Prediction Of Maximum Scour Depth Research Articles

Prediction of maximum scour depth in river bends by the Stacking model

Abstract The accurate prediction of maximum erosion depth in riverbeds is crucial for early protection of bank slopes. In this study, K-means clustering analysis was used for outlier identification and feature selection, resulting in Plan 1 with six influential features. Plan 2 included features selected by existing methods. Regression models were built using Support Vector Regression, Random Forest Regression (RF Regression), and eXtreme Gradient Boosting on sample data from Plan 1 and Plan 2. To enhance accuracy, a Stacking method with a feed-forward neural network was introduced as the meta-learner. Model performance was evaluated using root mean squared error, mean absolute error, mean absolute percentage error, and R2 coefficients. The results demonstrate that the performance of the three models in Plan 1 outperformed that of Plan 2, with improvements in R2 values of 0.0025, 0.0423, and 0.0205, respectively. Among the three regression models in Plan 1, RF Regression performs the best with an R2 value of 0.9149 but still lower than the 0.9389 achieved by the Stacking fusion model. Compared to the existing formulas, the Stacking model exhibits superior predictive performance. This study verifies the effectiveness of combining clustering analysis, feature selection, and the Stacking method in predicting maximum scour depth in bends, providing a novel approach for bank protection design.

Discussion of “Prediction of Maximum Scour Depth near Spur Dikes in Uniform Bed Sediment Using Stacked Generalization Ensemble Tree-Based Frameworks” by Manish Pandey, Mehdi Jamei, Masoud Karbasi, Iman Ahmadianfar, and Xuefeng Chu

Discussion of “Prediction of Maximum Scour Depth near Spur Dikes in Uniform Bed Sediment Using Stacked Generalization Ensemble Tree-Based Frameworks” by Manish Pandey, Mehdi Jamei, Masoud Karbasi, Iman Ahmadianfar, and Xuefeng Chu

Discussion of “Prediction of Maximum Scour Depth near Spur Dikes in Uniform Bed Sediment Using Stacked Generalization Ensemble Tree-Based Frameworks” by Manish Pandey, Mehdi Jamei, Masoud Karbasi, Iman Ahmadianfar, and Xuefeng Chu

Discussion of “Prediction of Maximum Scour Depth near Spur Dikes in Uniform Bed Sediment Using Stacked Generalization Ensemble Tree-Based Frameworks” by Manish Pandey, Mehdi Jamei, Masoud Karbasi, Iman Ahmadianfar, and Xuefeng Chu

Estimation of maximum scour depth around bridge piers under ice-covered conditions using data-driven methods

The scouring around bridge foundations is a significant concern in civil engineering. Several research has been conducted experimentally and numerically to study the maximum scour depth around the foundations of a bridge in open channel conditions. In cold regions, where ice forms on lakes, reservoirs, and rivers, the interaction between ice and hydraulic structures is further complicated. The flow distribution varies significantly leading to deeper and larger scouring around bridge foundations. The present study took advantage of the data-driven methods to investigate the impacts of ice conditions to maximum scour depth. In total, 96 datasets were extracted from previous studies. The M5 decision tree, Genetic Expression Programming (GEP), and Particle Swarm Optimization (PSO) were used in data analysis. The models were developed using the train-and-test approach to avoid over-training. The mentioned developed models were further compared with a previous empirical equation associated with the prediction of maximum scour depth around piers under ice conditions. Finally, a sensitivity analysis method was applied to evaluate the performance of the data-driven models. It was found that the approaching velocity and pier diameter play the most crucial role in determination of the maximum scour depth. The result is generally in agreement with those of previous experimental studies.

Effects of hooked-collar on the local scour around a lenticular bridge pier

This paper presents the results of comprehensive laboratory experiments to investigate the effects of hooked-collar on the scour development around a vertical pier with a lenticular cross section. The flow around the pier was uniform, steady, and under the clear-water condition. The axial scour profiles for cases without and with a lenticular hooked-collar were measured and the effects of hooked-collar dimensions and elevation from the bed were examined. To compute the efficiency of hooked-collar for scour prevention, the results of local scour for a bridge pier without a collar and a bridge pier with a plain collar, without a hooked wall, were used as benchmark data sets. A wide range of hooked-collar geometries such as the ratio of collar width to the pier width, Wc/Wp, ranging from 1.5 to 3.5, the ratio of hooked-collar wall height to the pier width, Hc/Wp, ranging from 0.15 to 0.6, and the ratio of collar elevation to the pier width, Ec/Wp, of −0.5, 0, and 0.5 were tested. The experimental results indicated that the equilibrium scour depth decreased with the ratio of hooked-collar to the pier width when Wc is twice the pier width, Wp. For Wc/Wp > 2, the scour depth was similar to the tests with an infinitely large pier width. In addition, the scour depth consistently reduced as the hooked-collar wall height, Hc, to the pier width, Wp, approached 0.3. The highest scour reduction efficiency was achieved when the hooked-collar being placed on the bed surface. Empirical models were developed for prediction of maximum scour depth near the lenticular bridge pier with a modified collar. The results showed that the volume of scour hole around a lenticular pier increased non-linearly with the maximum scour depth and it was independent of the hooked-collar geometry.

