Effect of Lithium-Slag in the Performance of Slag Cement Mortar Based on Least-Squares Support Vector Machine Prediction

Lu, Jianghu; Yu, Zhenting; Zhu, Yuanzhe; Huang, Shaowen; Luo, Qi; Zhang, Siyu

doi:10.3390/ma12101652

Cited by 35 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is a waste residue from lithium carbonate (Li 2 CO 3 ) production, and estimates suggest that about 10 tons of LS are generated for each ton of Li 2 CO 3 produced [25]. The chemical composition of LS mainly consists of SiO 2 , Al 2 O 3 and sodium oxide (Na 2 O) [26]. Fayalite slag (FS) is another industrial waste slag used in one-part AAMs [27,28].…”

Section: Industrial By-products and Waste Materialsmentioning

confidence: 99%

One part alkali activated materials: A state-of-the-art review

El-Zeadani

Bompa

Elghazouli

2022

Journal of Building Engineering

View full text Add to dashboard Cite

Section: Industrial By-products and Waste Materialsmentioning

confidence: 99%

One part alkali activated materials: A state-of-the-art review

El-Zeadani

Bompa

Elghazouli

2022

Journal of Building Engineering

View full text Add to dashboard Cite

“…Additionally, being a porous mineral material [ 70 ], LS stores free water within its pore structure, which increases the water retention in the concrete and reduces water evaporation. This, in turn, effectively minimizes drying shrinkage [ 13 ].…”

Section: Durability Of Cementitious Composites With Ls Incorporationmentioning

confidence: 99%

“…LS, which is rich in silicon, aluminum, and calcium oxides, has garnered interest as a substitute for ordinary Portland cement (OPC) in concrete production, thereby offering a reduced carbon footprint and costs [ 13 , 14 ]. However, its sulfuric acid extraction origins with elevated SO 3 levels necessitate caution in its use to maintain cement stability [ 15 , 16 , 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

A Review on Cementitious and Geopolymer Composites with Lithium Slag Incorporation

Gou,

Rupasinghe,

Sofi

et al. 2023

Materials

View full text Add to dashboard Cite

This study critically reviews lithium slag (LS) as a supplementary cementitious material (SCM), thereby examining its physiochemical characteristics, mechanical properties, and durability within cementitious and geopolymer composites. The review reveals that LS’s particle size distribution is comparable to fly ash (FA) and ground granulated blast furnace slag (GGBS), which suggests it can enhance densification and nucleation in concrete. The mechanical treatment of LS promotes early hydration by increasing the solubility of aluminum, lithium, and silicon. LS’s compositional similarity to FA endows it with low-calcium, high-reactivity properties that are suitable for cementitious and geopolymeric applications. Increasing the LS content reduces setting times and flowability while initially enhancing mechanical properties, albeit with diminishing returns beyond a 30% threshold. LS significantly improves chloride ion resistance and impacts drying shrinkage variably. This study categorizes LS’s role in concrete as a filler, pozzolan, and nucleation agent, thereby contributing to the material’s overall reduced porosity and increased durability. Economically, LS’s cost is substantially lower than FA’s; meanwhile, its environmental footprint is comparable to GGBS, thereby making it a sustainable and cost-effective alternative. Notwithstanding, there is a necessity for further research on LS’s fine-tuning through grinding, its tensile properties, its performance under environmental duress, and its pozzolanic reactivity to maximize its utility in concrete technologies. This study comprehensively discusses the current strengths and weaknesses of LS in the field of building materials, thereby offering fresh perspectives and methodologies to enhance its performance, improve its application efficiency, and broaden its scope. These efforts are driving the sustainable and green development of LS in waste utilization and advanced concrete technology.

show abstract

“…The study concluded with the highly precise prediction of UHPC compressive strength, having an R 2 of 0.96. Lu et al (2019) have applied the Support Vector Machine (SVM) modelling approach to determine the lithium-slag effect on the properties of cementitious mortar and resulted in an 11% enhanced and improved prediction performance of SVM with respect to other ML models. Similarly, Solhmirzaei et al (2020) also reported the effective prediction of SVM modelling in the case of shear capacity for UHPC beams.…”

Section: Introductionmentioning

confidence: 99%

Application of machine learning algorithms to evaluate the influence of various parameters on the flexural strength of ultra-high-performance concrete

et al. 2023

View full text Add to dashboard Cite

The effect of various parameters on the flexural strength (FS) of ultra-high-performance concrete (UHPC) is an intricate mechanism due to the involvement of several inter-dependent raw ingredients. In this digital era, novel artificial intelligence (AI) approaches, especially machine learning (ML) techniques, are gaining popularity for predicting the properties of concrete composites due to their better precision than typical regression models. In addition, the developed ML models in the literature for FS of UHPC are minimal, with limited input parameters. Hence, this research aims to predict the FS of UHPC considering extensive input parameters (21) and evaluate each their effect on its strength by applying advanced ML approaches. Consequently, this paper involves the application of ML approaches, i.e., Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Gradient Boosting (GB), to predict the FS of UHPC. The GB approach is more effective in predicting the FS of UHPC precisely than the SVM and MLP algorithms, as evident from the outcomes of the current study. The ensembled GB model determination coefficient (R2) is 0.91, higher than individual SVM with 0.75 and individual MLP with 0.71. Moreover, the precision of applied models is validated by employing the k-fold cross-validation technique. The validity of algorithms is ensured by statistical means, i.e., mean absolute error and root mean square errors. The exploration of input parameters (raw materials) impact on FS of UHPC is also made with the help of SHAP analysis. It is revealed from the SHAP analysis that the steel fiber content feature has the highest influence on the FS of UHPC.

show abstract

Effect of Lithium-Slag in the Performance of Slag Cement Mortar Based on Least-Squares Support Vector Machine Prediction

Cited by 35 publications

References 18 publications

One part alkali activated materials: A state-of-the-art review

One part alkali activated materials: A state-of-the-art review

A Review on Cementitious and Geopolymer Composites with Lithium Slag Incorporation

Application of machine learning algorithms to evaluate the influence of various parameters on the flexural strength of ultra-high-performance concrete

Contact Info

Product

Resources

About