Multisource monitoring data-driven slope stability prediction using ensemble learning techniques

Computers and Geotechnics, Год журнала: 2024, Номер 169, С. 106255 - 106255

Опубликована: Март 25, 2024

Язык: Английский

---

A state-of-the-art review on the application of lignosulfonate as a green alternative in soil stabilization

The Science of The Total Environment, Год журнала: 2024, Номер 943, С. 173500 - 173500

Опубликована: Май 28, 2024

Язык: Английский

---

Explainable machine learning for predicting mechanical properties of hot-rolled steel pipe

Journal of Iron and Steel Research International, Год журнала: 2025, Номер unknown

Опубликована: Фев. 24, 2025

Язык: Английский

---

Multi-target prediction and dynamic interpretation method for displacement of arch dam with cracks based on A-DSRSN and SHAP

Advanced Engineering Informatics, Год журнала: 2025, Номер 66, С. 103467 - 103467

Опубликована: Май 29, 2025

Язык: Английский

---

Displacement Interval Prediction Method for Arch Dam with Cracks: Integrated STL, MF-DFA and Bootstrap

Water, Год журнала: 2024, Номер 16(19), С. 2755 - 2755

Опубликована: Сен. 27, 2024

Displacement prediction models based on measured data have been widely applied in structural health monitoring. However, most neglect the particularity of displacement monitoring for arch dams with cracks, nor do they thoroughly analyze non-stationarity and uncertainty displacement. To address this issue, influencing factors were first considered, crack opening being incorporated into them, leading to construction HSCT model that accounts effects cracks. Feature selection was performed utilizing max-relevance min-redundancy (mRMR) algorithm, resulting screened subset influence factors. Next, decomposed trend, seasonal, remainder components applying seasonal-trend decomposition using loess (STL) algorithm. The multifractal characteristics these then analyzed by detrended fluctuation analysis (MF-DFA). Subsequently, predicted employing convolutional neural network-long short-term memory (CNN-LSTM) model. Finally, impact quantified intervals bootstrap method. results indicate proposed methods are effective, yielding satisfactory accuracy providing scientific basis technical support diagnosis hydraulic structures.

Язык: Английский

---

Features of the construction of canals in half-cut-half-fill

E3S Web of Conferences, Год журнала: 2024, Номер 590, С. 07006 - 07006

Опубликована: Янв. 1, 2024

This study examines the construction features of Bustan Canal in Republic Karakalpakstan, designed with a half-cut-half-fill method to optimize water supply and drainage capabilities. Given region’s high groundwater levels, canals were constructed trenches, serving dual purposes irrigation open mitigate flooding risks. The primary goal was enhance canal’s efficiency coefficient 0.85 by applying concrete lining its slopes bed, transitioning from mechanical gravity sourced Tuyamuyun Reservoir on Amu Darya River. highlights advantages using excavated soil for embankment construction, which significantly reduces transportation costs. Physical properties granulometric composition soils analyzed accredited laboratories, confirming optimal compaction densities between 1.72 g/cm³ 1.77 at moisture contents ranging 17% 20%. findings underscore importance this canal system supporting agriculture over an area 100,000 hectares, enhancing management practices Southern Karakalpakstan.

Язык: Английский

---

Estimating flexural strength of precast deck joints using Monte Carlo Model Averaging of non-fine-tuned machine learning models

Frontiers of Structural and Civil Engineering, Год журнала: 2024, Номер unknown

Опубликована: Дек. 3, 2024

Язык: Английский

---