Prediction of local scour around circular piles under waves using a novel artificial intelligence approach

Abstract

The scour phenomena around vertical piles in oceans and under waves may influence the structure stability. Therefore, accurately predicting the scour depth is an important task in the design of piles. Empirical approaches often do not provide the required accuracy compared with data mining methods for modeling such complex processes. The main objective of this study is to develop three data-driven methods, locally weighted linear regression (LWLR), support vector machine (SVR), and multivariate linear regression (MLR) to predict the scour depth around vertical piles due to waves in a sand bed. It is the first effort to develop the LWLR to predict scour depth around vertical piles. The models simulate the scour depth mainly based on Shields parameter, pile Reynolds number, grain Reynolds number, Keulegan–Carpenter number, and sediment number. 111 laboratory datasets, derived from several experimental studies, were used for the modeling. The results indicated that the LWLR provided highly accurate predictions of the scour depths around piles (R?=?0.939 and RMSE = 0.075). Overall, this study demonstrated that the LWLR can be used as a valuable tool to predict the wave-induced scour around piles.     

NF-GMDH-Based self-organized systems to predict bridge pier scour depth under debris flow effects

Existence of debris structures inevitably ascends the rate of scour process around bridge piers and flow area not only lead into remarkable deviation of flow but also increase the velocity around bridge piers. A myriad of experimental and field studies to understand effective parameters on the scour depth with debris effects were conducted. To reach permissible values of the scour depth for the practical uses, relationships extracted in previous investigations suffer from lack of generalization for experimental data ranges. In this way, neuro-fuzzy group method of data handling (NF-GMDH)-based self-organized models is applied to evaluate the pier scour depth. In this study, NF-GMDH network is implemented using evolutionary algorithms listed particle swarm optimization (PSO), gravitational search algorithm (GSA), and genetic algorithm (GA). In all, 243 experimental datasets including a wide range of input and output parameters to develop the proposed models were compiled from various literature. The efficiency of NF-GMDH networks for training and testing stages was perused. NF-GMDH-PSO model provided the scour depth with more precise predictions (root mean squared error (RMSE)?=?0.388 and scatter index (SI)?=?0.343) in comparison with NF-GMDH-GA (RMSE?=?0.402 and SI?=?0.361) and NF-GMDH-GSA (RMSE?=?0.456 and SI?=?0.407) networks. In addition, blockage ratio (ΔA) was taken into account as the most sumptuous parameter with utmost level of effectiveness using the sensitivity analysis.     

Developing empirical formulas for assessing the scour of vertical and inclined piers

Abstract

Because scour is one of the main reasons for bridge failure, this study focuses on accurately predicting the maximum scour depth around different vertical and inclined piers. Scouring is an issue of concern in the bridge design process, as most existing equations for predicting local scour near bridge piers suffer from over- or underprediction issues, resulting in higher foundation costs or bridge failure and inaccurate predictions of the scour around piers. The dimensionless maximum scour depths (y_s/D) of vertical and inclined piers were investigated for seven pier shapes with different L/D ratios and four inclination angles (θ) under shallow flow conditions. The inclined pier configuration reduced the y_s/D of the piers. The maximum y_s/D was observed for a rectangular pier with an L/D of 4.5 in both vertical and inclined configurations (θ of 10, 15 and 21°, respectively). The y_s/D was significantly decreased by increasing the angle of the pier from 10 to 30°. The y_s/D of the inclined rectangular piers decreased as θ decreased from 30 to 10° and the L/D ratio increased from 1 to 4.5. The best y_s/D results were obtained for inclined rectangular piers at a θ value of 30° and an L/D ratio of 7.5 compared to other shapes and inclination angles. New equations were developed to predict the local scour depth for circular, square and rectangular bridge piers. The equations yielded excellent results for predicting the maximum clear water scour depth around vertical and inclined piers with inclination angles of 10, 15, 21 and 30°, respectively.     

