Labyrinth weirs are commonly used hydraulic structures to increase discharge efficiency in free-overflow discharges. These weirs provide higher discharge efficiency than conventional linear weirs at the same headwaters. This study investigated hydraulic performance of rectangular labyrinth weirs under different geometries and flow conditions experimentally and numerically. The numerical model was verified and validated using the grid convergence index method recommended in the literature and the experimental data. The numerical modelling results showed that the increase in performance of the labyrinth weir was caused by the distribution of lateral velocities in the inlet keys, while the nappe interference in the downstream keys was responsible for the decrease in performance at high headwater. Within the limitations of 1.5≤L/B≤2.33 and 0.1<Ho/P<0.61, a performance increase of 44% on average and a maximum of 67% for unit channel width was found for rectangular labyrinth weirs compared to linear weirs. For given limitations, two new empirical formulas with high correlation were derived to estimate the discharge coefficients of rectangular labyrinth weirs based on channel width (B) and weir crest length (L) for Ho/P>0.1 in which are widely used in practice. It is concluded that, when compared with some of the data in the literature, the empirical formulas give satisfactory results.
{"title":"Experimental and numerical investigation of rectangular Labyrinth weirs in open channel","authors":"M. Cihan Aydin, Ali Emre Ulu, Ercan Işik","doi":"10.1680/jwama.22.00112","DOIUrl":"https://doi.org/10.1680/jwama.22.00112","url":null,"abstract":"Labyrinth weirs are commonly used hydraulic structures to increase discharge efficiency in free-overflow discharges. These weirs provide higher discharge efficiency than conventional linear weirs at the same headwaters. This study investigated hydraulic performance of rectangular labyrinth weirs under different geometries and flow conditions experimentally and numerically. The numerical model was verified and validated using the grid convergence index method recommended in the literature and the experimental data. The numerical modelling results showed that the increase in performance of the labyrinth weir was caused by the distribution of lateral velocities in the inlet keys, while the nappe interference in the downstream keys was responsible for the decrease in performance at high headwater. Within the limitations of 1.5≤<i>L/B</i>≤2.33 and 0.1<<i>H<sub>o</sub>/P</i><0.61, a performance increase of 44% on average and a maximum of 67% for unit channel width was found for rectangular labyrinth weirs compared to linear weirs. For given limitations, two new empirical formulas with high correlation were derived to estimate the discharge coefficients of rectangular labyrinth weirs based on channel width (<i>B</i>) and weir crest length (<i>L</i>) for <i>H<sub>o</sub></i>/<i>P</i>>0.1 in which are widely used in practice. It is concluded that, when compared with some of the data in the literature, the empirical formulas give satisfactory results.","PeriodicalId":54569,"journal":{"name":"Proceedings of the Institution of Civil Engineers-Water Management","volume":"1 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2024-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140804861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The evolution of the bar-pool configurations in response to the upstream damming has significant impacts on channel regulations, navigations, water intakes and protection projects. Herein, this paper reports and analyses the evolution of bar-pool configurations in the bends along the Lower Jingjiang Reach (LJR) after the impoundment of the Three Gorge Dam (TGD), which is distinguished from the natural evolution of the bends. The main factors to the different adjustments of bar-pool configurations are the changes in incoming flow and sediment regime during pre- and post-TGD periods. To capture the changes in the bar-pool configurations, we have presented a new cross-sectional geometrical characteristic - relative lateral distance of the centroid (RLDC). RLDC has close relations with incoming sediment coefficient (i.e. incoming discharge divided by suspended sediment concentration during flood season). RLDC is better than the conventional cross-sectional geometrical characteristic (e.g. width to depth ratio) to indicate the bar-pool configurations of the downstream of the large dam projects. Based on the delayed response model, the values of RLDC in the bends of the LJR are related to the previous 4-6 years’ incoming sediment coefficient, and the correlation coefficient is about 0.90. RLDC is expected to capture the variations of bar-pool configurations in the bends downstream of the large dam project.
