Predicting the compressive strength of steelmaking slag concrete with machine learning – Considerations on developing a mix design tool

Penido, Rúben El-Katib; Paixão, Rafael Christian Fonseca da; Costa, Laís Cristina Barbosa; Peixoto, Ricardo André Fiorotti; Cury, Alexandre; Mendes, Júlia Castro

doi:10.1016/j.conbuildmat.2022.127896

Cited by 29 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach establishes a relationship between decision variables (geopolymer components) and objectives (geopolymer properties), and uses optimization algorithms to nd the optimal geopolymer mixture. In recent years, researchers have started applying machine learning (ML) methods to model the properties of geopolymers [23][24][25].…”

Section: Introductionmentioning

confidence: 99%

Multi-objective optimization of ternary geopolymers with multiple solid wastes using machine learning and NSGA-II

Zhang,

Shang,

Huo

et al. 2024

Preprint

View full text Add to dashboard Cite

The design of the mixtures of the ternary geopolymer is challenging due to the need to balance multiple objectives, including cost, strength, and carbon emissions. In order to address this multi-objective optimization (MOO) problem, machine learning models and the NSGA-II algorithm are employed in this study. To train the machine learning models, namely Artificial Neural Network (ANN), Support Vector Regressor, Extremely Randomized Tree, and Gradient Boosting Regression, 120 uniaxial compressive strength (UCS) values of ternary geopolymers with fly ash (FA), granulated blast furnace slag (GBFS) and steel slag (SS) as precursor materials were obtained from laboratory tests. Results show that the ternary geopolymer with the ratio of FA:GBFS:SS of 2:5:3 has the highest 28-d UCS of 46.8 MPa. The predictive accuracy of the ANN model is the highest with R = 0.949 and RMSE = 3.988MPa on the test set. Furthermore, the Shapley Additive Explanations analysis indicates that precursor materials exhibit the most significant influence on the UCS, particularly the content of GBFS. Based on the ANN model and NSGA-II algorithm, a multi-objective optimization (MOO) model is developed to optimize simultaneously the strength, cost and carbon emission of the ternary geopolymer. The derived MOO model can be used to design mixtures of other cementitious materials with multiple objectives.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-objective optimization of ternary geopolymers with multiple solid wastes using machine learning and NSGA-II

Zhang,

Shang,

Huo

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The research landscape further expands with investigations into waste marble powder [9], self-compacting concrete [10], lightweight fiber-reinforced concrete [11,12], and recycled aggregate cement [13], showcasing the versatility of ML in diverse concrete compositions. Studies on foamed concrete [14], high-performance concrete [15], and steelmaking slag concrete [16] underscore the effectiveness of ML models, with outcomes shaping future applications. In addition, ANN is employed to predict the CS of concrete by mixing high volumes of fly ash (FA) [17] is tested.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Modeling Integrating Experimental Analysis for Predicting Compressive Strength of Concrete Containing Different Industrial Byproducts

Kalabarige,

Sridhar,

Subbaram

et al. 2024

Advances in Civil Engineering

View full text Add to dashboard Cite

This study aimed to develop accurate models for estimating the compressive strength (CS) of concrete using a combination of experimental testing and different machine learning (ML) approaches: baseline regression models, boosting model, bagging model, tree-based ensemble models, and average voting regression (VR). The research utilized an extensive experimental dataset with 14 input variables, including cement, limestone powder, fly ash, granulated glass blast furnace slag, silica fume, rice husk ash, marble powder, brick powder, coarse aggregate, fine aggregate, recycled coarse aggregate, water, superplasticizer, and voids in mineral aggregate. To evaluate the performance of each ML model, five metrics were used: mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), coefficient of determination (R2-score), and relative root mean squared error (RRMSE). The comparative analysis revealed that the VR model exhibited the highest effectiveness, displaying a strong correlation between actual and estimated outcomes. The boosting, bagging, and VR models achieved impressive R2-scores in the range of 86.69%–92.43%, with MAE ranging from 3.87 to 4.87, MSE from 21.74 to 38.37, RMSE from 4.66 to 4.87, and RRMSE between 8% and 11%. Particularly, the VR model outperformed all other models with the highest R2-score (92.43%) and the lowest error rate. The developed models demonstrated excellent generalization and prediction capabilities, providing valuable tools for practitioners, researchers, and designers to efficiently evaluate the CS of concrete. By mitigating environmental vulnerabilities and associated impacts, this research can significantly contribute to enhancing the quality and sustainability of concrete construction practices.

show abstract

“…Specific areas of structures and materials have been used ANN to evaluate the applicability of machine learning in civil engineering, with the majority of the studies in this field aiming to predict physical, chemical, or mechanical properties, especially in concrete. Examples include the prediction of compressive strength [26,28,29,[34][35][36][37], the elastic modulus [38][39][40][41][42][43], the determination of the workability of concrete and its consistency in the fresh state [44][45][46][47], the mapping of composite degradation mechanisms [48][49][50][51][52][53][54], and the development of a concrete-mix design model [55][56][57][58].…”

Section: Introductionmentioning

confidence: 99%

Influence of the ANN Hyperparameters on the Forecast Accuracy of RAC’s Compressive Strength

Almeida,

Felix,

de Sousa

et al. 2023

Materials

View full text Add to dashboard Cite

The artificial neural networks (ANNs)-based model has been used to predict the compressive strength of concrete, assisting in creating recycled aggregate concrete mixtures and reducing the environmental impact of the construction industry. Thus, the present study examines the effects of the training algorithm, topology, and activation function on the predictive accuracy of ANN when determining the compressive strength of recycled aggregate concrete. An experimental database of compressive strength with 721 samples was defined considering the literature. The database was used to train, validate, and test the ANN-based models. Altogether, 240 ANNs were trained, defined by combining three training algorithms, two activation functions, and topologies with a hidden layer containing 1–40 neurons. The ANN with a single hidden layer including 28 neurons, trained with the Levenberg–Marquardt algorithm and the hyperbolic tangent function, achieved the best level of accuracy, with a coefficient of determination equal to 0.909 and a mean absolute percentage error equal to 6.81%. Furthermore, the results show that it is crucial to avoid the use of overly complex models. Excessive neurons can lead to exceptional performance during training but poor predictive ability during testing.

show abstract

Predicting the compressive strength of steelmaking slag concrete with machine learning – Considerations on developing a mix design tool

Cited by 29 publications

References 32 publications

Multi-objective optimization of ternary geopolymers with multiple solid wastes using machine learning and NSGA-II

Multi-objective optimization of ternary geopolymers with multiple solid wastes using machine learning and NSGA-II

Machine Learning Modeling Integrating Experimental Analysis for Predicting Compressive Strength of Concrete Containing Different Industrial Byproducts

Influence of the ANN Hyperparameters on the Forecast Accuracy of RAC’s Compressive Strength

Contact Info

Product

Resources

About