Comparative analysis of sloshing effects on elevated water tanks’ dynamic response using ANN and MARS

Discover Materials, Год журнала: 2025, Номер 5(1)

Опубликована: Янв. 14, 2025

Important infrastructure elements like elevated water tanks are vulnerable to fluid sloshing brought on by earthquakes, which can seriously harm the structure. In order precisely capture fluid–structure interaction, this work uses a 3D finite element model based Coupled Eulerian–Lagrangian (CEL) approach investigate dynamic response of raised under seismic excitation. Seismic ground motions were applied model, and displacements, accelerations, stresses that resulted examined. The results highlight how significantly affects tank because waves increase structural deformations imposing large hydrodynamic pressures walls. tank's performance as tuned liquid damper (TLD) was also evaluated in study. Multivariate Adaptive Regression Splines (MARS) Artificial Neural Network (ANN) models created trained further examine forecast response. According statistical analysis Taylor diagram evaluation, ANN outperformed MARS forecasting displacement numerical simulations precise made possible use ABAQUS software, potent tool. study's conclusions be used improve construction reduce risk. impact different geometries, characteristics, may investigated future studies. This research innovatively employs software simulate stabilizing effect steel structures during earthquakes. By optimizing levels 60% capacity, study explores potential damping mechanism mitigate vibrations. comparison empty tanks, leads better throughout velocity, acceleration, responses, speeds up stabilization lowers loads. demonstrates well adjusted dampers (TLDs) vibrations tanks.

Язык: Английский

---

Predicting the compressive strength of polymer-infused bricks: A machine learning approach with SHAP interpretability

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

Опубликована: Март 8, 2025

Abstract The rapid increase in global waste production, particularly Polymer wastes, poses significant environmental challenges because of its nonbiodegradable nature and harmful effects on both vegetation aquatic life. To address this issue, innovative construction approaches have emerged, such as repurposing Polymers into building materials. This study explores the development eco-friendly bricks incorporating cement, fly ash, M sand, polypropylene (PP) fibers derived from Polymers. primary innovation lies leveraging advanced machine learning techniques, namely, artificial neural networks (ANN), support vector machines (SVM), Random Forest AdaBoost to predict compressive strength these Polymer-infused bricks. polymer bricks’ was recorded output parameter, with PP waste, age serving input parameters. Machine models often function black boxes, thereby providing limited interpretability; however, our approach addresses limitation by employing SHapley Additive exPlanations (SHAP) interpretation method. enables us explain influence different variables predicted outcomes, thus making more transparent explainable. performance each model evaluated rigorously using various metrics, including Taylor diagrams accuracy matrices. Among compared models, ANN RF demonstrated superior which is close agreement experimental results. achieves R 2 values 0.99674 0.99576 training testing respectively, whereas RMSE value 0.0151 (Training) 0.01915 (Testing). underscores reliability estimating strength. Age, ash were found be most important variable predicting determined through SHAP analysis. not only highlights potential enhance predictive for sustainable materials demonstrates a novel application improve interpretability context repurposing.

Язык: Английский

---

Hybrid machine learning models for predicting compressive strength of self-compacting concrete: an integration of ANFIS and Metaheuristic algorithm

Nondestructive Testing And Evaluation, Год журнала: 2025, Номер unknown, С. 1 - 33

Опубликована: Март 25, 2025

Self-compacting concrete (SCC) has become increasingly popular due to its superior workability, segregation resistance, and compressive strength. As the traditional methods for strength prediction are costly time-intensive, this study explores machine learning (ML) techniques as efficient alternatives SCC prediction. Three state-of-the-art hybrid Adaptive Neuro-Fuzzy Inference System (ANFIS) models, optimised using Firefly Algorithm (FA), Particle Swarm Optimization (PSO) Genetic (GA). For purpose, a robust dataset of 366 instances 7 input parameters is taken from literature. After data analysis pre-processing, hyperparameters models tuned best-fit model tested on unforeseen data. ANFIS-FF stands out best-performing (RTR2 = 0.945 RTS2 0.9395) in both training testing phases, closely followed by ANFIS-GA. All outperform ANFIS model, outlining significance hybridisation, however, ANFIS-PSO lags behind other two models. The highlights importance integrating with metaheuristic algorithms tackling complex engineering problems like design optimal mix design, minimising material waste ensuring cost-effectiveness. It serves benchmark future research comparing hybridisation starting point ANFIS.

Язык: Английский

---

Mean Limiting Pressure Factors Determination in Contiguous Pile Walls using RAFELA and Nonlinear Regression Models in Spatially Random Soil

Results in Engineering, Год журнала: 2025, Номер unknown, С. 104436 - 104436

Опубликована: Фев. 1, 2025

Язык: Английский

---

Assessment of mechanical properties of rock using deep learning approaches

Measurement, Год журнала: 2025, Номер unknown, С. 117180 - 117180

Опубликована: Март 1, 2025

Язык: Английский

---

Assessment of compressive strength of ultra‐high‐performance concrete using advanced machine learning models

Structural Concrete, Год журнала: 2025, Номер unknown

Опубликована: Апрель 6, 2025

Abstract In recent decades, concrete technology has seen a paradigm shift with the development of ultra‐high‐performance (UHPC). These materials surpass traditional in compressive strength (CS), tensile strength, durability, and ductility, making them ideal for various structural applications. This study investigates application four machine learning models: XGBoost (XGB), Gradient Boosting Machine (GBM), Adaptive (ADA), CatBoost to predict CS UHPC. The dataset comprises 810 observations 13 input features, including like cement, silica fume, aggregates. Pearson correlation analysis SHapley Additive exPlanations were utilized determine significance each feature on CS. Results showed strong positive correlations fiber, superplasticizer, age, while negative observed limestone powder, fly ash, nano‐silica, aggregate. XGB demonstrated highest predictive accuracy R 2 values 0.977 (training) 0.907 (testing), followed closely by GBM. ADA exhibited weakest performance. Also, similar results obtained from visual interpretation using Taylor diagram matrix. Overall, GBM emerged as most reliable models predicting UHPC CS, having slight edge generalization capabilities during testing.

Язык: Английский

---

Evaluating the feasibility of using iron powder as a partial replacement for fine aggregates in concrete: An AI-based modeling approach

Construction and Building Materials, Год журнала: 2025, Номер 474, С. 140890 - 140890

Опубликована: Апрель 9, 2025

Язык: Английский

---

Role of Artificial Intelligence (AI) Techniques in Tunnel Engineering—A Scientific Review

Indian geotechnical journal, Год журнала: 2025, Номер unknown

Опубликована: Апрель 24, 2025

Язык: Английский

---