Live-bed pier scour in supercritical open-channel flows

Under a flow in supercritical regime, depending on the pier width to water depth ratio, the flow pattern around a bridge pier can take the form of a wall-jet-like bow wave or a detached hydraulic jump. The present work aims at analysing the maximum scour depth at piers in both flow patterns. A dedicated experimental set-up was used to produce the live-bed scour experiments, varying the inflow velocity and pier diameter. During the experiments, scour developed very rapidly, achieving equilibrium conditions after few minutes. No major differences between the maximum scour depth in the wall-jet-like bow wave and detached hydraulic jump cases were observed. Measured scour depths were of comparable magnitude and followed similar tendencies with controlling parameters as in subcritical flows. Scour formulas for piers in subcritical flow thus achieve a good accuracy in prediction of maximum scour depth at piers in supercritical flows.

Prediction of Maximum Scour Depth near Spur Dikes in Uniform Bed Sediment Using Stacked Generalization Ensemble Tree-Based Frameworks

The scouring process near spur dikes could jeopardize the stability of riverbanks. Thus, accurate estimation of the maximum scour depth near spur dikes is crucial in river engineering. However, due to the complexity of the scour phenomenon around these structures, it has been a challenge to accurately estimate the maximum scour depth. Few efforts have been made to develop a machine learning (ML) approach for such a purpose. In this study, two novel multilayer stacked generalization frameworks are developed to model the scour depth near a spur dike in a uniform sediment condition. Stacked tree-based frameworks consist of three standalone ML approaches, including multivariate adaptive regression spline, multigene genetic programming, and kernel extreme learning machine as the first layer and the boosting regression tree (BRT) and bagging regression tree (BGT) as meta learners. A total of 186 data points were collected from previous experimental studies, and 32 flume experiments were further conducted under clear water conditions at the Indian Institute of Technology (IIT) Roorkee Laboratory in this study. The performances of the models were assessed using various statistical metrics [e.g., correlation coefficient (R), root-mean-square error (RMSE), and mean absolute percentage error (MAPE)], graphical criteria, and some existing empirical equations. The modeling results demonstrated that the stacked BRT and BGT frameworks were superior to all the standalone ML approaches (R=0.9786, RMSE=0.1654, and MAPE=11.68 for BRT; and R=0.9742, RMSE=0.1831, and MAPE =11.29 for BGT). This finding was also confirmed by a comparison between the empirical correlations and the artificial intelligence models. In addition, the sensitivity analysis proved that the mean sediment size ratio (L/d50) was the most influential variable in estimating the scour depth near spur dikes.

Study of Scour at Double Submarine Pipelines due to Water Currents.(Dept.C)

The main objective of this study is to improve the influence of spacing between double submarine pipelines on local scour. Experiments have shown how local scour develops around double submarine pipelines in noncohesive sediment. Based on experimental results, a number of curves are illustrated to represent the relationship between maximum scour depth and Froude number for pipeline diameters, spacing between pipelines, flow depth and flow rate per unit width. It highlights the limitations of Froude number of estimate maximum scour depth at submarine pipelines. According to Froude number limitations, three formulae for prediction of maximum scour depth at submarine pipelines are presented.

Numerical simulation of local scour around bridge piers using novel inlet turbulent boundary conditions

The numerical results of local scour for bridge piers are significantly affected by the inlet turbulent boundary conditions. A novel self-sustaining model (SSM) and corresponding the new inlet turbulent boundary conditions are proposed to quickly obtain a stable flow field of horizontal homogeneity. The Reynolds averaged Navier-Stokes (RANS) equations, and standard k-ԑ turbulence model are employed to solve the complex flow around the bridge piers. Based on the sediment transport model considering the effect of the arbitrary slope of riverbed and the collapse of sediment, the dynamic evolution process of local scouring around bridge piers is simulated. Then, the applicability of the numerical approach for local scour around bridge pier is validated by the flume test comparing with the flow pattern, the maximum scour depth and the morphology of scour pit. Finally, the influence factors of local scour for bridge piers including common pier shapes and different angle of attack are studied. The numerical results indicate that the proposed SSM can develop homogeneous isotropic turbulence to fine simulate local scour with prescribed inlet turbulent boundary conditions. The established sediment collapse model can reasonably reflect the collapse process in scouring. Importantly, the proposed numerical methods can provide a reasonable prediction of maximum scour depth. In addition, the performances of the local scouring are greatly sensitive to the pier shape and the angle of attack. The inflow parallelling to piers or choosing appropriate pier shape helpful to ease the scour.

