Development of hybrid gradient boosting models for predicting the compressive strength of high-volume fly ash self-compacting concrete with silica fume

Structures, Journal Year: 2024, Volume and Issue: 66, P. 106850 - 106850

Published: July 8, 2024

Language: Английский

---

Predicting Energy Consumption of Residential Buildings Using Metaheuristic-optimized Artificial Neural Network Technique in Early Design Stage

Building and Environment, Journal Year: 2025, Volume and Issue: unknown, P. 112749 - 112749

Published: Feb. 1, 2025

Language: Английский

---

Hybrid artificial neural network models for bearing capacity evaluation of a strip footing on sand based on Bolton failure criterion

Transportation Geotechnics, Journal Year: 2024, Volume and Issue: 48, P. 101347 - 101347

Published: Aug. 23, 2024

Language: Английский

---

Optimized machine learning models for predicting the tensile strength of high-performance concrete

Journal of Structural Integrity and Maintenance, Journal Year: 2025, Volume and Issue: 10(1)

Published: Jan. 2, 2025

Language: Английский

---

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

Nondestructive Testing And Evaluation, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 33

Published: March 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.

Language: Английский

---

A machine learning approach for corrosion rate modeling in Patna water distribution network of Bihar

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 5, 2025

Corrosion can affect water taste, color, and odor, making it crucial to monitor control corrosion in the distribution network maintain quality standards. This study used machine learning approaches such as MARS, GMDH, MPMR model rate networks. An experimental setup was established running for data collection, where several test coupons were inserted into pipeline. A coupon weight loss method employed calculate rate. The selected site continuously monitored 315 days observe (WDN). physicochemical parameters regularly tested at Environmental Engineering Laboratory NIT Patna. Machine analyses, including multivariate adaptive regression splines (MARS), group of handling (GMDH), polynomial (MPMR), consider 13 features, pH, temperature, conductivity, total dissolved solids, alkalinity, hardness, calcium magnesium chloride, sulfate, nitrate, oxygen, time, input parameters, with output parameter. Energy dispersive X-ray (EDX) analysis revealed changes composition before after exposure: carbon content decreased from 4 3%, oxygen increased 20 31%, iron 21 60%, sulfur 3 2%, manganese 1%, zinc 49 1% by weight. performance developed assessed via metrics, error characteristic (REC) curves, comprehensive measurement (COM), ranking techniques. On basis models, proposed MARS is most accurate model, R2 = 0.9872 training 0.9741 testing phase, followed GMDH models. REC curve also demonstrates superiority lower area-over-the-curve (AOC) values (training: 0.010, testing: 0.015), 0.028, 0.024) 0.054, 0.074) With lowest COM value (0.172), outperforms indicating its superior predictive capability generalizability.

Language: Английский

---

Application of novel deep neural network on prediction of compressive strength of fly ash based concrete

Nondestructive Testing And Evaluation, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 31

Published: Nov. 18, 2024

Fly ash (FA)-based high-strength concrete (HSC) has attracted significant interest due to its potential substitute Portland cement, offering both environmental benefits and improved performance. However, the design of FA-HSC is challenging, as key factors such fly percentage, water content, superplasticizer dosage have a complex influence on compressive strength. This study aims develop an efficient predictive tool for mix design, using artificial intelligence (AI) models address inherent variability uncertainty in these parameters. Six AI models, including Deep Neural Network (DNN), were employed analyse relationships between variables The DNN model, particular, demonstrated superior performance compared other with high coefficient determination (R2 = 0.89), variance accounted (VAF 88.3%), root mean square error (RMSE 0.06), residual standard (RSR 0.31). These results indicate that model can provide reliable predictions strength, more alternative traditional trial-and-error methods. AI-based approach save time material costs while optimising Overall, this AI-driven contributes advancement sustainable technology by enabling precise resource-efficient designs FA-based concrete.

Language: Английский

---

Estimation of the Compressive Strength of Ultrahigh Performance Concrete using Machine Learning Models

Intelligent Systems with Applications, Journal Year: 2024, Volume and Issue: 25, P. 200471 - 200471

Published: Dec. 25, 2024

Language: Английский

---

Machine learning prediction of the unconfined compressive strength of controlled low strength material using fly ash and pond ash

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Nov. 11, 2024

The sustainable use of industrial byproducts in civil engineering is a global priority, especially reducing the environmental impact waste materials. Among these, coal ash from thermal power plants poses significant challenge due to its high production volume and potential for pollution. This study explores controlled low-strength material (CLSM), flowable fill made ash, cement, aggregates, water, admixtures, as solution large-scale utilization. CLSM suitable both structural geotechnical applications, balancing management with resource conservation. research focuses on two key properties: flowability unconfined compressive strength (UCS) at 28 days. Traditional testing methods are resource-intensive, empirical models often fail accurately predict UCS complex nonlinear relationships among variables. To address these limitations, four machine learning models-minimax probability regression (MPMR), multivariate adaptive splines (MARS), group method data handling (GMDH), functional networks (FN) were employed UCS. MARS model performed best, achieving R

Language: Английский

---

Predicting High-Strength Concrete’s Compressive Strength: A Comparative Study of Artificial Neural Networks, Adaptive Neuro-Fuzzy Inference System, and Response Surface Methodology

Materials, Journal Year: 2024, Volume and Issue: 17(18), P. 4533 - 4533

Published: Sept. 15, 2024

Machine learning and response surface methods for predicting the compressive strength of high-strength concrete have not been adequately compared. Therefore, this research aimed to predict (HSC) using different methods. To achieve purpose, neuro-fuzzy inference systems (ANFISs), artificial neural networks (ANNs), methodology (RSM) were used as ensemble Using an ANN ANFIS, output was modeled optimized a function five independent variables. The RSM designed with three input variables: cement, fine coarse aggregate. facilitate data entry into Design Expert, model divided six groups, p-values responses 1 6 0.027, 0.010, 0.003, 0.023, 0.002, 0.026. following metrics evaluate projection: R, R2, MSE ANFIS modeling; Adj. Pred. R2 modeling. Based on data, it can be concluded that (R = 0.999, 0.998, 0.417), 0.981 0.963), 0.962, 0.926, 0.655) good chance accurately (HSC). Furthermore, there is strong correlation between ANN, RSM, models experimental data. Nevertheless, network demonstrates exceptional accuracy. sensitivity analysis shows cement aggregate most significant effect (45.29% 35.87%, respectively), while superplasticizer has least (0.227%). RSME values in 0.313 0.453 during test process 0.733 0.563 training process. Thus, found both presented better results higher accuracy construction materials.

Language: Английский

---