Predicting Max Scour Depths near Two-Pier Groups Using Ensemble Machine-Learning Models and Visualizing Feature Importance with Partial Dependence Plots and SHAP

Journal of Computing in Civil Engineering, Год журнала: 2025, Номер 39(2)

Опубликована: Янв. 11, 2025

Язык: Английский

---

Dynamic damage functions for scour protection at monopile foundations: Application of ensemble machine learning models

Ocean Engineering, Год журнала: 2025, Номер 323, С. 120590 - 120590

Опубликована: Фев. 8, 2025

Язык: Английский

---

The influence of collar parameters on local scour mechanism around the circular pier at the bend

Applied Water Science, Год журнала: 2024, Номер 14(9)

Опубликована: Авг. 12, 2024

Analysis of bridge failures due to scouring has been extensively studied by different researchers in recent years and as a result various methods controlling local scour cavity have given. Since most the research this field done on straight paths also complexity flow pattern bends, studying around piers located bends become necessity. Therefore, one main objectives study is investigate circular which are protected collars at river bends. The performance collar significantly depends its level pier, study. results showed that optimal structure, positions 60°, 90° 120° 0.2 pier width under bed with 3 mm thickness (0.06 width) approximately 68, 63 70% maximum depth was reduced compared collarless respectively. By analyzing research, it observed optimum range bend angles initial up 0.4 times bottom incipient bed. Moreover, getting closer plate placement toward elevation enhances collar's function decreasing scouring.

Язык: Английский

---

Analysing Bridge Pier Scour Depth Using Machine Learning: The Role of Slot Geometry

Опубликована: Янв. 1, 2025

Язык: Английский

---

Micromechanical analysis of local scour behaviors around circular piles in granular soil under steady flows with SPH-DEM

Ocean Engineering, Год журнала: 2025, Номер 328, С. 121061 - 121061

Опубликована: Апрель 4, 2025

Язык: Английский

---

Forecasting of time-dependent scour depth based on bagging and boosting machine learning approaches

Journal of Hydroinformatics, Год журнала: 2024, Номер 26(8), С. 1906 - 1928

Опубликована: Июль 17, 2024

ABSTRACT Forecasting the time-dependent scour depth (dst) is very important for protection of bridge structures. Since result a complicated interaction between structure, sediment, and flow velocity, empirical equations cannot guarantee an advanced accuracy, although they would preserve merit being straightforward physically inspiring. In this article, we propose three ensemble machine learning methods to forecast at piers: extreme gradient boosting regressor (XGBR), random forest (RFR), extra trees (ETR). These models predict given time, dst, based on following main variables: median grain size, d50, sediment gradation, σg, approach U, y, pier diameter Dp, time t. A total 555 data points from different studies have been taken research work. The results indicate that all proposed precisely estimate depth. However, XGBR method performs better than other with R = 0.97, NSE 0.93, AI 0.98, CRMSE 0.09 testing stage. Sensitivity analysis exhibits highly influenced by scale.

Язык: Английский

---

Local scour at group of bridge piers founded in gravel bed in staggered arrangement

Results in Engineering, Год журнала: 2024, Номер 23, С. 102608 - 102608

Опубликована: Июль 24, 2024

Local scour around bridge piers is the common cause of undermining foundation. Many researchers have studied local pier in finer sediment bed. The literature survey reveals a limited information available on group with and without collar founded gravel Keeping this view, an attempt made to examine experimentally efficacy three placed staggered triangular arrangement bed 3 mm effective size. data temporal variation depth, hole characteristics, areal extent were collected. collected experimental results infer very prominent engineers. obtained equilibrium depth help knowing up which protection can be provided against scour. It found that at longitudinal spacing (Z) equals 8.45 times diameter (b), nose was maximum than other spacing. At Z/b > 8.45, downstream decreases increasing reaches minimum = 40. < 10, upstream because decreasing effect reinforcement disappears 10. present study became free mutual interference centre-to-centre (c/c) 60 diameter. worth mentioning for collar, vanished c/c 20 show additional shielding makes from lesser collar. This concludes investigation useful when space between existing newly proposed bridges.

Язык: Английский

---

Enhancing accurate prediction of soil permeability coefficients using data-driven approaches for soil and water conservation

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2024, Номер 8(1)

Опубликована: Дек. 3, 2024

Язык: Английский

---