Interpretable Predictive Modelling of Basalt Fiber Reinforced Concrete Splitting Tensile Strength Using Ensemble Machine Learning Methods and SHAP Approach

Materials, Год журнала: 2023, Номер 16(13), С. 4578 - 4578

Опубликована: Июнь 25, 2023

Basalt fibers are a type of reinforcing fiber that can be added to concrete improve its strength, durability, resistance cracking, and overall performance. The addition basalt with high tensile strength has particularly favorable impact on the splitting concrete. current study presents data set experimental results tests curated from literature. Some best-performing ensemble learning techniques such as Extreme Gradient Boosting (XGBoost), Light Machine (LightGBM), Random Forest, Categorical (CatBoost) have been applied prediction reinforced fibers. State-of-the-art performance metrics root mean squared error, absolute error coefficient determination used for measuring accuracy prediction. each input feature model visualized using Shapley Additive Explanations (SHAP) algorithm individual conditional expectation (ICE) plots. A greater than 0.9 could achieved by XGBoost in strength.

Язык: Английский

---

Machine-Learning Methods for Estimating Performance of Structural Concrete Members Reinforced with Fiber-Reinforced Polymers

Archives of Computational Methods in Engineering, Год журнала: 2024, Номер unknown

Опубликована: Июнь 14, 2024

Abstract In recent years, fiber-reinforced polymers (FRP) in reinforced concrete (RC) members have gained significant attention due to their exceptional properties, including lightweight construction, high specific strength, and stiffness. These attributes found application structures, infrastructures, wind power equipment, various advanced civil products. However, the production process extensive testing required for assessing suitability incur time cost. The emergence of Industry 4.0 has presented opportunities address these drawbacks by leveraging machine learning (ML) methods. ML techniques recently been used forecast properties assess importance parameters efficient structural design broad applications. Given wide range applications, this work aims perform a comprehensive analysis algorithms predicting mechanical FRPs. performance evaluation models was discussed, detailed pros cons provided. Finally, limitations that currently exist were pinpointed, suggestions given improve prediction precision suitable evaluating FRP components.

Язык: Английский

---

Predicting the shear strength of rectangular RC beams strengthened with externally-bonded FRP composites using constrained monotonic neural networks

Engineering Structures, Год журнала: 2024, Номер 313, С. 118192 - 118192

Опубликована: Май 30, 2024

Язык: Английский

---

Modelling nonlinear shear creep behaviour of a structural adhesive using deep neural networks (DNN)

Construction and Building Materials, Год журнала: 2024, Номер 414, С. 135083 - 135083

Опубликована: Янв. 20, 2024

Язык: Английский

---

Predictive models in machine learning for strength and life cycle assessment of concrete structures

Automation in Construction, Год журнала: 2024, Номер 162, С. 105412 - 105412

Опубликована: Апрель 3, 2024

Язык: Английский

---

Improved forecasting of the compressive strength of ultra‐high‐performance concrete (UHPC) via the CatBoost model optimized with different algorithms

Structural Concrete, Год журнала: 2024, Номер unknown

Опубликована: Май 19, 2024

Abstract This paper focuses on the applicability of CatBoost models constructed using various optimization techniques for improved forecasting compressive strength ultra‐high‐performance concrete (UHPC). Phasor particle swarm (PPSO), dwarf mongoose (DMO), and atom search (ASO), which have been very popular recently, are preferred as algorithms. A comprehensive reliable data set is used to develop models, include 785 test results with 15 input features. The performance (PPSO‐CatBoost, DMO‐CatBoost, ASO‐CatBoost) optimized different algorithms thoroughly assessed by means statistical metrics error analysis determine model best capability, this compared obtained from previous studies. In addition, Shapley additive exPlanations (SHAP) ensure interpretability overcome “black box” problem machine learning (ML) models. demonstrate that all outstandingly forecast UHPC. Among these DMO‐CatBoost stands out other in metrics, such high coefficient determination ( R 2 ) values, low root mean squared (RMSE), absolute percentage (MAPE), (MAE) along a smaller ratio. words, RMSE, , MAPE, MAE values training 3.67, 0.993, 0.019, 2.35, respectively, whereas those 6.15, 0.978, 0.038, 4.51. Additionally, ranking optimize hyperparameters follows: DMO > PPSO ASO. On hand, SHAP showed age, fiber dosage, cement dosage significantly influence These findings can guide structural engineers design UHPC, thus assisting them developing strategies improve properties material. Finally, based developed work, graphical user interface has easily UHPC practical applications without additional tools or software.

Язык: Английский

---

Data-driven estimates of the strength and failure modes of CFRP-steel bonded joints by implementing the CTGAN method

Engineering Fracture Mechanics, Год журнала: 2024, Номер 299, С. 109962 - 109962

Опубликована: Фев. 20, 2024

Язык: Английский

---

Explainable machine learning: Compressive strength prediction of FRP-confined concrete column

Materials Today Communications, Год журнала: 2024, Номер 39, С. 108883 - 108883

Опубликована: Апрель 12, 2024

Язык: Английский

---

Boosting-Based Machine Learning Applications in Polymer Science: A Review

Polymers, Год журнала: 2025, Номер 17(4), С. 499 - 499

Опубликована: Фев. 14, 2025

The increasing complexity of polymer systems in both experimental and computational studies has led to an expanding interest machine learning (ML) methods aid data analysis, material design, predictive modeling. Among the various ML approaches, boosting methods, including AdaBoost, Gradient Boosting, XGBoost, CatBoost LightGBM, have emerged as powerful tools for tackling high-dimensional complex problems science. This paper provides overview applications science, highlighting their contributions areas such structure-property relationships, synthesis, performance prediction, characterization. By examining recent case on techniques this review aims highlight potential advancing characterization, optimization materials.

Язык: Английский

---

Shear performance prediction of RC beams shear-strengthened with FRP sheet: A machine learning driven design-oriented method

Engineering Structures, Год журнала: 2025, Номер 334, С. 120240 - 120240

Опубликована: Апрель 7, 2025

Язык: Английский

---