertical breakwater. With the development of machine learning technology, the traditional hydrodynamic problems ushered in a new solution concept which has attracted many attentions in the field of physics and engineering. At present, many scholars have applied machine learning algorithm to wave related problems. The machine learning algorithm can autonomously learn the corresponding laws according to the training data set, and establish the prediction model of hydrodynamic characteristics by data mapping. In practical application, it does not need to solve the fluid motion control equation, and has high computational efficiency. In this paper, based on the convolutional neural network (CNN), the wave transmission characteristics of the culvert breakwater under different incident and different opening conditions are predicted. The corresponding training data set is generated by a CFD model for convolution neural network training. The CFD results are compared with physical results for validation. After the data mapping relationship between different working conditions and the corresponding wave transmission results are established, the wave transmission coefficient and wave characteristics of transmission wave under the new working conditions can be predicted rapidly. The results show that the trained convolutional neural network can calculate the corresponding results within 10 milliseconds with a relatively high accuracy. This study can provide a new idea for solving the problem of interaction between waves and coastal structures, and is of importance in engineering application.