Local scour prediction around piers with complex geometry

A laboratory study of local scour at complex piers under steady clear-water conditions is presented. The term complex piers is used to define a bridge pier comprising of a column, pile cap, and pile group. Comprehensive data over the full range of possible pile cap elevations for complex piers with different geometries were obtained using five complex pier models, which were scaled down from existing bridges in Malaysia. The data are used to evaluate existing methodologies for characterizing the effective width of complex piers with varying pile cap location relative to the undisturbed streambed. The effect of pile cap location on scour depth is also addressed. To improve the predictions of local scour at complex piers, the new data and some previous data are used to propose a new method to predict local scour depth at complex piers.     

强潮流作用下桥墩不对称“双肾型”冲刷地貌特征与机理

本文在海图地形资料分析桥轴线附近的海床自然冲刷的基础上,利用多波束测深技术研究大桥主墩附近局部冲刷地形。结果表明,该大桥桥位附近地形冲刷较显著,且大桥主墩位置有持续冲刷的趋势;主墩上、下游群桩最大冲刷深度呈上游最深、中部淤积、下游渐深的不对称形态,最大局部冲刷深度为4 m;桥墩整体冲刷坑形态呈南北“双肾型”;潮流流向与桥墩迎流面存在偏南的入射角,使得各桥墩南侧的最大冲深和冲刷范围均大于北侧。     

New expression-based models to estimate scour depth at clear water conditions in rectangular channels

Scouring in the channel contractions occurs due to the flow concentration within them inducing excessive bed shear stress. This is a complex process, so it is difficult to describe it through a general empirical model, the present research work describes contemporary conceptual relationships to estimate the local scour depth under equilibrium and clear water conditions in rectangular channels. Incidentally, gene-expression programming (GEP), evolutionary polynomial regression (EPR), and model tree (MT)-based formulations were utilized to predict the scour depth at long contractions. The input variables comprising average flow velocity, critical threshold velocity of sediment movement, flow depth, median particle diameter, geometric standard deviation, and uncontracted and contracted channel widths were used to feed the applied models. The performances of the developed approach were compared with those calculated using existing scour prediction equations. The results showed that the developed MT approach in terms of linear relationships could predict the scour depth more precisely than GEP, EPR, and the traditional equations. What is more, dimensionless parameter of h₁/b₁ (ratio of upstream flow depth to uncontracted channel width) was determined as the most influential variable in predicting the scour depth in long contractions.     

Experimental Study on Local Scour Around Bridge Piers in Tidal Current

Local scour around a bridge pier is an important pm‘mneter for the design of a bridge. Compared with the local scour in a mono-directional current, the local scour in a tidal current has its unique characteristics. In this paper, several aspects of local scour around bridge piers in tidal current, including the scour development process, the plane form of a scour hole and the maximum scour depth, are studied through movable bed flume experiments.     

Linear genetic programming for prediction of circular pile scour

Genetic programming (GP) has nowadays attracted the attention of researchers in the prediction of hydraulic data. This study presents linear genetic programming (LGP), which is an extension to GP, as an alternative tool in the prediction of scour depth around a circular pile due to waves in medium dense silt and sand bed. Field measurements were used to develop LGP models. The proposed LGP models were compared with adaptive neuro-fuzzy inference system (ANFIS) model results. The predictions of LGP models were observed to be in good agreement with measured data, and quite better than ANFIS and regression-based equation of scour depth at circular piles. The results were tabulated in terms of statistical error measures and illustrated via scatter plots.     