{"title":"Cross-sectional geometrical characteristic for the bends along the lower Jingjiang reach","authors":"Haoyong Tian, Chenchen Yao, Zaimin Ren, Zhaofang Zeng, Jing Guo, Minghui Yu, Chunchen Xia","doi":"10.1680/jwama.23.00062","DOIUrl":"https://doi.org/10.1680/jwama.23.00062","url":null,"abstract":"The evolution of the bar-pool configurations in response to the upstream damming has significant impacts on channel regulations, navigations, water intakes and protection projects. Herein, this paper reports and analyses the evolution of bar-pool configurations in the bends along the Lower Jingjiang Reach (LJR) after the impoundment of the Three Gorge Dam (TGD), which is distinguished from the natural evolution of the bends. The main factors to the different adjustments of bar-pool configurations are the changes in incoming flow and sediment regime during pre- and post-TGD periods. To capture the changes in the bar-pool configurations, we have presented a new cross-sectional geometrical characteristic - relative lateral distance of the centroid (RLDC). RLDC has close relations with incoming sediment coefficient (i.e. incoming discharge divided by suspended sediment concentration during flood season). RLDC is better than the conventional cross-sectional geometrical characteristic (e.g. width to depth ratio) to indicate the bar-pool configurations of the downstream of the large dam projects. Based on the delayed response model, the values of RLDC in the bends of the LJR are related to the previous 4-6 years’ incoming sediment coefficient, and the correlation coefficient is about 0.90. RLDC is expected to capture the variations of bar-pool configurations in the bends downstream of the large dam project.","PeriodicalId":54569,"journal":{"name":"Proceedings of the Institution of Civil Engineers-Water Management","volume":"251 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140616024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The short-term dramatic degradation of the riverbed poses a great threat to the river and the functioning of infrastructure in its vicinity. In this paper, a straight flume experiment was carried out to measure the velocity, water level, riverbed elevation, and riverbed morphology under different experiment conditions, combined with the SfM (Structure-from-Motion) method to generate the riverbed DEMs and orthomosaic, and the impact of flexible net on riverbed evolution of degrading channel was studied. This study reveals that under the action of the flexible net, the degradation mode of the riverbed changes from parallel degradation to rotational degradation with erosion datum as the fulcrum, and with an increase in the longitudinal length of the flexible net, the riverbed's protection efficiency grows. The flexible net can effectively limit the movement of sediment under the net, and the finer sediment silting raises erosion datum elevation. It is noticed that the location and morphological characteristics of the downstream scour holes are greatly affected by the deformation of the erosion datum. The scour hole shows an asymmetric distribution because of the uneven scouring of the flow to the downstream riverbed. The research results have a certain guiding role in the management of degrading channels.
河床的短期急剧退化对河流及其附近基础设施的运行构成了巨大威胁。本文开展了直槽实验，测量了不同实验条件下的流速、水位、河床高程和河床形态，并结合 SfM（Structure-from-Motion）方法生成了河床 DEM 和正射影像图，研究了柔性网对退化河道河床演变的影响。研究发现，在柔性网的作用下，河床的退化模式由平行退化转变为以侵蚀基准面为支点的旋转退化，且随着柔性网纵向长度的增加，河床的保护效率也随之提高。柔性网能有效限制网下泥沙的运动，而泥沙淤积越细，侵蚀基准面标高越高。可以发现，下游冲刷孔的位置和形态特征受侵蚀基准面变形的影响很大。由于水流对下游河床的冲刷不均匀，冲刷孔呈现不对称分布。研究成果对退化河道的治理具有一定的指导作用。
{"title":"Impacts of the flexible net on riverbed evolution in degrading channels","authors":"Runxiang Li, Jing Zhang, Zhixue Guo","doi":"10.1680/jwama.23.00018","DOIUrl":"https://doi.org/10.1680/jwama.23.00018","url":null,"abstract":"The short-term dramatic degradation of the riverbed poses a great threat to the river and the functioning of infrastructure in its vicinity. In this paper, a straight flume experiment was carried out to measure the velocity, water level, riverbed elevation, and riverbed morphology under different experiment conditions, combined with the SfM (Structure-from-Motion) method to generate the riverbed DEMs and orthomosaic, and the impact of flexible net on riverbed evolution of degrading channel was studied. This study reveals that under the action of the flexible net, the degradation mode of the riverbed changes from parallel degradation to rotational degradation with erosion datum as the fulcrum, and with an increase in the longitudinal length of the flexible net, the