Stacked-based machine learning to predict the uniaxial compressive strength of concrete materials

Computers & Structures, Год журнала: 2025, Номер 308, С. 107644 - 107644

Опубликована: Янв. 6, 2025

Язык: Английский

---

Stacked-based hybrid gradient boosting models for estimating seepage from lined canals

Journal of Water Process Engineering, Год журнала: 2025, Номер 70, С. 106913 - 106913

Опубликована: Янв. 9, 2025

Язык: Английский

---

Modeling hydraulic jump roller length on rough beds: a comparative study of ANN and GEP models

Deleted Journal, Год журнала: 2025, Номер unknown

Опубликована: Янв. 8, 2025

Abstract Hydraulic jumps (HJs) play a vital role in energy dissipation hydraulic systems and are critical for the effective design of water management structures. This study employed Artificial Neural Network (ANN) Gene Expression Programming (GEP) models to predict roller length ratio ( L * ) HJs over rough beds. The analysis utilized dataset 367 experimental observations with 70–30 training testing split. Comprehensive data descriptions were conducted, ensuring detailed understanding inputs, including upstream Froude number F ), initial sequent HJ depth H = h 2 / 1 channel bed roughness K k s ). Descriptive statistics revealed moderate variability mostly symmetric distributions, making suitable predictive modeling. A sensitivity was conducted confirmed that had highest influence on , followed by . ANN model achieved R 0.937 0.935, RMSEs 1.737 1.719, respectively. GEP demonstrated 0.941 0.930, 1.682 1.780. Both displayed reliable capabilities, minimal bias consistent performance unseen data, supported comprehensive error distribution uncertainty evaluations. Moreover, high level agreement prior research results, highlighting importance thorough characterization validation. Thus, have been recognized as techniques predicting jump length. Graphical

Язык: Английский

---

Enhanced energy dissipation prediction in modified semi-cylindrical weirs using machine learning techniques

Modeling Earth Systems and Environment, Год журнала: 2025, Номер 11(2)

Опубликована: Фев. 13, 2025

Язык: Английский

---

Advanced predictive machine and deep learning models for round-ended CFST column

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 20, 2025

Confined columns, such as round-ended concrete-filled steel tubular (CFST) are integral to modern infrastructure due their high load-bearing capacity and structural efficiency. The primary objective of this study is develop accurate, data-driven approaches for predicting the axial load-carrying (Pcc​) these columns benchmark performance against existing analytical solutions. Using an extensive dataset 200 CFST stub column tests, research evaluates three machine learning (ML) models - LightGBM, XGBoost, CatBoost deep (DL) Deep Neural Network (DNN), Convolutional (CNN), Long Short-Term Memory (LSTM). Key input features include concrete strength, length, cross-sectional dimensions, tube thickness, yield which were analysed uncover underlying relationships. results indicate that delivers highest predictive accuracy, achieving RMSE 396.50 kN R2 0.932, surpassing XGBoost (RMSE: 449.57 kN, R2: 0.906) LightGBM 0.916). less effective, with DNN attaining 496.19 0.958, while LSTM underperformed substantially 2010.46 0.891). SHapley Additive exPlanations (SHAP) identified width most critical feature, contributing positively capacity, length a significant negative influencer. A user-friendly, Python-based interface was also developed, enabling real-time predictions practical engineering applications. Comparison 10 demonstrates traditional methods, though deterministic, struggle capture nonlinear interactions inherent in thus yielding lower accuracy higher variability. In contrast, presented here offer robust, adaptable, interpretable solutions, underscoring potential transform design analysis practices ultimately fostering safer more efficient systems.

