Prediction of Compressive Strength of Concrete By Various Methods: A Comparative Synthesis of Conventional , Statistical , Machine Learning and Intelligent Prediction Techniques

  • Unique Paper ID: 211185
  • Volume: 13
  • Issue: 6
  • PageNo: 3641-3645
  • Abstract:
  • The concrete compressive strength test acts as the basic metric for assessing the strength and quality of a structure. Laboratory testing is time-consuming and requires large amounts of resources; thus, there is a need for quick and efficient estimation methods. In this study, three estimation models were examined: Multiple Linear Regression (MLR), Quadratic Response Surface Methodology (RSM),and Artificial Neural Networks (ANN). The mixture proportions were taken according to IS 10262:2019 and IS 456:2000 standards in grades M30 to M50. Accuracy of each model was assessed using coefficient of determination (R2), Root Mean Square Error (RMSE),and Mean Absolute Error (MAE). It was proven that ANN provides better prediction performance and can be used as an efficient method

Copyright & License

Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{211185,
        author = {ROHAN MADHUKAR BHUSARE and KIRAN RANGNATH CHILLARE and VISHAL SHINDE and HARSHAD JAYRAM JOPALE and RUSHIRAJ PANDIT and SANTOSH BALIRAM MAHANOR},
        title = {Prediction of Compressive Strength of Concrete By Various Methods: A Comparative Synthesis of Conventional , Statistical , Machine Learning and Intelligent Prediction Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {6},
        pages = {3641-3645},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=211185},
        abstract = {The concrete compressive strength test acts as the basic metric for assessing the strength and quality of a structure. Laboratory testing is time-consuming and requires large amounts of resources; thus, there is a need for quick and efficient estimation methods. In this study, three estimation models were examined: Multiple Linear Regression (MLR), Quadratic Response Surface Methodology (RSM),and Artificial Neural Networks (ANN). The mixture proportions were taken according to IS 10262:2019 and IS 456:2000 standards in grades M30 to M50. Accuracy of each model was assessed using coefficient of determination (R2), Root Mean Square Error (RMSE),and Mean Absolute Error (MAE). It was proven that ANN provides better prediction performance and can be used as an efficient method},
        keywords = {concrete compressive strength; machine learning; artificial neural network; support vector regression; random forest; gradient boosting; Cat Boost; prediction model; explainable machine learning.},
        month = {November},
        }

Cite This Article

BHUSARE, R. M., & CHILLARE, K. R., & SHINDE, V., & JOPALE, H. J., & PANDIT, R., & MAHANOR, S. B. (2026). Prediction of Compressive Strength of Concrete By Various Methods: A Comparative Synthesis of Conventional , Statistical , Machine Learning and Intelligent Prediction Techniques. International Journal of Innovative Research in Technology (IJIRT), 13(6), 3641–3645.

Related Articles