riverbed's protection efficiency grows. The flexible net can effectively limit the movement of sediment under the net, and the finer sediment silting raises erosion datum elevation. It is noticed that the location and morphological characteristics of the downstream scour holes are greatly affected by the deformation of the erosion datum. The scour hole shows an asymmetric distribution because of the uneven scouring of the flow to the downstream riverbed. The research results have a certain guiding role in the management of degrading channels.","PeriodicalId":54569,"journal":{"name":"Proceedings of the Institution of Civil Engineers-Water Management","volume":"10 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139025490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Determining the locations and shapes of silt storage dams (SSDs) is necessary before planning and constructing new ones or maintaining old ones. Google images with a spatial resolution of 0.54 m were cropped, labelled and enhanced to establish two schemes of remote sensing images that contain SSDs with different input and batch sizes. Five deep learning models (FCN (fully connected convolutional neural network, SegNet (deep convolutional encoder–decoder architecture for image segmentation), U-Net (convolutional networks for biomedical image segmentation), PSPNet (pyramid scene parsing network) and DeepLab-V3+) were constructed to extract SSDs from the images based on the two schemes. The loss curves, accuracies and extraction results derived from the five models were compared to identify the optimal model for SSD extraction. The results show that the overall accuracies, F 1 scores and mean intersections over unions obtained from DeepLab-V3+ were, respectively, 95.29%, 70.33% and 74.13% for scheme 1 (S1) and 96.29%, 73.34% and 76.99% for scheme 2 (S2), which were better than the values for other models. PSPNet had the shortest training times (128 s/step for S1 and 348 s/step for S2). An input size of 480 × 480 pixels, a batch size of 4 and 2304 images enhanced the extraction accuracy and prevented overfitting. The results provide a reference for the planning, construction and maintenance of water and soil conservation measures.
{"title":"Performance comparison of deep learning models to extract silt storage dams in remote sensing images to prevent water loss and soil erosion","authors":"Jingwei Hou, Moyan Zhu, Bo Hou","doi":"10.1680/jwama.22.00094","DOIUrl":"https://doi.org/10.1680/jwama.22.00094","url":null,"abstract":"Determining the locations and shapes of silt storage dams (SSDs) is necessary before planning and constructing new ones or maintaining old ones. Google images with a spatial resolution of 0.54 m were cropped, labelled and enhanced to establish two schemes of remote sensing images that contain SSDs with different input and batch sizes. Five deep learning models (FCN (fully connected convolutional neural network, SegNet (deep convolutional encoder–decoder architecture for image segmentation), U-Net (convolutional networks for biomedical image segmentation), PSPNet (pyramid scene parsing network) and DeepLab-V3+) were constructed to extract SSDs from the images based on the two schemes. The loss curves, accuracies and extraction results derived from the five models were compared to identify the optimal model for SSD extraction. The results show that the overall accuracies, F 1 scores and mean intersections over unions obtained from DeepLab-V3+ were, respectively, 95.29%, 70.33% and 74.13% for scheme 1 (S1) and 96.29%, 73.34% and 76.99% for scheme 2 (S2), which were better than the values for other models. PSPNet had the shortest training times (128 s/step for S1 and 348 s/step for S2). An input size of 480 × 480 pixels, a batch size of 4 and 2304 images enhanced the extraction accuracy and prevented overfitting. The results provide a reference for the planning, construction and maintenance of water and soil conservation measures.","PeriodicalId":54569,"journal":{"name":"Proceedings of the Institution of Civil Engineers-Water Management","volume":"73 21","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135088199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hydrological simulation and prediction is a vital aspect of the hydrological change research. Accurate prediction of hydrological factors such as stage and discharge is essential for water resources planning, reservoir dispatching and operation, shipping management and flood control. River discharge forecasting during flood season is an important issue in water resources planning and management. To