Machine learning approaches for predicting compressive strength of concrete with fly ash admixture

Mahajan, Lomesh; Bhagat, S. R.

doi:10.17515/resm2022.534ma0927

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This research also gives a means of comparing and evaluating the results of experiments conducted using individual and ensemble ML approaches. Both statistical tests and k-fold performance models were evaluated for cross-validation [71]. The purpose of this analysis is to look at how different inputs affect the reliability of the expected output.…”

Section: Research Significancementioning

confidence: 99%

See 1 more Smart Citation

Predicting strength of concrete by ensemble technique

Kirange¹,

Mahajan²

2023

Res. Eng. Struct. Mater.

View full text Add to dashboard Cite

The developing countries share similar attributes at all the regions. Still 43% of urban population did not escape from slums live hoods. As many developing countries focuses on the infrastructural development and try to improve people living standards. This infrastructural built-up activity consumes lots of concrete and other construction materials. These construction materials possess different properties from place to place. Cementitious composites undergo transformations in their fundamental properties due to regional variations in environmental conditions. Therefore, their mechanical strength computing tools plays crucial role. When topic touches with concrete, one of the most important characteristics is the compressive strength. Predicting the strength of concrete has traditionally been done with using mechanical means, but in recent years few soft computing methods have become important tools. In this research, we apply two methods to compute the Compressive strength of fly ash concrete based on the results of our own experimental findings. To anticipate concrete strength., this study investigated the properties of all the materials involved. The ensemble methodology and the decision tree were two of the success-forecasting methodologies that were investigated, and comparative assessments were made on them. The R 2 value for the ensemble methodology was determined to be 0.96, which was much higher than the DT method's 0.76. In addition to k-fold Cross Validation, the findings of the trials are further supported by assessments of root mean square error (RMSE) and root mean error (RME). Ensemble approaches are good for minimizing model variance, improving prediction accuracy. Combining many models to make a single forecast from all their potential predictions eliminates variation.

show abstract

Section: Research Significancementioning

confidence: 99%

“…Concrete factories have a hard time with strength prediction because of this. In ancient times [12], the strength became an important criterion for heterogeneous building. Due to worldwide standards and sustainable development, the mineral additives used for making concrete found key role in the environment [13].…”

Section: Introductionmentioning

confidence: 99%

Predicting strength of concrete by ensemble technique

Kirange¹,

Mahajan²

2023

Res. Eng. Struct. Mater.

View full text Add to dashboard Cite

show abstract

“…In the last decades, many researchers have worked on the application of robust machine learning techniques in different civil engineering sectors as regression and classification tasks [4,12]. Additionally, researchers have focused on exploring various techniques to enhance the prediction accuracy of concrete compressive strength by using machine learning (ML) techniques as well [5,9,[13][14][15][16][17]. Among these techniques, ensemble learning methods have garnered significant attention due to their ability to combine multiple models to achieve superior predictive performance.…”

Section: Introductionmentioning

confidence: 99%

Concrete Compressive Strength Prediction by Ensemble Machine Learning Approach

Thapa

2024

J. Eng. Sci.

View full text Add to dashboard Cite

The prediction of concrete compressive strength is a crucial aspect of ensuring the structural integrity and durability of construction projects. In recent years, machine learning approaches have improved upon the limitations of empirical formulas and laboratory testing methods for predicting concrete compressive strength. This study utilizes ensemble machine-learning techniques, such as Bagging, XGBoost, and Stacking models, to enhance the accuracy of concrete compressive strength prediction models. A five-fold cross-validation technique was applied to mitigate the problems of underfitting or overfitting in the regression model. Furthermore, various statistical indices were employed to compare the forecasting performance of these ensemble techniques. The prediction performance of this research revealed that XGBoost achieved the highest R-squared value of 93%, followed by Stacking and Bagging regression models at 92%. Consequently, this research underscores the potential of ensemble techniques as valuable tools in the domain of civil engineering, paving the way for more reliable and efficient construction practices.

show abstract