Circular time-domain reflectometry system for monitoring bridge scour depth

Abstract

Sediment has a severe effect on bridge stability, and time-domain reflectometry (TDR) is a suitable method for assessing scour depth. This paper presents a fundamental study to demonstrate the suitability of a circular TDR system to enhance the resolution when monitoring scour depth with consideration of detailed local changes over a wide area around piers. A total of 32 electrodes are vertically installed on a cylinder pier around the circumference at ～7.36?mm intervals. Scour depth is investigated through small-scale laboratory experiments, where a measured waveform reflects the artificially constructed scour depth with high resolution (≈5?mm). Different scour types including circular, mushroom, elliptical, and irregular shapes are developed to verify the application of circular TDR, and shapes are predicted through the detailed local distribution. The influences of the reflected waveform according to water level change, temperature variation, and salinity effect are investigated as additional considerations, and the relative deviation of scour depth is analyzed. This study demonstrates that the proposed circular TDR system achieves better resolution than existing single TDR systems and may provide a better alternative technique for monitoring scour depth.     

Evaluation of the applicability of pier local scour formulae using laboratory and field data

The reliable estimation of the local scour depth at a bridge pier is essential for proper design and maintenance of bridge piers. Most local scour formulae have been developed based on the results of laboratory experiments. The formulae based on laboratory data do not often produce reasonable predictions for field piers because laboratory investigations are apt to oversimplify or ignore many of the complexities of the flow fields around the bridge piers. Validation of the formulae is necessary in order to ascertain which of the formulae are able to provide reasonable estimates of the local scour depth. In this study, six commonly cited formulae based on laboratory data or field data were selected for validation using 180 laboratory data sets gathered from the literature and 446 field data sets collected from four countries. The six formulae validated in this paper are the Colorado State University (CSU), Neill, Froehlich, Breuser, Laursen, and simplified Chinese formulae. Comparisons between the predicted and measured depths were performed using scour from the laboratory and field data. An artificial neural network technique was also applied in order to compare the tendencies between the field and laboratory data sets.     

Linear genetic programming to scour below submerged pipeline

Genetic programming (GP) has nowadays attracted the attention of researchers in the prediction of hydraulic data. This study presents Linear Genetic Programming (LGP), which is an extension to GP, as an alternative tool in the prediction of scour depth below a pipeline. The data sets of laboratory measurements were collected from published literature and were used to develop LGP models. The proposed LGP models were compared with adaptive neuro-fuzzy inference system (ANFIS) model results. The predictions of LGP were observed to be in good agreement with measured data, and quite better than ANFIS and regression-based equation of scour depth at submerged pipeline.     

GMDH to predict scour depth around a pier in cohesive soils

This study presents new application of group method of data handling (GMDH) to predict scour depth around a vertical pier in cohesive soils. Quadratic polynomial was used to develop GMDH network. Back propagation algorithm has been utilized to adjust weighting coefficients of GMDH polynomial thorough trial and error method. Parameters such as initial water content, shear strength, compaction of cohesive bed materials, clay content of cohesive soils, and flow conditions are main factors affecting cohesive scour. Performances of the GMDH network were compared with those obtained using several traditional equations. The results indicated that the proposed GMDH-BP has produced quite better scour depth prediction than those obtained using traditional equations. To assign the most significant parameter on scour process in cohesive soils, sensitivity analysis was performed for the GMDH-BP network and the results showed that clay percentage was the most effective parameter on scour depth. The error parameter for three classes of IWC and C_p showed that the GMDH-BP model yielded better scour prediction in ranges of IWC = 36.3–42.28% and C_p = 35–100%. In particular application, the GMDH network was proved very successful compared to traditional equations. The GMDH network was presented as a new soft computing technique for the scour depth prediction around bridge pier in cohesive bed materials.     

