Optimizing high-strength concrete compressive strength with explainable machine learning

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2025, Номер 8(3)

Опубликована: Фев. 3, 2025

Язык: Английский

---

Optimizing machine learning techniques and SHapley Additive exPlanations (SHAP) analysis for the compressive property of self-compacting concrete

Materials Today Communications, Год журнала: 2024, Номер 39, С. 108804 - 108804

Опубликована: Апрель 1, 2024

Язык: Английский

---

Analyzing the efficacy of waste marble and glass powder for the compressive strength of self-compacting concrete using machine learning strategies

REVIEWS ON ADVANCED MATERIALS SCIENCE, Год журнала: 2024, Номер 63(1)

Опубликована: Янв. 1, 2024

Abstract Self-compacting concrete (SCC) is well-known for its capacity to flow under own weight, which eliminates the need mechanical vibration and provides benefits such as less labor faster construction time. Nevertheless, increased cement content of SCC results in an increase both costs carbon emissions. These challenges are resolved this research by utilizing waste marble glass powder substitutes. The main objective study create machine learning models that can predict compressive strength (CS) using gene expression programming (GEP) multi-expression (MEP) produce mathematical equations capture correlations between variables. models’ performance assessed statistical metrics, hyperparameter optimization conducted on experimental dataset consisting eight independent indicate MEP model outperforms GEP model, with R 2 value 0.94 compared 0.90. Moreover, sensitivity SHapley Additive exPlanations analysis revealed most significant factor influencing CS curing time, followed slump quantity. A sustainable approach design presented study, improves efficacy minimizes testing.

Язык: Английский

---

Integrating Experimental Analysis and Gradient Boosting for the Durability Assessment of Lime-Based Mortar in Acidic Environment

Buildings, Год журнала: 2025, Номер 15(3), С. 408 - 408

Опубликована: Янв. 28, 2025

This paper presents a comprehensive study of the mechanical properties lime-based mortar in an acidic environment, employing both experimental analysis and machine learning to model techniques. Despite extensive use construction, particularly for strengthening structures as externally bonded materials, its behavior under conditions remains poorly understood literature. aims address this gap by investigating performance prolonged exposure environments, laying groundwork further research critical area. In phase, commercial hydraulic was subjected varying environmental conditions, including solution immersion with pH 3.0, distilled water immersion, dry storage. Subsequently, specimens were tested flexure following durations 1000, 3000, 5000 h. modeling extreme gradient boosting (XGBoost) algorithm deployed predict h exposure. Using data, models trained capture complex relationships between stress-displacement curve (as output) various properties, density, corrosion, moisture, duration input features). The predictive demonstrated remarkable accuracy generalization (using 4-fold cross-validation approach) capabilities (R2 = 0.984 RMSE 0.116, testing dataset), offering reliable tool estimating mortar’s over extended periods environment. comparative that samples exposed environment reached peak values at 3000 exposure, followed decrease contrast, exhibited earlier onset strength increase, indicating different material responses conditions.

Язык: Английский

---

Modeling the impact of SiO2, Al2O3, CaO, and Fe2O3 on the compressive strength of cement modified with nano-silica and silica fume

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2025, Номер 8(2)

Опубликована: Янв. 31, 2025

Язык: Английский

---

Analyzing the compressive strength, eco-strength, and cost–strength ratio of agro-waste-derived concrete using advanced machine learning methods

REVIEWS ON ADVANCED MATERIALS SCIENCE, Год журнала: 2025, Номер 64(1)

Опубликована: Янв. 1, 2025

Abstract Agro-waste like eggshell powder (ESP) and date palm ash (DPA) are used as supplementary cementitious materials (SCMs) in concrete because of their pozzolanic attributes well environmental cost benefits. In addition, performing lab tests to optimize mixed proportions with different SCMs takes considerable time effort. Therefore, the creation estimation models for such purposes is vital. This study aimed create interpretable prediction compressive strength (CS), eco-strength (ECR), cost–strength ratio (CSR) DPA–ESP concrete. Gene expression programming (GEP) was employed model generation via hyperparameter optimization method. Also, importance input features determined SHapley Additive exPlanations (SHAP) analysis. The GEP accurately matched experimental results CS, ECR, CSR These can be future predictions, reducing need additional saving effort, time, costs. model’s accuracy confirmed by an R 2 value 0.94 high values 0.91 ECR 0.92 CSR, lower statistical checks. SHAP analysis suggested that test age most critical factor all outcomes.