improve the calibration accuracy and stability of the stage-discharge relationship model, the feasibility of integrated algorithm in the study of stage-discharge relationship is explored. A random forest algorithm based on neural network is proposed by using the framework of integrated algorithm. First, Levenberg-Marquardt (LM) algorithm is used to optimize the weight updating process of Back propagation (BP) neural network and improve the convergence speed of the model. Second, the LM-BP algorithm is used as a decision tree to build a random forest algorithm. The model is tested with the hydrological data of Hongqi Station in Dadu River in flood season. Based on the mean absolute error, mean square error and mean absolute percentage error of the performance indicators, the results for the classical model, BP neural network model, LM-BP neural network model and optimized algorithm model are evaluated. The evaluation results show that the optimized algorithm model (Mae = 3.13 m3/s MSE = 19.28 m3/s MAPE = 1.8%) is superior to other algorithm models, and the integrated algorithm model has high accuracy and good stability in flood season flow forecasting.
{"title":"Research on stage-discharge relationship model based on random forest algorithm","authors":"Yuechuan Gao, Zhu Jiang, Yuchen Wang","doi":"10.1680/jwama.23.00029","DOIUrl":"https://doi.org/10.1680/jwama.23.00029","url":null,"abstract":"Hydrological simulation and prediction is a vital aspect of the hydrological change research. Accurate prediction of hydrological factors such as stage and discharge is essential for water resources planning, reservoir dispatching and operation, shipping management and flood control. River discharge forecasting during flood season is an important issue in water resources planning and management. To improve the calibration accuracy and stability of the stage-discharge relationship model, the feasibility of integrated algorithm in the study of stage-discharge relationship is explored. A random forest algorithm based on neural network is proposed by using the framework of integrated algorithm. First, Levenberg-Marquardt (LM) algorithm is used to optimize the weight updating process of Back propagation (BP) neural network and improve the convergence speed of the model. Second, the LM-BP algorithm is used as a decision tree to build a random forest algorithm. The model is tested with the hydrological data of Hongqi Station in Dadu River in flood season. Based on the mean absolute error, mean square error and mean absolute percentage error of the performance indicators, the results for the classical model, BP neural network model, LM-BP neural network model and optimized algorithm model are evaluated. The evaluation results show that the optimized algorithm model (Mae = 3.13 m3/s MSE = 19.28 m3/s MAPE = 1.8%) is superior to other algorithm models, and the integrated algorithm model has high accuracy and good stability in flood season flow forecasting.","PeriodicalId":54569,"journal":{"name":"Proceedings of the Institution of Civil Engineers-Water Management","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135112431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mohammad Ranjbar Kabootarkhani, Soudabeh Golestani Kermani, Ammar Aldallal, Mohammad Zounemat-Kermani
River floods disrupt communication and transportation networks, damage buildings and infrastructure, destroy agricultural products and livestock, cause capital losses and endanger human life. Accurate and proper flood prediction and forecasting are major challenges in hydrology and water resources management. The aim of this study was to forecast and estimate the daily flows of three rivers in Iran using four tree-based data-mining methods, two ensemble bagging methods and the stochastic time series model Arima (auto-regressive integrated moving average). A comparison of these different methodologies is the main contribution of this work. Five statistical measures were used to evaluate the accuracy of these models based on 4 years of daily discharge flow data. The hold-out method was used to divide the data into training (70%) and testing (30%) sets. It was found that the ensemble tree-based chi-square automatic interaction detector provided the most precise forecasts. The overall results indicate that the data-mining methods of ensemble models and tree-based models improved the average accuracy of the models by 25.0% and 15.5% compared with the stochastic Arima model, respectively, indicating the superiority of their potential in capturing the non-linear behaviour of flow discharges.