Local scour at complex bridge piers – experimental validation of current prediction methods

ABSTRACT Prediction of maximum scour depth at complex bridge piers is frequently decisive for the safe design of bridges. Some methods are available for this purpose but, due to the discrepancies of their predictions, such methods deserve further validation on the basis of new and independent data sets. For this purpose, clear-water experiments were performed by systematically varying the pile-cap elevation of a particular pier shape. Equilibrium scour depths were reached and measured and the comparison of predictions with measurements was established. The method of Sheppard and Renna, published in 2005, was found to predict with the highest accuracy the attained results for the tested complex pier. However, it should be stressed that this method slightly underestimates scour when the pile cap is out of the water or partly imbibed in the flow. It also under-predicts the scour depth when the pile cap is deeply buried in the bed.

Comparison of Three Commonly Used Equations for Calculating Local Scour Depth around Bridge Pier under Ice Covered Flow Condition

A precise prediction of maximum scour depth around bridge foundations under ice covered condition is crucial for their safe design because underestimation may result in bridge failure and over-estimation will lead to unnecessary construction costs. Compared to pier scour depth predictions within an open channel, few studies have attempted to predict the extent of pier scour depth under ice-covered condition. The present work examines scour under ice by using a series of clear-water flume experiments employing two adjacent circular bridge piers in a uniform bed were exposed to open channel and both rough and smooth ice covered channels. The measured scour depths were compared to three commonly used bridge scour equations including Gao’s simplified equation, the HEC-18/Jones equation, and the Froehlich Design Equation. The present study has several advantages as it adds to the understanding of the physics of bridge pier scour under ice cover flow condition, it checks the validity and reliability of commonly used bridge pier equations, and it reveals whether they are valid for the case of scour under ice-covered flow conditions. In addition, it explains how accurately an equation developed for scour under open channel flow can predict scour around bridge piers under ice-covered flow condition.

Prediction of Maximum Scour Depth Using Scaled Down Bridge Model in Laboratory

Recently, United States faced catastrophic flooding in West Virginia, Texas, Louisiana, Oklahoma, Arkansas, and the flooding resulted in several bridge failures. Among them, bridge scour is one of the main causes behind many bridge failures and financial losses as well as loss of life. Since 1960, a lot of scour research have been done and the several estimation methods were already in the hand of hydraulic engineers. Currently, the issues of scour are once again rising topic because the occurrence of extreme weather events are expected to worsen in frequency. Furthermore, current practice of scour estimation shows over-prediction and sometimes, under-prediction. One possible reason is adding separate estimates of contraction and local scour when in fact these processes occur simultaneously. Another possible reason is these equations are based on the experiments using free-surface flow in idealized-rectangular flumes even though extreme flood event can cause bridge overtopping flow in combination with submerged orifice flow. In this study, experiments were carried out in a compound shape channel using scaled down bridge model in different flow conditions (free, submerged orifice and overtopping flow). Based on the findings from laboratory experiments coupled with widely used empirical scour estimation methods, such as CSU pier scour equation, Melville-Sheppard equation and Ambient pier scour method, we will present a comprehensive way of predicting design scour depth which overcomes problem regarding separate estimation of different scour depths. In addition to develop a procedure for estimating of design scour depth, the mechanism and characteristics of scour process will be investigated and a comparison of these equations will be presented.

Predicting scour depth at seawalls using GP and ANNs

Accurate prediction of maximum scour depth is important for the optimum design of seawall structure. Owing to the complex interaction of the incident waves, sediment bed, and seawalls, the prediction of the scour depth is not an easy task to accomplish. Undermining the recent experimental and numerical advancement, the available empirical equations have limited accuracy and applicability. The aim of this study is to investigate the application of robust data-mining methods including genetic programming (GP) and artificial neural networks (ANNs) for predicting the maximum scour depth at seawalls under the broken and breaking waves action. The performance of GP and ANNs models has been compared with the existing empirical formulas employing statistical measures. The results indicated that both the GP and ANNs models functioned significantly better than the existing empirical formulas. Furthermore, the capability of GP was used to produce meaningful mathematical rules, and an analytical formula for predicting the maximum scour depth at seawalls under breaking and broken waves' attacks was developed by utilizing GP.

