Updated Support Vector Machine for Seismic Liquefaction Evaluation Based on the Penetration Tests

Simplified techniques based on in situ testing methods are commonly used to predict liquefaction potential. Many of these simplified methods are based on finding the liquefaction boundary separating two categories (the occurrence or non-occurrence of liquefaction) through the analysis of liquefaction case histories. As the liquefaction classification problem is highly nonlinear in nature, it is difficult to develop a comprehensive model taking into account all the independent variables, such as the seismic and soil properties, using conventional modeling techniques. Hence, in many of the conventional methods that have been proposed, simplified assumptions have been made. In this study, an updated support vector machine (SVM) based on particle swarm optimization (PSO) is used to evaluate liquefaction potential in two separate case studies. One case is based on standard penetration test (SPT) data and the other is based on cone penetration test (CPT) data. The SVM model effectively explores the relationship between the independent and dependent variables without any assumptions about the relationship between the various variables. This study serves to demonstrate that the SVM can “discover” the intrinsic relationship between the seismic and soil parameters and the liquefaction potential. Comparisons indicate that the SVM models perform far better than the conventional methods in predicting the occurrence or non-occurrence of liquefaction.     

Updated Support Vector Machine for Seismic Liquefaction Evaluation Based on the Penetration Tests

Simplified techniques based on in situ testing methods are commonly used to predict liquefaction potential. Many of these simplified methods are based on finding the liquefaction boundary separating two categories (the occurrence or non-occurrence of liquefaction) through the analysis of liquefaction case histories. As the liquefaction classification problem is highly nonlinear in nature, it is difficult to develop a comprehensive model taking into account all the independent variables, such as the seismic and soil properties, using conventional modeling techniques. Hence, in many of the conventional methods that have been proposed, simplified assumptions have been made. In this study, an updated support vector machine (SVM) based on particle swarm optimization (PSO) is used to evaluate liquefaction potential in two separate case studies. One case is based on standard penetration test (SPT) data and the other is based on cone penetration test (CPT) data. The SVM model effectively explores the relationship between the independent and dependent variables without any assumptions about the relationship between the various variables. This study serves to demonstrate that the SVM can “discover” the intrinsic relationship between the seismic and soil parameters and the liquefaction potential. Comparisons indicate that the SVM models perform far better than the conventional methods in predicting the occurrence or non-occurrence of liquefaction.     

Evaluation of undrained failure envelopes of caisson foundations under combined loading

In this paper, results of a three-dimensional finite element study addressing the effect of embedment ratio (L/D) of caisson foundations on the undrained bearing capacity under uniaxial and combined loadings are discussed. The undrained response of caisson foundations under uniaxial vertical (V), horizontal (H) and moment (M) loading are investigated. A series of equations are proposed to predict the ultimate vertical, moment and maximum horizontal bearing capacity factors. The undrained response of caisson foundations under combined V-H and V-M load space is studied and presented using failure envelopes generated with side-swipe method. The kinematic mechanism accompanying failure under uniaxial loading is addressed and presented for different embedment ratios. Predictions of the uniaxial bearing capacities are compared with other models and it is confirmed that the proposed equations appropriately describe the capacity of caisson foundations under uniaxial vertical, horizontal and moment loading in homogenous undrained soils. The results of this paper can be used as a basis for standard design codes of off-shore skirted shallow foundations which will be the first of its kind.     

An improved particle swarm optimization algorithm with harmony strategy for the location of critical slip surface of slopes

The determination of optimal values for three parameters required in the original particle swarm optimization algorithm is very difficult.It is proposed that two new parameters simulating the harmony search strategy can be adopted instead of the three parameters which are required in the original particle swarm optimization algorithm to update the positions of all the particles.The improved particle swarm optimization is used in the location of the critical slip surface of soil slope,and it is found that the improved particle swarm optimization algorithm is insensitive to the two parameters while the original particle swarm optimization algorithm can be sensitive to its three parameters.     