{"title":"Forecasting river daily discharge using decision tree and time series methods","authors":"Mohammad Ranjbar Kabootarkhani, Soudabeh Golestani Kermani, Ammar Aldallal, Mohammad Zounemat-Kermani","doi":"10.1680/jwama.22.00079","DOIUrl":"https://doi.org/10.1680/jwama.22.00079","url":null,"abstract":"River floods disrupt communication and transportation networks, damage buildings and infrastructure, destroy agricultural products and livestock, cause capital losses and endanger human life. Accurate and proper flood prediction and forecasting are major challenges in hydrology and water resources management. The aim of this study was to forecast and estimate the daily flows of three rivers in Iran using four tree-based data-mining methods, two ensemble bagging methods and the stochastic time series model Arima (auto-regressive integrated moving average). A comparison of these different methodologies is the main contribution of this work. Five statistical measures were used to evaluate the accuracy of these models based on 4 years of daily discharge flow data. The hold-out method was used to divide the data into training (70%) and testing (30%) sets. It was found that the ensemble tree-based chi-square automatic interaction detector provided the most precise forecasts. The overall results indicate that the data-mining methods of ensemble models and tree-based models improved the average accuracy of the models by 25.0% and 15.5% compared with the stochastic Arima model, respectively, indicating the superiority of their potential in capturing the non-linear behaviour of flow discharges.","PeriodicalId":54569,"journal":{"name":"Proceedings of the Institution of Civil Engineers-Water Management","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135804731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the rapid economic growth and urbanization, water shortage and water pollution are becoming more and more serious. It is of great significance for decision makers to get the efficiency of the water system and know its development trend. Data Envelopment Analysis (DEA) stands as a robust tool for assessing efficiency. However, the DEA model lacks predictive capabilities, which can't give guidance for future development. In contrast, the Back Propagation Neural Network (BPNN) offers powerful nonlinear mapping and adaptive prediction capabilities. To compensate for the deficiencies of the DEA model, the three stage DEA-BPNN model is developed based on environmental compatibility and economic development. This model enables specific efficiency measurements, identifies system weaknesses, and anticipates future trends. Then, the proposed model is applied to the “One Belt And One Road” region, comparing its predictive performance with that of linear regression, generalized additive model, support vector machines, k-nearest neighbors, random forest, and gradient boost decision trees. As a result, among the determination of several prediction models, the BPNN model obtains more accurate prediction results.
{"title":"Evaluating the efficiency of water development-utilization-treatment system in “One Belt and One Road” regions: A three stage DEA-BPNN model","authors":"Shiyu Yan, Liming Yao, Zhineng Hu","doi":"10.1680/jwama.22.00034","DOIUrl":"https://doi.org/10.1680/jwama.22.00034","url":null,"abstract":"With the rapid economic growth and urbanization, water shortage and water pollution are becoming more and more serious. It is of great significance for decision makers to get the efficiency of the water system and know its development trend. Data Envelopment Analysis (DEA) stands as a robust tool for assessing efficiency. However, the DEA model lacks predictive capabilities, which can't give guidance for future development. In contrast, the Back Propagation Neural Network (BPNN) offers powerful nonlinear mapping and adaptive prediction capabilities. To compensate for the deficiencies of the DEA model, the three stage DEA-BPNN model is developed based on environmental compatibility and economic development. This model enables specific efficiency measurements, identifies system weaknesses, and anticipates future trends. Then, the proposed model is applied to the “One Belt And One Road” region, comparing its predictive performance with that of linear regression, generalized additive model, support vector machines, k-nearest neighbors, random forest, and gradient boost decision trees. As a result, among the determination of several prediction models, the BPNN model obtains more accurate prediction results.","PeriodicalId":54569,"journal":{"name":"Proceedings of the Institution of Civil Engineers-Water Management","volume":"243 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135352289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Accurate