Machine Learning Modeling to Predict the Compressive Strength of Concrete

Synopsis

This study developed accurate models using machine learning to estimate the compressive strength of concrete, with the voting regression model showing the highest effectiveness and outperforming other models, providing valuable tools for evaluating concrete strength efficiently and enhancing construction practices for sustainability.

Machine learning has emerged as a transformative tool in civil engineering, offering promising avenues for advancing prediction and analysis within diverse domains. Its integration into civil engineering practices holds the potential to augment predictability and cost-effectiveness by reducing the dependence on resource-intensive real-time experimentation. A significant application of machine learning in civil engineering is the prediction of compressive strength in concrete.

The compressive strength of concrete, a crucial factor for ensuring structural integrity in constructions like buildings and bridges, traditionally involves time-consuming experimental testing.

The advent of machine learning presents an opportunity to create models capable of precise compressive strength estimation, thereby streamlining the assessment process. Concrete, valued for its strength, durability, and adaptability, serves as a cornerstone in construction. The Compressive Strength of concrete directly influences its performance, making accurate predictions essential.

Traditional methods are resource-intensive, prompting the exploration of machine learning models for efficient and cost-effective Compressive Strength assessment.

Lakshmana Kalabarige and colleagues (2024) described machine learning modeling integrating experimental analysis for predicting compressive strength of concrete containing different industrial byproducts. 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.

The performance of each machine learning model was evaluated using five metrics: 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).

This study focuses on applying various machine learning models to experimental data involving concrete and industrial byproducts to forecast concrete strength. This study focuses on different machine learning approaches: baseline regression models, boosting model, bagging model, tree-based ensemble models, and average voting regression (VR).

The study employs a comprehensive set of regression models, including four baseline regression models (BRM), two boosting-based models (LGBM) and XGB, as well as tree-based BAMs like Random Forest (RF) and extra tree regression (ETR). It also incorporates both the ETR-based bagging model (BagETR) and XGB-based bagging (BagXGB) and average voting regression (AVR) models in their analysis.

The dataset used in this study consists of 223 experimental compositions of concrete, with the Compressive Strength ranged from 10 to 120 MPa. The data collection process involved testing concrete cube samples of size 150×150×150 mm3 in a universal testing machine with a capacity of 100 T. The dataset consists of 223 instances with 15 features, with Compressive Strength being a dependent feature and 14 independent variables.

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.

Future work

The future scope of the study will focus on exploring advanced machine learning techniques, specifically integrating deep learning models, to overcome dataset size limitations and refine the accuracy of concrete strength predictions.

 

Reference

Lakshmana Rao Kalabarige, Jayaprakash Sridhar, Sivaramakrishnan Subbaram, Palaniappan Prasath, Ravindran Gobinath, "Machine Learning Modeling Integrating Experimental Analysis for Predicting Compressive Strength of Concrete Containing Different Industrial Byproducts", Advances in Civil Engineering, vol. 2024, Article ID 7844854, 11 pages, 2024. https://doi.org/10.1155/2024/7844854   

 

Cite this page

Machine Learning Modeling to Predict the Compressive Strength of Concrete. (n.d.). Titumirhasan.Com. Retrieved March 3, 2024, from https://www.titumirhasan.com/2024/03/machine-learning-modeling-to-predict.html