Application of probabilistic neural network to design breakwater armor blocks

This study presents a probabilistic neural network (PNN) technique for predicting the stability number of armor blocks of breakwaters. The PNN is prepared using the experimental data of Van der Meer. The predicted stability numbers of the PNN are compared with those of previous studies, i.e. by an empirical formula and a previous neural network model. The agreement index between the measured and predicted stability numbers by PNN are better than those by the previous studies. The PNN offers a way to interpret the network's structure in the form of a probability density function and it is easy to implement. Therefore, it can be an effective tool for designers of rubble mound breakwaters.     

Design of rubble-mound breakwaters using M5 ′ machine learning method

Predicting the stability of armor blocks of breakwaters and revetments is a very important issue in coastal and ocean engineering. Recently, soft computing tools such as artificial neural networks and fuzzy logic have been used to predict the stability number of armor blocks. However, these tools are not as transparent as empirical formulas. This study presents another soft computing approach, i.e. model trees for predicting the stability number of armor blocks. The main advantage of model trees is that, unlike the other data learning tools, they are easier to use and more importantly they represent understandable mathematical rules. A total of 579 experimental test data from Van der Meer 1988 are used for developing the model. The conventional governing parameters were selected as the input variables and the obtained results were compared with those of measurements, empirical and soft computing models. Using statistical measures, it was shown that the developed models are more accurate than previous empirical and soft computing models. Furthermore, some simple rules are given for armor blocks’ design.     

斜坡堤护面块体安放过程及稳定性数值模拟

利用基于光滑粒子流体动力学(SPH)数值方法的开源软件DualSPHysics进行数值试验,模拟斜坡式防波堤上扭王字护面块体的安放过程,研究护面块体的稳定性。首先以DualSPHysics为平台开发了护面块体的安放功能模块,并对护面块体的安放效果进行评价,实现了按指定安放密度进行块体安放。块体安放完成后,在数值波浪水槽中研究护面块体在规则波作用下的运动及受力响应,并分析护面块体失稳的典型形式和失稳标准,通过系统化的参数分析,探讨波浪要素及块体安放等因素对块体稳定性的影响。结果表明,扭王字块体稳定性系数的取值范围为21.64~26.20,是规范推荐值的1.5倍左右。块体鼻轴方向的相对位置主要影响单个块体的上举脱出失稳,鼻轴方向在坡面上赤平投影图越分散,护面块体层整体上越稳定。坡面坡度变缓时,护面块体层整体下滑趋势减弱,但更易发生上举脱出失稳;单个块体缺失会加大周围块体的上举失稳概率。     

防波堤断面结构型式及护面块体稳定性模型试验研究——2008北京奥运会青岛帆船比赛基地水工模型试验

为确保2008北京奥运会青岛帆船比赛基地内工程的水工建筑物安全可靠,对给定的2种防波堤断面结构型式及护面块体稳定性进行物理模型试验。准确掌握在极端高水位、设计高水位、设计低水位和极端低水位时．SW向、25a和50a一遇波浪作用下,试验断面所承受的波浪作用力,及SE向50a一遇波浪作用下块体的稳定重量。并绘制各工况1％峰值波压力分布图,得出断面波压力的分布规律。对断面结构和护面块体稳定性进行分析。     

波浪周期对防波堤护面块体稳定性影响的试验分析

波浪对斜坡堤护面结构的冲刷破坏作用受诸多因素的影响,如波浪要素、水深条件、坡面角度、护面块体型式等。在进行某项有关斜坡堤护面块体的课题研究中发现,当防波堤断面结构确定后,护面人工块体的稳定性主要取决于波高及波周期的变化。在进行这方面内容设计计算中,通常波高的取值都能给予足够的重视,但波周期对护面块体稳定性的影响容易被忽视。本研究通过物理模型试验,针对波浪周期对斜坡堤护面块体稳定性的影响进行了总结分析,为防波堤设计提供参考。     

波浪作用下斜坡上护面块体内部应力分布数值模拟

基于3D FEMDEM方法建立三维原型尺度数值模型,模拟波浪荷载作用下斜坡上护面块体内部的应力分布。波浪作用下结构物的水动力荷载采用微幅波理论模拟,护面块体之间的运动、碰撞接触以及块体内部的应力变化采用3D FEMDEM方法模拟。块体之间的接触力采用基于势函数的罚函数法计算,有限元的变形采用中心差分的显式方法求解。应用该数值模型与ANSYS软件程序对自重作用下混凝土扭王字块的内部应力分布特性进行了比较分析,验证了数值模型应力计算的可行性和计算精度。通过数值模拟计算给出了波浪作用下斜坡上护面块体之间的相对运动和块体内部的应力分布及应力历时曲线,探讨了块体内部应力变化特性。     

防波堤的人工神经网络Monte Carlo法可靠性分析

防波堤建设费用巨大,且一旦遭到破坏,后果甚为严重,因此,如何准确地计算防波堤的可靠性意义重大.随着人工神经网络理论的快速发展,人工神经网络方法在结构可靠性分析中的应用逐渐得到重视.基于神经网络的Monte Carlo法计算直立式防波堤的可靠性,概率意义明确.以秦皇岛典型直立堤为算例,采用基于神经网络的Monte Carlo法对直立式防波堤进行可靠性分析时,将直立堤滑动破坏和倾覆破坏的极限状态方程中的所有参数均作为变量处理,并将计算结果与Monte Carlo模拟的直接抽样法、重要抽样法以及独立变量JC法的计算结果进行对比.结果表明:基于神经网络的Monte Carlo法和Monte Carlo模拟的直接抽样法、重要抽样法计算结果相近,而比独立变量JC法的计算结果略低.     