基于SVM回归模型的SAR图像有效波高估测

A new method for estimating significant wave height(SWH) from advanced synthetic aperture radar(ASAR) wave mode data based on a support vector machine(SVM) regression model is presented. The model is established based on a nonlinear relationship between σ0, the variance of the normalized SAR image, SAR image spectrum spectral decomposition parameters and ocean wave SWH. The feature parameters of the SAR images are the input parameters of the SVM regression model, and the SWH provided by the European Centre for Medium-range Weather Forecasts(ECMWF) is the output parameter. On the basis of ASAR matching data set, a particle swarm optimization(PSO) algorithm is used to optimize the input kernel parameters of the SVM regression model and to establish the SVM model. The SWH estimation results yielded by this model are compared with the ECMWF reanalysis data and the buoy data. The RMSE values of the SWH are 0.34 and 0.48 m, and the correlation coefficient is 0.94 and 0.81, respectively. The results show that the SVM regression model is an effective method for estimating the SWH from the SAR data. The advantage of this model is that SAR data may serve as an independent data source for retrieving the SWH, which can avoid the complicated solution process associated with wave spectra.     

Research on Bulbous Bow Optimization Based on the Improved PSO Algorithm

In order to reduce the total resistance of a hull, an optimization framework for the bulbous bow optimization was presented. The total resistance in calm water was selected as the objective function, and the overset mesh technique was used for mesh generation. RANS method was used to calculate the total resistance of the hull. In order to improve the efficiency and smoothness of the geometric reconstruction, the arbitrary shape deformation (ASD) technique was introduced to change the shape of the bulbous bow. To improve the global search ability of the particle swarm optimization (PSO) algorithm, an improved particle swarm optimization (IPSO) algorithm was proposed to set up the optimization model. After a series of optimization analyses, the optimal hull form was found. It can be concluded that the simulation based design framework built in this paper is a promising method for bulbous bow optimization.     

复合加载下桶形基础循环承载性能数值分析

作为一种新型基础形式,吸力式桶形基础除了承受海洋平台结构及自身重量等竖向荷载的长期作用之外,往往还遭受波浪等所产生的水平荷载及其力矩等其它荷载分量的瞬时或循环作用。对复合加载模式下软土地基中桶形基础及其结构的循环承载性能尚缺乏合理的分析与计算方法。应用Andersen等对重力式平台基础及地基所建议的分析方法,基于软黏土的循环强度概念,在大型通用有限元分析软件ABAQUS平台上,通过二次开发,将软土的循环强度与Mises屈服准则结合,针对吸力式桶形基础,基于拟静力分析建立了复合加载模式下循环承载性能的计算模型,并与复合加载作用下极限承载性能进行了对比。由此表明,与极限承载力相比,桶形基础的循环承载力显著降低。     

Weibull分布参数的粒子群算法估计

基于广西涠洲岛海洋监测站3个方向的年极值波高观测资料,在假设其服从Weibull分布的基础上,运用最小二乘法,矩估计法和最速下降法对Weibull分布的参数进行估计,同时引入粒子群算法确定Weibull分布的3个参数,对文中4种方法得出的拟合结果及运算效率进行比较分析,说明了粒子群算法在估计极值分布参数中的优势.     

An investigation into the lateral loading response of shallow bucket foundations for offshore wind turbines through centrifuge modeling in sand

A shallow suction bucket is a new foundation type for offshore wind turbines. Due to its large size and bulky shape, the bucket and the soil within the bucket do not necessarily deform as a whole. Moreover, limited research has been conducted on the hydrodynamic wave influence on the shallow bucket bearing response. These factors pose great challenges to the shallow bucket foundation design. This paper presents a set of centrifuge tests of a shallow bucket model subjected to monotonic and dynamic lateral loads to study the lateral bearing response of shallow bucket foundations in the field under combined loads induced by wind, waves, etc. In addition to the routine measurements (e.g., load-displacement), the soil pressures on the bucket and the distribution and evolution of the excess pore pressures in the surrounding soils are also obtained. The deformation pattern of the bucket (e.g., rotation center) is revealed through displacement measurements. Finally, the proposed easy-to-use analytical equations using the limit equilibrium to assess the bearing capacity of bucket foundations, taking into account the influence of the soil strength degradation caused by hydrodynamic wave loadings, are found to yield good results upon comparison with the centrifuge data, providing useful guidelines for the design of shallow bucket foundations.     

Effect of embedment on the vertical capacity of bucket foundation in loose saturated sand: Physical modeling

ABSTRACT

Bucket foundations have been widely used for a variety of offshore applications. The effects of skirt length on ultimate bearing capacity of bucket foundation have been studied and reported in published scientific papers. However, few studies have addressed the behavior of bucket foundations in loose saturated sand. In this paper, a series of experimental investigations were performed to determine the bearing capacity of bucket foundation under uniaxial loading. The experiments were conducted on small-scale foundations under vertical loading in loose saturated sand. It was found that increasing the skirt length would enhance the bearing capacity of bucket foundation. As reflected in the present study, bearing strength might be enhanced more than 5 times in loose saturated sand in comparison to surface footing with equivalent diameter. Based on the experimental investigation, a depth factor was proposed to approximate bearing capacity of bucket foundations in terms of those for surface footing and embedment ratio. Moreover, the corresponding settlement of foundation at the failure load was found to increase with skirt length.     