港珠澳大桥青州航道桥桥墩基础冲刷试验研究

桥墩基础冲刷是桥梁毁坏的重要因素,是桥梁基础设计的关键指标之一。目前国内外对于桥墩基础在复杂动力条件下冲刷深度的研究常采用物理模型试验方法,利用正态系列模型方法,在波流水槽中研究了水流、潮流和波流共同作用下青州航道桥索塔基础周围流态变化和局部冲刷特征。研究结果表明,桥墩最大冲刷深度和冲淤范围与水流流速、桥墩轴线与水流夹角和波浪等因素有关;在潮流最大流速和恒定流流速一致情况下,桥墩局部冲刷深度达到平衡后,将会达到与恒定流基本一致的最大冲深;波流共同作用下的最大冲刷深度比恒定流增加10%左右。设计桥墩形状在100年一遇水流和波浪共同作用下桥墩基础局部最大冲刷深度为13.7 m。     

Clear water scour around a finite array of cylinders

This experimental study presents clear-water scour and deposition patterns around hexagonal arrays of circular cylinders in steady flow conditions. Understanding the scour processes around such configurations could facilitate the design of several hydraulic and marine engineering structures, such as bridge piers and piles. The flow alteration caused by the examined porous obstacles depends on the solid volume fraction of the obstacles and on the angle of attack of the incoming flow, due to the limited number of cylinders constituting the array. Flume experiments with erodible bed were carried out for four array densities (solid volume fractions: 0.14, 0.20, 0.32 and 0.56) under three different orientations (regular, angled and staggered configurations). The scour/deposition characteristics were obtained by means of laser scanner and the results were compared to solid cylinders of equal circumambient diameter. Different angles of attack of the incoming flow lead to different blockage ratios, which have direct impact on the scour characteristics and deposition patterns. The arrays with the higher solid volume fraction generated scour/deposition patterns similar to solid cylinder, while in the arrays with the lower solid volume fractions, local scour around the individual small cylinders became evident. Finally, considering that the load bearing capacity of a pier basically depends on the area of its cross-section, a comparison of the maximum induced scour depth and volume by the cylinder arrays and the solid cylinder with equal solid cross-sectional area is presented, in order to introduce an alternative pier configuration that induces less scour. The results showed that the array of cylinders could generate 27% less scour volume and 22% less scour depth compared to its single solid cylinder counterpart.     

Estimation of pile group scour using adaptive neuro-fuzzy approach

An accurate estimation of scour depth around piles is important for coastal and ocean engineers involved in the design of marine structures. Owing to the complexity of the problem, most conventional approaches are often unable to provide sufficiently accurate results. In this paper, an alternative attempt is made herein to develop adaptive neuro-fuzzy inference system (ANFIS) models for predicting scour depth as well as scour width for a group of piles supporting a pier. The ANFIS model provides the system identification and interpretability of the fuzzy models and the learning capability of neural networks in a single system. Two combinations of input data were used in the analyses to predict scour depth: the first input combination involves dimensional parameters such as wave height, wave period, and water depth, while the second combination contains nondimensional numbers including the Reynolds number, the Keulegan–Carpenter number, the Shields parameter and the sediment number. The test results show that ANFIS performs better than the existing empirical formulae. The ANFIS predicts scour depth better when it is trained with the original (dimensional) rather than the nondimensional data. The depth of scour was predicted more accurately than its width. A sensitivity analysis showed that scour depth is governed mainly by the Keulegan–Carpenter number, and wave height has a greater influence on scour depth than the other independent parameters.     

大型桥梁钢沉井下沉过程局部冲刷研究

钢沉井下沉过程中局部冲刷的研究是同类桥墩设计和施工十分关心的重要课题,它对保证钢沉井安全有效施工、桥梁设计中施工期桥墩最大冲深、失稳和安全计算有重要参考价值。通过室内试验研究了钢沉井下沉过程中的局部冲刷机理和冲刷形态,探讨了桥墩下部钢沉井基础施工的相对高程对局部冲刷的变化规律,并将试验研究所获得的局部冲刷规律和影响因素,采用墩型系数方法引入局部冲刷计算中,给出了计算公式。研究成果补充了国家行业规范内容,对同类工程的设计、施工具有借鉴和指导意义。     