Prediction of maximum scour depth around piers with debris accumulation using EPR, MT, and GEP models

Pier scour phenomena in the presence of debris accumulation have attracted the attention of engineers to present a precise prediction of the local scour depth. Most experimental studies of pier scour depth with debris accumulation have been performed to find an accurate formula to predict the local scour depth. However, an empirical equation with appropriate capacity of validation is not available to evaluate the local scour depth. In this way, gene-expression programming (GEP), evolutionary polynomial regression (EPR), and model tree (MT) based formulations are used to develop to predict the scour depth around bridge piers with debris effects. Laboratory data sets utilized to perform models are collected from different literature. Effective parameters on the local scour depth include geometric characterizations of bridge piers and debris, physical properties of bed sediment, and approaching flow characteristics. The efficiency of the training stages for the GEP, MT, and EPR models are investigated. Performances of the testing results for these models are compared with the traditional approaches based on regression methods. The uncertainty prediction of the MT was quantified and compared with those of existing models. Also, sensitivity analysis was performed to assign effective parameters on the scour depth prediction.

Scour prediction and scour protections in offshore wind farms

This paper is the result of research whose main objective is to analyse different methods used for the prediction of maximum scour depth and scour extension, and for the design of scour protections in offshore wind farms located in shallow water, using medium and large diameter monopile foundations. Physical agents such as waves, currents and wind play a major role in the design of structures like offshore farms. As a result, the study has highlighted the need for introducing experience backed climate monomials such as the dimensionless wave height parameter (H0) and proposes the use of formulations that can express the extent of scour protections as a function of waves in transitional waters.

Clear-water scour depth below underwater pipelines

The paper presents (1) a semi-theoretical model for the computation of maximum clear-water scour depth below underwater pipelines in uniform sediments under steady flow and (2) an experimental investigation on the influence of upward seepage on clear-water scour depth below underwater pipelines. Based on the “image method” of the potential flow theory for the flow through the gap between a circular pipeline and the scoured bed, a theoretical model is presented for the computation of maximum scour depth below underwater pipelines in clear-water condition considering the wall correction. Also, a simple theoretical calculation, that involves Chiew's (1991) [Chiew, Y.M., 1991. “Prediction of maximum scour depth at submarine pipelines.” J Hydraul Eng 117(4), 452–466] gap flow curve, is proposed to estimate the maximum scour depth considering the wall correction. The computed results agree satisfactorily with the experimental data. In addition, the potential predictors of the maximum scour depth given by different researchers are compared with the experimental data. The result of an experimental investigation on the scour depth below pipelines under the influence of upward seepage through the bed sediment is presented. In general, the scour depth below pipelines with upward seepage is smaller than that without seepage. There exists a critical value of the ratio of seepage velocity to main flow velocity that corresponds to a minimum scour depth.

Local Scour Downstream of Box‐Culvert Outlets

This laboratory study investigates the local scouring phenomenon in sand that occurs downstream of box culverts. Although culvert hydraulics can include special cases, such as culverts on hydraulically steep slopes for which special energy dissipators at an outlet must be provided to handle supercritical flows, this study was restricted to culverts on horizontal or mild slopes that operate freely and do not require special energy dissipators at their outlets. The principal factors governing this form of local scouring were found to be the discharge rate, the culvert width, the tailwater depth, the downstream channel width, and the bed‐material properties. The experimental program investigated the effects of these principal variables on the local scour hole characteristics. The investigation also reviewed some well‐known empirical formulas for the prediction of maximum scour depth, under a variety of hydraulic conditions. One such relationship for maximum scour depth in a stone bed downstream of a culvert outlet, was modified in this study to make it applicable to scour in sand beds.

Prediction of Maximum Scour Depth at Submarine Pipelines

This paper examines and reviews published results relating to local scour around submarine pipelines. It highlights the limitations of existing methods for estimating scour depth at the pipeline. Based on experimental results, the study proposes an empirical function relating the amount of gap flow through the scour hole for given flow conditions. With the aid of this function, it is possible to predict the maximum Scour depth at submarine pipelines for given flow and geometric boundary conditions. Published results suggest that the maximum equilibrium scour depth occurs when the pipeline is just lying on a plane bed and subjected to a pure unidirectional current. The undisturbed bed shear stress is equal to the critical shear stress for sediment entrainment. This condition implies that there is no general sediment transport away from the pipeline. The predicted maximum scour depth using the iterative method proposed in this study compares well with experimental results.