基于粒子群算法优化的BP神经网络在海水水质评价中的应用

针对目前存在的海水水质受多因素影响、评价难的现状，提出了一种基于粒子群算法（PSO）优化误差反向传播（BP）神经网络的海水水质评价模型。该模型通过PSO得到BP神经网络最优的权值和阈值，结合青岛东部海域10个监测站点的数据得到水质评价结果。实验证明，该模型和单因子评价、传统的BP神经网络评价相比较，具有训练时间短、预测精度高的特点，在海水水质评价中具有良好的应用价值。     

基于粒子群优化神经网络的水深反演模型

针对直接采用BP神经网络反演水深收敛速度慢,且易陷入局部最优的问题,提出了一种基于粒子群(PSO)优化BP神经网络的水深遥感新模型。该模型首先利用粒子群算法对BP神经网络的权重和阈值进行优化,然后将该优化值作为BP神经网络的初始值,最后再将PSO优化后的模型用于测试海区的反演精度评估。实验结果表明,该模型的网络收敛速度明显加快,水深反演的精度也得到提高。     

Investigation of scour effects on lateral behaviors of suction caisson

ABSTRACT

The use of suction caissons can reduce the development costs of offshore wind energy and has broad application prospects. However scour around marine foundations is inevitable, it gravely affects the stability of marine engineering. Therefore, there is an urgent need to study the weakening effects of scour on suction caisson. In this study, the variation trends of remaining soil parameters (the effective unit weight and the peak effective friction angle) after scour are examined with consideration of the dilatancy and stress history of sandy silt. It is found that the parameters of shallow soil change considerably after scour, and the larger the scour depth, the greater is the change in the parameters. However, the deep soil is less affected. On the basis of these findings, scour effects on the ultimate moment capacity of suction caisson are studied. The ultimate moment capacity is found to greatly reduce under scour, and its calculated value is larger than the actual value when the effects of dilatancy and stress history are ignored. To simplify calculation, it is feasible to replace the ultimate moment capacity when both dilatancy and stress history are considered with that when only dilatancy is considered.     

Steady-State Configuration and Tension Calculations of Marine Cables Under Complex Currents via Separated Particle Swarm Optimization？

Under complex currents, the motion governing equations of marine cables are complex and nonlinear, and the calculations of cable configuration and tension become difficult compared with those under the uniform or simple currents. To obtain the numerical results, the usual Newton-Raphson iteration is often adopted, but its stability depends on the initial guessed solution to the governing equations. To improve the stability of numerical calculation, this paper proposed separated the particle swarm optimization, in which the variables are separated into several groups, and the dimension of search space is reduced to facilitate the particle swarm optimization. Via the separated particle swarm optimization, these governing nonlinear equations can be solved successfully with any initial solution, and the process of numerical calculation is very stable. For the calculations of cable configuration and tension of marine cables under complex currents, the proposed separated swarm particle optimization is more effective than the other particle swarm optimizations.     

考虑预载固结效应的海底浅基础承载力包络面演化规律研究

由于预载下土体固结,海底浅基础的承载力会随作业时间的增加而改变,其时变效应评估困难。基于修正剑桥模型,采用水土耦合有限元方法研究了预载作用下浅基础在正常固结黏土海床中承载力破坏包络面的时变规律。在验证数值模型准确性后,通过位移探针测试获取复合加载模式下浅基础的破坏包络面,揭示了预载和固结程度对基础承载力和破坏包络面的影响,给出了预载作用下浅基础承载力包络面计算方法。结果表明：随着预载比增加,固结单轴承载力呈现线性增长,固结承载力增幅在水平向最大;部分固结承载力相对增幅与预载比无关,而随固结度变化;破坏包络面形状由预载比控制,而包络面大小由预载比和固结度共同控制。研究结果可为海洋浅基础的时变承载力评估提供参考依据。     

Steady-State Configuration and Tension Calculations of Marine Cables Under Complex Currents via Separated Particle Swarm Optimization

