Review of Low to High Strength Alkali-Activated and Geopolymer Concrete

Kamath, Muralidhar; Prashanth, Shreelaxmi; Kumar, Mahesh

doi:10.1007/978-981-15-8293-6_8

Cited by 7 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among these, the more prominent are linear, multilinear, and nonlinear regression methods [14][15][16][17]. Machine Learning (ML) based on data analysis techniques are also gaining popularity in different study areas [18][19][20][21][22], by which a robust and precise prediction model for the compressive strength of concrete could be developed upon analyzing crucial data [23][24][25][26]. In recent studies, artificial neural network (ANN) and Decision trees (DT) have come out with more potential for predicting the more accurate compressive strength [27][28][29].…”

Section: Introductionmentioning

confidence: 99%

Comparative study of advanced computational techniques for estimating the compressive strength of UHPC

Khan¹,

Lao²,

Dai³

2022

JACF

View full text Add to dashboard Cite

The effect of raw materials on the compressive strength of concrete is a complex process, especially in the case of ultra-high-performance concrete (UHPC), where a higher number of inter-dependent parameters are involved in the strength development. In this era of digitalization, advanced machine learning methods are used to predict the material's mechanical characteristics because of their superior performance compared to conventional and nonlinear statistical regression models. Thus, the goal of the current study is to estimate the compressive strength of UHPC from the designed raw materials using advanced machine learning techniques. The compressive strength of UHPC is predicted from the 14 input parameters, i.e., cement, fly ash, slag, silica fume, nano-silica, limestone powder, sand, coarse aggregate, quartz powder, water, superplasticizer, PE fiber, steel fiber, and curing time. A total of eight machine learning models were compared that include multi-layer perceptron neural network (MLPNN), MLPNN Bootstrap aggregating (MLPNN-BA), MLPNN adaptive boosting (MLPNN-AB), Gradient boosting (GB), Decision tree (DT), DT Bootstrap aggregating (DT-BA), DT adaptive boosting (DT-AB) and Random Forest (RNF). The validation and performance evaluation of the above models were checked by using K-fold cross-validation, mean absolute error (MAE), root mean square error (RSME), coefficient of determination (R2), relative root mean square error (RRMSE), performance index (PI), and Nash Sutcliffe efficiency (NSE). The optimal model was selected based on the results of all statistical checks. It was found the ensembled machine learning models especially decision tree-based models outperform the neural network-based models with higher accuracy and low error. Thus, the recommended machine learning model is random forest having superior prediction capacity followed by DT Bootstrap aggregating and DT adaptive boosting.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparative study of advanced computational techniques for estimating the compressive strength of UHPC

Khan¹,

Lao²,

Dai³

2022

JACF

View full text Add to dashboard Cite

show abstract

“…The accuracy of models also depends upon larger the data considered, and which leads to more accurate predicted model. Developing a precise and dependable compressive strength prediction model enables the engineers and researchers with crucial data to analyze (Ben Chaabene et al, 2020;Chou and Pham, 2013;Jagadisha et al, 2021;Kamath et al, 2021aKamath et al, , 2021bPatel et al, 2018). Predominantly previous works only evolve their prediction systems based on single artificial learning model or statistics.…”

Section: Introductionmentioning

confidence: 99%

“…Hardened properties of concrete depend upon factors such as cement content, water to cement ratio, type and properties of pozzolana used and the dosage of superplasticizers (Hemmati Pourghashti et al , 2018). The microstructure, pore structure and distribution and orientation of microcracks also have a significant influence on its compressive strength (Kamath et al , 2021a, 2021b). Designers and engineers have been working ways and means on to have an effective analytical/statistical tool to predict the hardened properties of conventional and special concretes (Ahmad et al , 2021; Loganathan et al , 2015; Loganathan and Gandhi, 2015).…”

Section: Introductionmentioning

confidence: 99%

Machine-Learning-Algorithm to predict the High-Performance concrete compressive strength using multiple data

Kamath

Prashanth

Kumar

et al. 2022

JEDT

View full text Add to dashboard Cite

Purpose The compressive strength of concrete depends on many interdependent parameters; its exact prediction is not that simple because of complex processes involved in strength development. This study aims to predict the compressive strength of normal concrete and high-performance concrete using four datasets. Design/methodology/approach In this paper, five established individual Machine Learning (ML) regression models have been compared: Decision Regression Tree, Random Forest Regression, Lasso Regression, Ridge Regression and Multiple-Linear regression. Four datasets were studied, two of which are previous research datasets, and two datasets are from the sophisticated lab using five established individual ML regression models. Findings The five statistical indicators like coefficient of determination (R2), mean absolute error, root mean squared error, Nash–Sutcliffe efficiency and mean absolute percentage error have been used to compare the performance of the models. The models are further compared using statistical indicators with previous studies. Lastly, to understand the variable effect of the predictor, the sensitivity and parametric analysis were carried out to find the performance of the variable. Originality/value The findings of this paper will allow readers to understand the factors involved in identifying the machine learning models and concrete datasets. In so doing, we hope that this research advances the toolset needed to predict compressive strength.

show abstract

“…Alkali activators plays an essential role in dissolution of atoms to form geopolymer precursors. Potassium Hydroxide, Sodium Hydroxide, Potassium Silicate, and Sodium Silicate are alkaline solutions that have been used popularly [16][17][18][19]. Commonly used alkaline liquids are Sodium Hydroxide and Sodium Silicate.…”

Section: Introductionmentioning

confidence: 99%

Fresh mechanical and durability properties of alkali-activated fly ash-slag concrete: a review

Abhishek

Prashant

Kamath

et al. 2021

Innov. Infrastruct. Solut.

Self Cite

View full text Add to dashboard Cite

This paper describes a review of the state-of-the-art research carried on the fresh and hardened properties of Alkali Activated Binders and Concretes. Though, many research have been carried out in the recent times on alkali activated binders, few key parameters still remain unattended, that restricts the commercial application of AAMs to the general construction activities. Fresh properties, mechanical strength and durability performance of Alkali activated concrete with various Alumino silicates as base materials is mentioned. An essential parameter of Alkali activated concrete is the concentration of alkaline solution on which various properties like mechanical strength, setting time and durability depends. Influence of wide range of concentrations from 6 to 16 M on these properties are studied and reported in this paper. This paper mainly concentrates on properties of readily available base materials such as Fly ash and Slag and the means to improve their performance through the use of various industrial and agro-based byproducts as additives. Problems pertaining to practical applicability of AAMs to general construction activities are also highlighted.

show abstract

Review of Low to High Strength Alkali-Activated and Geopolymer Concrete

Cited by 7 publications

References 27 publications

Comparative study of advanced computational techniques for estimating the compressive strength of UHPC

Comparative study of advanced computational techniques for estimating the compressive strength of UHPC

Machine-Learning-Algorithm to predict the High-Performance concrete compressive strength using multiple data

Fresh mechanical and durability properties of alkali-activated fly ash-slag concrete: a review

Contact Info

Product

Resources

About