Hybrid data-driven approaches to predicting the compressive strength of ultra-high-performance concrete using SHAP and PDP analyses

Case Studies in Construction Materials, Год журнала: 2024, Номер 20, С. e02991 - e02991

Опубликована: Фев. 19, 2024

Ultra-high-performance concrete (UHPC) is a cutting-edge and advanced constructions material known for its exceptional mechanical properties durability. Recently, machine learning (ML) methods play pivotal role in predicting the compressive strength (CS) of UHPC evaluating dominant input parameters suitable mix design. This research, three hybrid models were utilized: Random Forest (RF), AdaBoost (AB), Gradient Boosting (GB) algorithms with particle swarm optimization (PSO), namely AB-PSO, RF-PSO, GB-PSO, to predict perform SHAP (Shapley additive explanation) analysis. To build predictive ML models, dataset 810 experimental data points was collected from published literature. Additionally, interaction plots generated visualize impact each feature on specific prediction made by model. Our results indicate that better than traditional GB-PSO model showed high accuracy among models. The had higher precision compared other two It achieved R2 values 0.9913 during training stage 0.9804 testing CS. analysis revealed age, fiber, cement, silica fume, superplasticizer significant influence strength, while comparatively lower. PDP (Partial Dependence Plots) amount individually variables can be calculated simply designed These findings are valuable construction applications offer essential insights design engineers builders, aiding their understanding significance component UHPC.

Язык: Английский

---

Predicting Penetration Depth in Ultra-High-Performance Concrete Targets under Ballistic Impact: An Interpretable Machine Learning Approach Augmented by Deep Generative Adversarial Network

Results in Engineering, Год журнала: 2025, Номер unknown, С. 103909 - 103909

Опубликована: Янв. 1, 2025

Язык: Английский

---

Sustainable mix design and carbon emission analysis of recycled aggregate concrete based on machine learning and big data methods

Journal of Cleaner Production, Год журнала: 2025, Номер 489, С. 144734 - 144734

Опубликована: Янв. 1, 2025

Язык: Английский

---

Predicting the compressive strength of engineered geopolymer composites using automated machine learning

Construction and Building Materials, Год журнала: 2024, Номер 442, С. 137509 - 137509

Опубликована: Июль 31, 2024

Язык: Английский

---

Prediction and comparison of burning rate of n-heptane pool fire in open space based on BPNN and XGBoost

Process Safety and Environmental Protection, Год журнала: 2024, Номер 189, С. 89 - 101

Опубликована: Июнь 18, 2024

Язык: Английский

---

Explainable Ensemble Learning and Multilayer Perceptron Modeling for Compressive Strength Prediction of Ultra-High-Performance Concrete

Biomimetics, Год журнала: 2024, Номер 9(9), С. 544 - 544

Опубликована: Сен. 9, 2024

The performance of ultra-high-performance concrete (UHPC) allows for the design and creation thinner elements with superior overall durability. compressive strength UHPC is a value that can be reached after certain period time through series tests cures. However, this estimated by machine-learning methods. In study, multilayer perceptron (MLP) Stacking Regressor, an ensemble models, used to predict high-performance concrete. Then, ML model’s explained feature importance analysis Shapley additive explanations (SHAPs), developed models are interpreted. effect using different random splits training test sets has been investigated. It was observed stacking regressor, which combined outputs Extreme Gradient Boosting (XGBoost), Category (CatBoost), Light Machine (LightGBM), Extra Trees regressors forest as final estimator, performed significantly better than MLP regressor. shown predicted regressor average R2 score 0.971 on set. On other hand, model 0.909. results SHAP showed age amounts silica fume, fiber, superplasticizer, cement, aggregate, water have greatest impact predictions.

Язык: Английский

---

Predictive and experimental assessment of chloride ion permeation in concrete subjected to multi-factorial conditions using the XGBoost algorithm

Journal of Building Engineering, Год журнала: 2024, Номер 98, С. 111041 - 111041

Опубликована: Окт. 12, 2024

Язык: Английский

---

Enhancing load capacity prediction of column using eReLU-activated BPNN model

Structures, Год журнала: 2023, Номер 58, С. 105600 - 105600

Опубликована: Дек. 1, 2023

Язык: Английский

---

Prediction of compressive strength of high-performance concrete using optimization machine learning approaches with SHAP analysis

Journal of Building Pathology and Rehabilitation, Год журнала: 2024, Номер 9(2)

Опубликована: Май 24, 2024

Язык: Английский

---

Intelligent predicting and monitoring of ultra-high-performance fiber reinforced concrete composites − A review

Composites Part A Applied Science and Manufacturing, Год журнала: 2024, Номер unknown, С. 108555 - 108555

Опубликована: Окт. 1, 2024

Язык: Английский

---