Abstract
Predicting properties of concrete is a major issue for building sustainable structures. In the last decade, numerous publications have shown that machine learning algorithms can play a major role to predict these properties. The key factor is the availability of data to train the models. Collecting, cleaning and consolidating data can be challenging tasks, especially in a concrete industry in which the digitalization of the supply chain is still in progress. We propose in this study to use raw production data to evaluate the performance of a machine learning algorithm compared to an empirical model. The concrete strength value is predicted using both approaches and compared to the measured value. Even if machine learning algorithm shows good performance, no significant increase in the prediction accuracy is obtained.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Neville, A.M.: Properties of Concrete. 5th edn. Pearson (2011)
Powers, T.C., Brownyard, T.L.: Studies of the physical properties of hardened Portland cement paste. Res. Lab. Portland Cem. Assoc. Bull. 22, 101–992 (1948)
Acker, P.: Micromechanical analysis of creep and shrinkage mechanisms. In: Ulm, F.-J., Bažant, Z.P., Wittmann, F.H. (eds.), Creep, Shrinkage and Durability Mechanics of Concrete and Other Quasi-brittle Materials, 6th International Conference, Elsevier, Amsterdam, pp. 15–26 (2001)
De Larrard, F.: Concrete Mixture Proportioning: A Scientific Approach. CRC Press, Boca Raton (1999)
Copeland, B.J.: Artificial intelligence. https://www.britannica.com/technology/artificial-intelligence (2022)
Dao, D.V., et al.: A sensitivity and robustness analysis of GPR and ANN for high-performance concrete compressive strength prediction using a monte carlo simulation. Sustainability, 12, 830 (2020)
Cui, L., Chen, P., Wang, L., Li, J., Ling, H.: Application of extreme gradient boosting based on grey relation analysis for prediction of compressive strength of concrete. Adv. Civ. Eng. 2021(5), 1–14 (2021)
Ahmed, A., Jin, W., Ali, M.: Artificial intelligence models for predicting mechanical properties of recycled aggregate concrete. critical review. J. Ad. Concr. Technol. 20, 404–429 (2022)
G. Ke, G., et al.: LightGBM: a highly efficient gradient boosting decision tree. In: Advances in Neural Information Processing Systems. vol. 30 (2017)
Bahmani, M.J.: Understanding lightGBM parameters (and how to tune them) (2022). https://neptune.ai/blog/lightgbm-parameters-guide
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Delaplace, A., Razinhas, U.O., Bouchard, R., Griesser, A. (2023). Performance of Data Driven Algorithms to Predict Concrete Strength Using Production Raw Data. In: Jędrzejewska, A., Kanavaris, F., Azenha, M., Benboudjema, F., Schlicke, D. (eds) International RILEM Conference on Synergising Expertise towards Sustainability and Robustness of Cement-based Materials and Concrete Structures. SynerCrete 2023. RILEM Bookseries, vol 44. Springer, Cham. https://doi.org/10.1007/978-3-031-33187-9_64
Download citation
DOI: https://doi.org/10.1007/978-3-031-33187-9_64
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33186-2
Online ISBN: 978-3-031-33187-9
eBook Packages: EngineeringEngineering (R0)