Experiment Verification of Damage Detection for Offshore Platforms by Neural Networks

1 .Introduction Large civil engineering structures are exposed to various external loads such as earthquakes ,winds ,traffic and wave loads during their lifetime . The structures may become deteriorated and de-graded withtime in an unexpected way, which m…     

海底沉积物声学特征定量分析及其智能分类研究

海底底质特性描述及分类是当今浅海声学的研究热点,海底沉积物的物理结构特性与其声学响应特征密切相关。在分析海底沉积物声传播特性的基础上,应用现代计算机信号分析技术手段,对海底沉积物声学响应波形提取了4个特征参数:声速、波幅指数、波形关联维分形指数和声波频谱的频率矩。以这4个特征参数作为输入向量,海底沉积物的结构类型作为输出向量,建立径向基概率神经网络模型。研究表明建立的神经网络模型具有较强的海底沉积物分类预报能力。     

基于二元LSTM神经网络的船舶运动预测算法研究

在海况环境下,进行船舶运动预测时.由于惯性传感器采集系统本身的电学特性,会产生误差偏移,影响预测的准确性.针对这一问题,在常规长短期记忆网络(LSTM)的基础上,设计改良了一种二元的LSTM网络架构.在船舶运动仿真平台上进行模拟船舶升沉运动实验,并通过惯性传感系统测量仿真平台实时积分位移进行计算验证.验证统计该网络预测...     

基于多种神经网络的风暴潮增水预测方法的比较分析

简要介绍了利用BP神经网络、小波神经网络、递归神经网络进行风暴潮增水值预测的原理。选取广东省珠江口以南的阳江站2017年风暴潮增水数据进行测试。结果表明,三种神经网络方法针对阳江地区风暴潮增水的预测均具有可靠性和实用性。以当前增水值为输入量的单因子模型更能反映真实风暴潮增水趋势,而从增水极值预测的准确性来看,以台风风力、气压、风向等相关参数为输入量的多因子模型优于单因子模型。BP神经网络更适用于多因子长时间预测,小波神经网络在单因子短时间预测上准确性更高,递归神经网络预测值与实测值相关性更强。在工程运用中,需根据地域时空特点、数据资料的丰富度与预测值评估指标选择合适的方法。     

波浪作用下方块石护面稳定性研究

护面是海堤和护岸的重要结构,直接抵御波浪作用,可采用人工块体、块石等,种类繁多。采用紧密排列方块石作为护面结构是一种景观性较好的型式,依据方块石厚度不同能抵御不同大小的波浪作用。干砌条石及干砌块石护面曾有一些规范给出过计算方法,但现行规范没有相关内容可供设计参考,已有计算方法的理论分析还存在不足。当波浪与斜坡堤相互作用时,方块石护面出现位移或脱落可能发生在波浪回落最低阶段、波浪破碎打击阶段及破后爬高水流作用阶段,通过研究得到了不同阶段波浪对方块石护面作用力的计算方法。在波浪回落最低阶段,考虑了护面及其下方垫层渗透性影响,通过理论分析建立了低渗透护面浮托压强计算模型,采用物模试验将计算结果与试验测量值进行了对比分析,结果表明总体趋势符合,量值接近;在波浪破碎冲击阶段,基于射流冲击作用原理,提出了波浪在斜坡面破碎冲击压强计算方法,通过试验分析了波浪破碎水深波高比与破波相似参数的关系,利用浅水波理论计算了波浪破碎冲击水流流速;在爬高水流作用阶段,提出了水流引起的方块石护面垂直浮托力及水平拖曳力的计算方法,通过试验结果拟合了浮托力系数和拖曳力系数,验证了水流作用下护面的受力特征。最后,针对方块...     

Application of artificial neural networks in tide-forecasting

An accurate tidal forecast is an important task in determining constructions and human activities in ocean environments. Conventional tidal forecasting has been based on harmonic analysis using the least squares method to determine harmonic parameters. However, a large number of parameters are required for the prediction of a long-term tidal level with harmonic analysis. Unlike conventional harmonic analysis, this paper presents an artificial neural network (ANN) model for forecasting the tidal-level using the short term measuring data. The ANN model can easily decide the unknown parameters by learning the input–output interrelation of the short-term tidal records. Three field data with three types of tides will be used to test the performance of the proposed ANN model. The numerical results indicate that the hourly tidal levels over a long duration can be predicted using a short-term hourly tidal record.     