assessment of scour depth around bridge abutments is crucial to reasonable design of abutment structures. In this study, machine learning (ML) models are implemented, including M5′ model tree (M5′MT), multivariate adaptive regression spline (MARS), locally weighted polynomial regression (LWPR) and multigene genetic programming (MGGP) to predict scour depth around vertical-wall, 45° wing-wall and semicircular bridge abutments. Published experimental data are adopted, with four input parameters considered for the prediction of relative scour depth. The optimal input combination for each model is first determined using correlation and sensitivity analyses; results reveal that MGGP exhibits the best agreement with experimental data for vertical-wall and semicircular abutments, whereas LWPR outperforms the other models for the 45° wing-wall abutment. In addition, compared with the empirical equations and ML models employed in the literature, the accuracy of scour depth prediction is significantly improved with the ML models used in this study. Considering the comprehensive performance for all types of abutments in terms of accuracy, reliability and interpretability, MGGP is recommended as the representative of the implemented ML models with its mean absolute percentage error of 2.40% for a vertical-wall abutment, 3.95% for a 45° wing-wall abutment and 3.85% for a semicircular abutment.
{"title":"Prediction of scour depth around bridge abutments with different shapes using machine learning models","authors":"Yangyu Deng, Yakun Liu, Di Zhang, Ze Cao","doi":"10.1680/jwama.22.00087","DOIUrl":"https://doi.org/10.1680/jwama.22.00087","url":null,"abstract":"Accurate assessment of scour depth around bridge abutments is crucial to reasonable design of abutment structures. In this study, machine learning (ML) models are implemented, including M5′ model tree (M5′MT), multivariate adaptive regression spline (MARS), locally weighted polynomial regression (LWPR) and multigene genetic programming (MGGP) to predict scour depth around vertical-wall, 45° wing-wall and semicircular bridge abutments. Published experimental data are adopted, with four input parameters considered for the prediction of relative scour depth. The optimal input combination for each model is first determined using correlation and sensitivity analyses; results reveal that MGGP exhibits the best agreement with experimental data for vertical-wall and semicircular abutments, whereas LWPR outperforms the other models for the 45° wing-wall abutment. In addition, compared with the empirical equations and ML models employed in the literature, the accuracy of scour depth prediction is significantly improved with the ML models used in this study. Considering the comprehensive performance for all types of abutments in terms of accuracy, reliability and interpretability, MGGP is recommended as the representative of the implemented ML models with its mean absolute percentage error of 2.40% for a vertical-wall abutment, 3.95% for a 45° wing-wall abutment and 3.85% for a semicircular abutment.","PeriodicalId":54569,"journal":{"name":"Proceedings of the Institution of Civil Engineers-Water Management","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134948214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Excess scour developing around tandem and eccentric piers of side-by-side bridges may aggravate bridge failure. Thinking differently, this kind of pier-like structure combination may increase scour and shift sediments towards the bank which may help in self-dredging. Therefore, accurate estimation of temporal scour depth (d st ) around such piers is getting the utmost priority nowadays. However, very little work has been done in this regard. Most of the previous equations predict d st only for isolated pier. In the present study, 2-3 piers were placed eccentrically inline in addition to isolated piers to empirically derive equations for accurately predicting d st considering circular, triangular and square pier shapes. Present experimental results for isolated circular pier are validated using literature equations and also cross-validated with other literatures experimental data. Predictive equations are proposed for 2-3 piers with eccentrically inline arrangements, taking their intermediate spacing's as key variables. These equations are established based on dimensional analysis and non-linear regression. Overall analysis reveals that the estimated temporal scour depths based on the proposed integrated equation are closely within the ±80% accuracy band. The proposed equations can be used to accurately predict temporal scour for selected combinations of piers within the given experimental ranges.