Язык: Английский

---

Soft computing approaches for forecasting discharge over symmetrical piano key weirs

AI in Civil Engineering, Год журнала: 2025, Номер 4(1)

Опубликована: Март 3, 2025

Abstract Piano Key Weir (PKW) is an advanced hydraulic structure that enhances water discharge efficiency and flood control through its innovative design, which allows for higher flow rates at lower upstream levels. Accurate prediction crucial PKW performance within various management systems. This study assesses the efficacy of Artificial-Neural-Network (ANN) Gene-Expression-Programming (GEP) models in improving symmetrical PKWs. A comprehensive dataset comprising 476 experimental records from previously published studies was utilized, considering a range geometric fluid parameters (PKW key widths, height, head). In training stage, ANN model demonstrated superior determination coefficient (R 2 ) 0.9997 alongside Mean Absolute Percentage Error (MAPE) 0.74%, whereas GEP yielded R 0.9971 MAPE 2.36%. subsequent testing both displayed high degree accuracy comparison to data, attaining value 0.9376. Furthermore, SHapley-Additive-exPlanations Partial-Dependence-Plot analyses were incorporated, revealing head exerted greatest influence on prediction, followed by height width. Therefore, these are recommended as reliable, robust, efficient tools forecasting Additionally, mathematical expressions associated script codes developed this made accessible, thus providing engineers researchers with means perform rapid accurate predictions.

Язык: Английский

---

Prediction of ultimate strength and strain in FRP wrapped oval shaped concrete columns using machine learning

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 28, 2025

The accurate prediction of the strength enhancement ratio ([Formula: see text]) and strain (εcc/εco) in FRP-wrapped elliptical concrete columns is crucial for optimizing structural performance. This study employs machine learning (ML) techniques to enhance accuracy reliability. A dataset 181 samples, derived from experimental studies finite element modeling, was utilized, with a 70:30 train-test split (127 training samples 54 testing samples). Four ML models: Decision Tree (DT), Adaptive Boosting (ADB), Stochastic Gradient (SGB), Extreme (XGB) were trained optimized using Bayesian Optimization refine their hyperparameters improve performance.Results demonstrate that SGB achieved best performance predicting [Formula: text], an R2 0.850, lowest RMSE (0.190), highest generalization capability, making it most reliable model predictions. For (εcc/εco), XGB outperformed other models, achieving 0.779 (2.162), indicating better balance between accuracy, generalization, minimal overfitting. DT ADB exhibited lower predictive performance, higher residual errors capacity. Furthermore, Shapley Additive exPlanations analysis identified FRP thickness-elastic modulus product (tf × Ef) compressive as influential features impacting both ratios. To facilitate real-world applications, interactive graphical user interface developed, enabling engineers input ten parameters obtain real-time

Язык: Английский

---

Metaheuristic-driven CatBoost model for accurate seepage loss prediction in lined canals

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2025, Номер 8(5)

Опубликована: Март 25, 2025

Язык: Английский

---

An interpretable deep learning model for the accurate prediction of mean fragmentation size in blasting operations

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 3, 2025

Язык: Английский

---

Predicting axial load capacity in elliptical fiber reinforced polymer concrete steel double skin columns using machine learning

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 15, 2025

The current study investigates the application of artificial intelligence (AI) techniques, including machine learning (ML) and deep (DL), in predicting ultimate load-carrying capacity strain ofboth hollow solid hybrid elliptical fiber-reinforced polymer (FRP)-concrete-steel double-skin tubular columns (DSTCs) under axial loading. Implemented AI techniques include five ML models - Gene Expression Programming (GEP), Artificial Neural Network (ANN), Random Forest (RF), Adaptive Boosting (ADB), eXtreme Gradient (XGBoost) one DL model Deep (DNN).Due to scarcity experimental data on DSTCs, an accurate finite element (FE) was developed provide additional numerical insights. reliability proposed nonlinear FE validated against existing results. then employed a parametric generate 112 points.The examined impact concrete strength, cross-sectional size inner steel tube, FRP thickness both DSTCs.The effectiveness assessed by comparing models' predictions with results.Among models, XGBoost RF achieved best performance training testing respect determination coefficient (R2), Root Mean Square Error (RMSE), Absolute (MAE) values. provided insights into contributions individual features using SHapley Additive exPlanations (SHAP) approach. results from SHAP, based prediction model, indicate that area core has most significant effect followed unconfined strength total multiplied its elastic modulus. Additionally, user interface platform streamline practical DSTCs.

Язык: Английский

---