GMDH-GEP to predict free span expansion rates below pipelines under waves

ABSTRACT

In this research, group method of data handling (GMDH) as a one of the self-organized approaches is utilized to predict three-dimensional free span expansion rates around pipeline due to waves. The GMDH network is developed using gene-expression programming (GEP) algorithm. In this way, GEP was performed in each neuron of GMDH instead of polynomial quadratic neuron. Effective parameters on the three-dimensional scour rates include sediment size, pipeline geometry, and wave characteristics upstream of pipeline. Four-dimensionless parameters are considered as input variables by means of dimensional analysis technique. Furthermore, scour rates along the pipeline, vertical scour rate, and additionally scour rates in the left and right of pipeline are determined as output parameters. Results of the proposed GMDH-GEP models for the training stages and testing ones are evaluated using various statistical indices. Performances of the GMDH-GEP models are compared with artificial neural network (ANN), GEP, GMDH, and traditional equations-based regression models. Moreover, sensitivity analysis and parametric study are conducted to perceive influences of different input parameters on the three-dimensional scour rates.     

中性网格对圆桩局部冲刷的水动力弱化及防护效果分析

针对水下桩墩的局部冲刷问题,提出一种适用范围广、防冲促淤效果显著的防护措施。该防护措施把一种相对密度略大于水、几何特征特殊的中性网格结构完全覆盖在冲刷坑或可能出现冲刷坑的床面上,以减弱冲刷坑内水动力,促进泥沙落淤,达到减轻局部冲刷的目的。通过数值模拟和水槽试验探讨了中性网格结构对圆桩周围冲刷坑内水动力及床面形态的影响,并研究了网孔尺寸对防冲促淤效果的影响规律。结果表明：该中性网格结构能显著减小局部冲刷坑内的流速,有效抑制局部冲刷,且对桩前来流来沙的影响微弱。孔径比7.7的网格防护结构可以使无黏性沙床上圆桩的局部冲刷深度减少92%,已存在的冲刷坑则可被修复73%。这些研究成果为桩墩局部冲刷防护提供一种新的思路。     

长江口沙波分布区桥墩局部冲刷深度计算公式的改进

利用多波束水深仪、浅地层剖面仪和多普勒流速仪对长江口苏通大桥南、北主墩区域现场测量,结果显示主墩周围最大冲刷深度为8.3 m和19.6 m。建墩前后河床形态变化显著,建墩后桥墩所在床面由平床改变为典型不对称沙波发育,平均波长为30.8 m和23.1 m,平均波高为4.2 m和9.4 m,陡坡朝向下游。基于实测水文条件和地形资料,以沙波起动流速和落急最大流速分别取代单向流作用下"平床"假定的桥墩局部冲刷计算公式中单颗粒泥沙的起动流速和墩前流速,获得河口涨落潮双向流作用下沙波底床桥墩局部冲刷计算公式。且该公式计算的苏通大桥南、北主墩局部冲刷深度为9.5 m和22.1 m,非常接近实测值。     

Three-dimensional velocity measurements around bridge piers in gravel bed

The experimental results of time average velocity components measured around circular pier models during transient scour stage using acoustic Doppler velocimeter are shown for flow pattern and turbulence characteristics. Totally, four experiments were performed under clear water scour conditions in a model of gravel bed stream. Four circular pier models of diameter 6.6, 8.4, 11.5, and 13.5?cm were used for this study. Detailed controlled measurements on velocity components, and turbulence intensities near the pier and in scour hole at 0° and 180° plane are shown. Flow structure around a pier model in the presence of a scoured region was compared with the flow structure similarly noticed around all pier model runs by utilizing the observations taken at 0° and 180° plane from flow axis. Size of the primary vortex at 0° plane with largest diameter pier model in place (R4 run) is found to be maximum and was approximately 61% larger than that for smallest diameter pier model in place (R1 run). The time-averaged velocity components of turbulence intensities plots at 0° and 180° planes are also presented around each pier.