Simulation on the Strength of Model Armor Block on Rubble-Mound Breakwaters

This paper mainly deals with the simulation on the strength of the concrete armor block in model test. According to the requirement for the strength of blocks in models with various scales, the components of materials for model blocks and their proportions are determined. The failure of armor blocks on rubble-mound breakwaters is reproduced by model tests.     

海堤上波浪爬高与越浪计算分析

基于线性波理论,采用VOF法、RNG k-ε的湍流模型,通过FLUENT软件平台的二次开发功能实现了质量源造波。利用多孔介质模型,在动量方程里添加多孔介质源项,对斜坡堤上铺设异型块体时的爬高与越浪进行了数值模拟,并通过模拟爬高值率定出FLUENT中多孔阻力系数与多种异形块体糙渗系数之间的关系,进而建立了可供实际应用的海堤上波浪爬高与越浪数值模型。     

基于决策树与二分分割算法的BP神经网络在赤潮等级预测中的应用研究

针对赤潮灾害等级预测难的现状,提出了一种基于C4.5决策树与二分分割算法优化的BP(反向传播)神经网络赤潮等级预测模型。该模型针对传统BP神经网络输入参数难以选择和隐含层节点数量难以确定的问题,通过决策树分类获取最优的属性组合,来解决输入参数难以选择的问题;通过"二分分割算法",来解决隐含层节点数难以确定的问题。实验结果表明,该模型在青岛近海海域赤潮灾害等级预测中,预测结果的均方根误差(RMSE)小于传统BP神经网络的预测误差,并且在网络训练时间上有所缩短,预测精度上有所提高,能够获得良好的预测结果,可为赤潮等级预测提供新的解决方法。     

Prediction of maximum wave-induced liquefaction in porous seabed using multi-artificial neural network model

In the last few decades, considerable efforts have been devoted to the phenomenon of wave-induced liquefactions, because it is one of the most important factors for analysing the seabed and designing marine structures. Although numerous studies of wave-induced liquefaction have been carried out, comparatively little is known about the impact of liquefaction on marine structures. Furthermore, most previous researches have focused on complicated mathematical theories and some laboratory work. In the present study, a data dependent approach for the prediction of the wave-induced liquefaction depth in a porous seabed is proposed, based on a multi-artificial neural network (MANN) method. Numerical results indicate that the MANN model can provide an accurate prediction of the wave-induced maximum liquefaction depth with 10% of the original database. This study demonstrates the capacity of the proposed MANN model and provides coastal engineers with another effective tool to analyse the stability of the marine sediment.     

Experimental analysis of breakwater stability with antifer concrete block

Armor is a pavement made of erosion-resistant materials like a stone or concrete that is constructed to protect breakwater, coasts, and other coastal line features against erosion. These armors are a kind of protective layer made of stone or concrete, used in breakwater constructions or coastal lines, arrayed with specific regular or irregular pattern on the breakwater or the coast. The antifer concrete blocks have almost cubic form, often changed into frustum by adding inclined plates to their sides. One of the most important advantages of these armors is their diversified regular and irregular placement patterns. In this study, using the physical modeling and different tests, the stability level of antifer concrete blocks was evaluated considering the decrease of the armor weight. Results of this study show that by a 10% decrease in the block weight, the failure graph slope is increased and the damage is intensified.     

基于遗传小波神经网络的海底声学底质识别分类

分割海底声纳探测图像,提取单元特征向量进行主成份分析,选取均值、标准差、对比度、相关系数、能量及同质性作为训练特征向量,构建小波神经网络。利用遗传算法优化小波神经网络的初始权值及小波参数,对砂、礁石、泥3种底质类型分别进行训练,并得到3种底质的测试精度都在90%以上,优于单独利用小波神经网络进行训练时的测试精度,克服了小波神经网络训练时易陷入局部极小的固有缺陷,表明基于遗传算法的小波神经网络可有效用于海底底质声纳图像的识别和分类。     

Static stability of submerged partial revetment structures under regular and irregular waves

Physical models of submerged partial revetment structures were built on natural beach sand with a diameter of 0.35 mm and specific gravity of 2.63. The armor units, the diameter and specific gravity of which varied in the range of 8.5–67.95 mm and 1.81–2.77 respectively, were placed only on wave breaking areas. A series of experiments has been conducted on the conditions of different armor units and different wave characteristics using regular waves and irregular waves. Based on the experimental data, the effects of wave height, wave period, diameter and specific gravity of armor units, water depth in the channel, and wave types on static damage of given structures are assessed. Some empirical formulas have been suggested through regression analysis to describe static stability and stability number of submerged partial revetment structures under pure regular waves, pure irregular waves, and regular–irregular waves. The suggested formulas compared with Van der Meer’s (1988) formulas and some differences have occurred because of differences among revetment types and test conditions; therefore, proposed formulas give reasonable results for the test conditions used.