Under complex currents, the motion governing equations of marine cables are complex and nonlinear, and the calculations of cable configuration and tension become difficult compared with those under the uniform or simple currents. To obtain the numerical results, the usual Newton?Raphson iteration is often adopted, but its stability depends on the initial guessed solution to the governing equations. To improve the stability of numerical calculation, this paper proposed separated the particle swarm optimization, in which the variables are separated into several groups, and the dimension of search space is reduced to facilitate the particle swarm optimization. Via the separated particle swarm optimization, these governing nonlinear equations can be solved successfully with any initial solution, and the process of numerical calculation is very stable. For the calculations of cable configuration and tension of marine cables under complex currents, the proposed separated swarm particle optimization is more effective than the other particle swarm optimizations.     

Experimental Study on Stability of Breakwaters with Penetrating Box Foundations

1 .ＩｎｔｒｏｄｕｃｔｉｏｎＴｈｅｐｅｎｅｔｒａｔｉｎｇｂｕｃｋｅｔａｎｄｂｏｘｆｏｕｎｄａｔｉｏｎｉｓａｎｅｗｔｙｐｅｏｆｓｔｒｕｃｔｕｒｅ ,ｗｈｉｃｈｈａｓｂｅｅｎａｐｐｌｉｅｄｉｎｍａｎｙｅｎｇｉｎｅｅｒｉｎｇｆｉｅｌｄｓ .Ｉｎｖｉｅｗｏｆｔｈｅｈｉｇｈｃｏｎｓｔｒｕｃｔｉｏｎｃｏｓｔａｎｄｔｈｅｆｏｒｍｉｄａｂｌｅｃｏｎｓｔｒｕｃｔｉｂｉｌｉｔｙｏｆｏｆｆ ｓｈｏｒｅｐｌａｔｆｏｒｍｓｗｉｔｈｐｉｌｅｄｆｏｕｎｄａｔｉｏｎｓ ,Ｂａｅｒｈｅｉｍｅｔａｌ.(1 990 )ｐｒｏｐｏｓｅｄｔｈｅｃｏｎｃ…     

海底管线沉降量计算方法的理论研究与试验验证

根据极限平衡和极限分析方法,首先建立了软土地基土体上海底管线的极限承载力计算公式.当地基处于极限状态时,基础作用于地基的全部荷载应等于该地基土体的承载能力,根据这一关系式可以推导出海底管线沉降量的计算公式.最后通过对试验结果的分析,证实所采用的计算方法是可行的.     

Robust LS-SVM regression for ore grade estimation in a seafloor hydrothermal sulphide deposit

Due to the geological complexities of ore body formation and limited borehole sampling, this paper proposes a robust weighted least square support vectormachine (LS-SVM) regression model to solve the ore grade estimation for a seafloor hydrothermal sulphide deposit in Solwara 1, which consists of a large proportion of incomplete samples without ore types and grade values. The standard LS-SVM classification model is applied to identify the ore type for each in complete sample. Then, a weighted K-nearest neighbor (WKNN) algorithm is proposed to interpolate the missing values. Prior to modeling, the particle swarm optimization (PSO) algorithm is used to obtain an appropriate splitting for the training and test data sets so as to eliminate the large discrepancies caused by randomdivision. Coupled simulated annealing (CSA) and grid search using 10-fold cross validation techniques are adopted to determine the optimal tuning parameters in the LS-SVM models. The effectiveness of the proposed model by comparing with other well-known techniques such as inverse distance weight (IDW), ordinary kriging (OK), and back propagation (BP) neural network is demonstrated. The experimental results show that the robust weighted LS-SVM outperforms the othermethods, and has strong predictive and generalization ability.     

海上风电嵌岩桩水平抗力影响因素研究

桩基础是我国海上风电工程中应用最为广泛的基础形式,其中嵌岩桩因其施工难度大,承载力高备受关注。与其他类型的桩基础不同,嵌岩桩的水平承载力不仅受到围岩强度的影响,更与其成桩质量与灌浆材料的强度相关。采用有限元方法分析了嵌岩深度、桩基直径与壁厚、桩身倾斜度等多种因素对嵌岩桩水平承载力的影响,提出了确定嵌岩桩水平极限抗力的标准。研究表明：桩与围岩间的灌浆环会先于桩身发生破坏,因此可将灌浆环受拉破坏作为判断嵌岩桩达到水平极限承载力的标准;桩身倾斜度对嵌岩桩的水平极限承载力影响较大,直径和壁厚的增加,均能提高桩基的水平承载力。