Machine learning-based prediction of compressive strength for limestone calcined clay cements

Khessaimi, Yassine El; Hafiane, Youssef El; Smith, Agnès; Peyratout, Claire; Tamine, Karim; Adly, Samir; Barkatou, Moulay A.

doi:10.1016/j.jobe.2023.107062

Cited by 3 publications

(1 citation statement)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning is a promising solution to predicting the properties of multi-component materials. Although many studies have employed ML models to predict the properties of cementitious materials [19][20][21], only a few studies [22][23][24] have applied ML to LC 3 . Thus, there is a technological gap associated with the limited development and use of ML applications in LC 3 systems, at least compared with other cementitious materials (e.g., OPC and alkali-activated cement).…”

Section: Introductionmentioning

confidence: 99%

On the Prediction of the Mechanical Properties of Limestone Calcined Clay Cement: A Random Forest Approach Tailored to Cement Chemistry

Han,

Aylas-Paredes,

Huang

et al. 2023

Minerals

View full text Add to dashboard Cite

Limestone calcined clay cement (LC3) is a sustainable alternative to ordinary Portland cement, capable of reducing the binder’s carbon footprint by 40% while satisfying all key performance metrics. The inherent compositional heterogeneity in select components of LC3, combined with their convoluted chemical interactions, poses challenges to conventional analytical models when predicting mechanical properties. Although some studies have employed machine learning (ML) to predict the mechanical properties of LC3, many have overlooked the pivotal role of feature selection. Proper feature selection not only refines and simplifies the structure of ML models but also enhances these models’ prediction performance and interpretability. This research harnesses the power of the random forest (RF) model to predict the compressive strength of LC3. Three feature reduction methods—Pearson correlation, SHapley Additive exPlanations, and variable importance—are employed to analyze the influence of LC3 components and mixture design on compressive strength. Practical guidelines for utilizing these methods on cementitious materials are elucidated. Through the rigorous screening of insignificant variables from the database, the RF model conserves computational resources while also producing high-fidelity predictions. Additionally, a feature enhancement method is utilized, consolidating numerous input variables into a singular feature while feeding the RF model with richer information, resulting in a substantial improvement in prediction accuracy. Overall, this study provides a novel pathway to apply ML to LC3, emphasizing the need to tailor ML models to cement chemistry rather than employing them generically.

show abstract

Section: Introductionmentioning

confidence: 99%

On the Prediction of the Mechanical Properties of Limestone Calcined Clay Cement: A Random Forest Approach Tailored to Cement Chemistry

Han,

Aylas-Paredes,

Huang

et al. 2023

Minerals

View full text Add to dashboard Cite

show abstract

Research on predicting compressive strength of magnesium silicate hydrate cement based on machine learning

Luo,

Li,

Lin

et al. 2023

Construction and Building Materials

View full text Add to dashboard Cite

Modelling the mechanical properties of concrete produced with polycarbonate waste ash by machine learning

Sathvik,

Kumar,

Ulloa

et al. 2024

Sci Rep

View full text Add to dashboard Cite

India’s cement industry is the second largest in the world, generating 6.9% of the global cement output. Polycarbonate waste ash is a major problem in India and around the globe. Approximately 370,000 tons of scientific waste are generated annually from fitness care facilities in India. Polycarbonate waste helps reduce the environmental burden associated with disposal and decreases the need for new raw materials. The primary variable in this study is the quantity of polycarbonate waste ash (5, 10, 15, 20 and 25% of the weight of cement), partial replacement of cement, water-cement ratio and aggregates. The mechanical properties, such as compressive strength, split tensile strength and flexural test results, of the mixtures with the polycarbonate waste ash were superior at 7, 14 and 28 days compared to those of the control mix. The water absorption rate is less than that of standard concrete. Compared with those of conventional concrete, polycarbonate waste concrete mixtures undergo minimal weight loss under acid curing conditions. Polycarbonate waste is utilized in the construction industry to reduce pollution and improve the economy. This study further simulated the strength characteristics of concrete made with waste polycarbonate ash using least absolute shrinkage and selection operator regression and decision trees. Cement, polycarbonate waste, slump, water absorption, and the ratio of water to cement were the main components that were considered input variables. The suggested decision tree model was successful with unparalleled predictive accuracy across important metrics. Its outstanding predictive ability for split tensile strength (R2 = 0.879403), flexural strength (R2 = 0.91197), and compressive strength (R2 = 0.853683) confirmed that this method was the preferred choice for these strength predictions.

show abstract

Machine learning-based prediction of compressive strength for limestone calcined clay cements

Cited by 3 publications

References 78 publications

On the Prediction of the Mechanical Properties of Limestone Calcined Clay Cement: A Random Forest Approach Tailored to Cement Chemistry

On the Prediction of the Mechanical Properties of Limestone Calcined Clay Cement: A Random Forest Approach Tailored to Cement Chemistry

Research on predicting compressive strength of magnesium silicate hydrate cement based on machine learning

Modelling the mechanical properties of concrete produced with polycarbonate waste ash by machine learning

Contact Info

Product

Resources

About