Язык: Английский

---

Hybrid Machine Learning Model Based on GWO and PSO Optimization for Prediction of Oilwell Cement Compressive Strength under Acidic Corrosion

SPE Journal, Год журнала: 2024, Номер 29(09), С. 4684 - 4695

Опубликована: Июнь 27, 2024

Summary It is difficult to solve the problem that cement sheath of oil and gas wells corroded by acid gas, change in compressive strength (CS) after corrosion key affecting sealing capacity sheath. In this study, we used four traditional machine learning (ML) algorithms—artificial neural network (ANN), support vector regression (SVR), extreme (ELM), random forest (RF)—to establish a model for predicting CS stone. We Shapley additive exPlanations (SHAP) explain influence process input characteristics on output results, explored mechanism various factors CS. The results show SVR RF are two models with better prediction ability. Particle swarm optimization (PSO) gray wolf (GWO) algorithms optimize models. After optimization, accuracy determination coefficient (R2) was higher than 0.90, R2 optimal PSO-RF 0.9275, root mean square error (RMSE) 2.6516.

Язык: Английский

---

Experimenting the effectiveness of waste materials in improving the compressive strength of plastic-based mortar

Case Studies in Construction Materials, Год журнала: 2024, Номер 21, С. e03543 - e03543

Опубликована: Июль 17, 2024

The reduction in compressive strength (CS) of cementitious composites incorporating waste plastic is the main concern limiting its applicability building sector. Using industrial wastes as cement substitutes to enhance CS mortar a sustainable approach. This study used fine powdered materials such silica fume (SF), marble powder (MP), and glass (GP) plastic-based for their effectiveness enhancing CS. Plastic specimens were cast using 5–25 % contents sand replacement by mass, 28-day was recorded reference. SF, GP, MP utilized mixtures separately proportions %, with 5 increment, substituting mass. These powders also combinations two (SF+GP, SF+MP, GP+MP) three (SF+GP+MP) mixtures. Moreover, prediction models built experimental database mortar. Gradient boosting bagging ensemble machine learning (ML) techniques chosen model development. decrease limited It determined that most effective substitution levels mortar, according enhancement, 15, 10, 15 wt.% cement, respectively. ML closely matched results, terms R2 error evaluations, outputs more accurate than gradient boosting. had 0.89 0.94, respectively, average absolute errors 0.87 0.65 MPa.

Язык: Английский

---

Evaluating the strength loss and the effectiveness of glass and eggshell powder for cement mortar under acidic conditions

REVIEWS ON ADVANCED MATERIALS SCIENCE, Год журнала: 2024, Номер 63(1)

Опубликована: Янв. 1, 2024

Abstract The cementitious composite’s resistance to the introduction of harmful ions is primary criterion that used evaluate its durability. efficacy glass and eggshell powder in cement mortar exposed 5% sulfuric acid solutions was investigated this study using artificial intelligence (AI)-aided approaches. Prediction models based on AI were built experimental datasets with multi-expression programming (MEP) gene expression (GEP) forecast percentage decrease compressive strength (CS) after exposure. Furthermore, SHapley Additive exPlanations (SHAP) analysis examine significance prospective constituents. results experiments substantiated these models. High coefficient determination ( R 2 ) values (MEP: 0.950 GEP: 0.913) indicated statistical significance, meaning test anticipated outcomes consistent each other MEP GEP models, respectively. According SHAP analysis, amount (GP) had most significant link CS loss deterioration, showing a positive negative correlation, In order optimize efficiency cost-effectiveness, created possess capability theoretically assess decline GP-modified across various input parameter values.

Язык: Английский

---

Aprendizado de máquina para predição de resistência à compressão de argamassas com e sem resíduo de construção

Matéria (Rio de Janeiro), Год журнала: 2024, Номер 29(4)

Опубликована: Янв. 1, 2024

RESUMO O presente trabalho objetivou avaliar o desempenho de algoritmos aprendizado máquinas na predição da resistência à compressão argamassas. A base dados foi criada através uma busca bibliográfica mais 50 referências que foram catalogadas para conter dosagens argamassa com ou sem adição resíduos construção e demolição (RCD). conjunto avaliado passou por um pré-processamento integração dos resíduo demolição, normalização. Como normalização optou-se pelo uso técnica z-score. Em seguida, os Aprendizado Máquina (AM): regressões linear polinomial, árvores decisão, ensembles redes neurais utilizados a compressão. separado em 80% treino validação 20% teste. cruzada empregada do tipo k-fold 10 divisões no subconjunto treino. Avaliando modelos algoritmo ensemble Gradient Boosting apresentou melhor quando comparado aos demais, atingindo valor superior 90% coeficiente determinação. Por fim, conclui-se AM é ferramenta prática importante Além disso, modelo inteligência artificial prototipado comunidade científica versão web disponível framework Streamlit linguagem Python.

---