{"title":"Equation for localized time-dependent scour at pier-like structures with eccentric inline arrangements","authors":"Buddhadev Nandi, Subhasish Das","doi":"10.1680/jwama.23.00006","DOIUrl":"https://doi.org/10.1680/jwama.23.00006","url":null,"abstract":"Excess scour developing around tandem and eccentric piers of side-by-side bridges may aggravate bridge failure. Thinking differently, this kind of pier-like structure combination may increase scour and shift sediments towards the bank which may help in self-dredging. Therefore, accurate estimation of temporal scour depth (d st ) around such piers is getting the utmost priority nowadays. However, very little work has been done in this regard. Most of the previous equations predict d st only for isolated pier. In the present study, 2-3 piers were placed eccentrically inline in addition to isolated piers to empirically derive equations for accurately predicting d st considering circular, triangular and square pier shapes. Present experimental results for isolated circular pier are validated using literature equations and also cross-validated with other literatures experimental data. Predictive equations are proposed for 2-3 piers with eccentrically inline arrangements, taking their intermediate spacing's as key variables. These equations are established based on dimensional analysis and non-linear regression. Overall analysis reveals that the estimated temporal scour depths based on the proposed integrated equation are closely within the ±80% accuracy band. The proposed equations can be used to accurately predict temporal scour for selected combinations of piers within the given experimental ranges.","PeriodicalId":54569,"journal":{"name":"Proceedings of the Institution of Civil Engineers-Water Management","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135060733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Scour is a significant concern for bridge design and maintenance, and scour countermeasures are often used to prevent or reduce erosion caused by scouring. The W weir is a grade control structure that serves many purposes, including scour controls at the bridge pier. A series of laboratory experimental runs were carried out by changing the size and height along with its location from the pier to the weir to optimize the structural configuration of downscaled W weir. It is observed from the experiments that the scour hole profile at the upstream of the downscaled W weir changes with the height of the weir. When the height of the weir was 1.0D (D = diameter of the pier), two small depressions of almost identical size were observed inside the main scour hole, one just in front of each upstream apex of the W weir. One cone-shaped scour hole was observed when the height of the W weir was 0.5D with its maximum depth in between the upstream apexes. The reduction of scour in front of the pier was more when the height of the weir was 1.0D. The maximum scour control achieved among all the different structural combinations of downscaled W weir was 47.66%. The maximum scour control was achieved when the downscaled W weir had a 2.0D size with the height of 1.0D placed at a 2.0D distance from the pier.
{"title":"Scour countermeasures around cylindrical pier by using downscaled W weir","authors":"R. Karthik, U. Kumar, A.K. Barbhuiya","doi":"10.1680/jwama.22.00026","DOIUrl":"https://doi.org/10.1680/jwama.22.00026","url":null,"abstract":"Scour is a significant concern for bridge design and maintenance, and scour countermeasures are often used to prevent or reduce erosion caused by scouring. The W weir is a grade control structure that serves many purposes, including scour controls at the bridge pier. A series of laboratory experimental runs were carried out by changing the size and height along with its location from the pier to the weir to optimize the structural configuration of downscaled W weir. It is observed from the experiments that the scour hole profile at the upstream of the downscaled W weir changes with the height of the weir. When the height of the weir was 1.0D (D = diameter of the pier), two small depressions of almost identical size were observed inside the main scour hole, one just in front of each upstream apex of the W weir. One cone-shaped scour hole was observed when the height of the W weir was 0.5D with its maximum depth in between the upstream apexes. The reduction of scour in front of the pier was more when the height of the weir was 1.0D. The maximum scour control achieved among all the different structural combinations of downscaled W weir was 47.66%. The maximum scour control was achieved when the downscaled W weir had a 2.0D size with the height of 1.0D placed at a 2.0D distance from the pier.","PeriodicalId":54569,"journal":{"name":"Proceedings of the Institution of Civil Engineers-Water Management","volume":"20 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90263366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：