Concrete Strength Prediction Using Different Machine Learning Processes: Effect of Slag, Fly Ash and Superplasticizer
Abstract
:1. Introduction
2. Materials and Method
2.1. ML Modelling Framework
2.2. Prediction Models
2.2.1. Random Forest
- High accuracy can be achieved by using an integrated algorithm.
- The random process (i.e., random sampling and random features) reduces the over-fitting of a single DT, enables the processing of high-dimensional data with more features, and does not involve feature selection.
- The inclusion of unusual data has minimal impact on the outcomes.
- Multiple DTs are independent of one another and their computation times are short [31].
2.2.2. Principal Component Analysis
2.2.3. Particle Swarm Optimization (PSO)
2.3. Dataset Preparation
2.3.1. Dataset Sources
2.3.2. Dataset Pre-Processing
2.3.3. Dataset Division
2.4. Hyper-Parameter Training
2.5. Performance Measures
3. Results and Discussion
3.1. Performances of Machine Learning Models
3.2. Sensitivity Analysis of Input Variables
4. Conclusions and Outlook
- (1)
- The R, EVS, MAE and MSE values on the original dataset were 0.954, 0.901, 3.746 and 27.535, respectively, indicating that the ML model constructed in this study can accurately predict the strength of concrete prepared with BFS, FA, and superplasticizer, which has potential engineering application value.
- (2)
- After PCA processing, the prediction accuracy decreased (R = 0.864, EVS = 0.740, MAE = 6.130, MSE = 72.351), indicating that PCA dimension reduction has a negative impact on ML modeling and cannot be adopted. However, there is no doubt that the combination of the two has exploratory significance.
- (3)
- The sensitivity analysis showed that curing time has the greatest influence on the compressive strength of concrete, followed by cement > water > superplasticizer> fine aggregate > blast furnace slag > coarse aggregate > fly ash. This provided potential ideas for further improving the strength of concrete.
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Vázquez-Rowe, I.; Ziegler-Rodriguez, K.; Laso, J.; Quispe, I.; Aldaco, R.; Kahhat, R. Production of cement in Peru: Understanding carbon-related environmental impacts and their policy implications. Resour. Conserv. Recycl. 2019, 142, 283–292. [Google Scholar] [CrossRef]
- Wei, J.; Cen, K. Empirical assessing cement CO2 emissions based on China’s economic and social development during 2001–2030. Sci. Total Environ. 2019, 653, 200–211. [Google Scholar] [CrossRef] [PubMed]
- Fengming, X.; Steven, J.D.; Philippe, C.; Douglas, C.; Dabo, G.; Claus, P.; Tiemao, S.; Mark, S.; Jie, L.; Lanzhu, J.; et al. Substantial global carbon uptake by cement carbonation. Nat. Geosci. 2016, 9, 880–883. [Google Scholar]
- Chopperla, S.T.; Jupalli, R.; Kanraj, D.; Bahurudeen, A.; Haneefa, M.K.; Santhanam, M. Development of an Efficient Procedure for Sustainable Low Carbon Cement Manufacturing Process. Appl. Mech. Mater. 2015, 787, 142–146. [Google Scholar] [CrossRef]
- Lehner, P.; Konečný, P.; Ghosh, P. Variation of Durability and Strength Parameters of Pumice Based Mixtures. Materials 2021, 14, 3674. [Google Scholar] [CrossRef] [PubMed]
- Dirk, D.; Fredrik, E.; Sander, A.; Jeroen, H.; Peter, T.J.; Bo, B.; Bart, B.; Patrick, W. Hot stage processing of metallurgical slags. Resour. Conserv. Recycl. 2008, 52, 1121–1131. [Google Scholar]
- Tripathy, S.K.; Dasu, J.; Murthy, Y.R.; Kapure, G.; Pal, A.R.; Filippov, L.O. Utilisation perspective on water quenched and air-cooled blast furnace slags. J. Clean. Prod. 2020, 262, 121354. [Google Scholar] [CrossRef]
- Václavík, V.; Dirner, V.; Dvorský, T.; Daxner, J. The use of blast furnace slag. Metalurgija 2012, 51, 461–464. [Google Scholar]
- Kolani, B.; Buffo-Lacarrière, L.; Sellier, A.; Escadeillas, G.; Boutillon, L.; Linger, L. Hydration of slag-blended cements. Cem. Concr. Compos. 2012, 34, 1009–1018. [Google Scholar] [CrossRef]
- Yuksel, I. Blast-furnace slag. In Woodhead Publishing Series in Civil and Structural Engineering; Siddique, R., Cachim, P., Eds.; Woodhead Publishing: Sawston, UK, 2018; pp. 361–415. [Google Scholar] [CrossRef]
- Abdul Razak, H.; Venkatesh Babu, D.L. Fresh, Strength and Durability Characteristics of Binary and Ternary Blended Self Compacting Concrete. Int. J. Eng. Adv. Technol. 2019, 9. [Google Scholar]
- Gonzalez, A.; Navia, R.; Moreno, N. Fly ashes from coal and petroleum coke combustion: Current and innovative potential applications. Waste Manag. Res. 2009, 27, 976–987. [Google Scholar] [CrossRef] [PubMed]
- Elmrabet, R.; El Harfi, A.; El Youbi, M.S. Study of properties of fly ash cements. Mater. Today Proc. 2019, 13, 850–856. [Google Scholar] [CrossRef]
- Oner, A.; Akyuz, S.; Yildiz, R. An experimental study on strength development of concrete containing fly ash and optimum usage of fly ash in concrete. Cem. Concr. Res. 2005, 35, 1165–1171. [Google Scholar] [CrossRef]
- Chidiac, S.E.; Panesar, D.K. Evolution of mechanical properties of concrete containing ground granulated blast furnace slag and effects on the scaling resistance test at 28 days. Cem. Concr. Compos. 2008, 30, 63–71. [Google Scholar] [CrossRef]
- Majhi, R.K.; Nayak, A.N.; Mukharjee, B.B. Development of sustainable concrete using recycled coarse aggregate and ground granulated blast furnace slag. Constr. Build. Mater. 2018, 159, 417–430. [Google Scholar] [CrossRef]
- Subpaasa, P.; Nito, N.; Fujiwara, S.; Date, S. Evaluation of the Prediction and Durability on the Chloride Penetration in Cementitious Materials with Blast Furnace Slag as Cement Addition. Constr. Mater. 2022, 2, 53–69. [Google Scholar]
- Öner, M.; Erdoğdu, K.; Günlü, A. Effect of components fineness on strength of blast furnace slag cement. Cem. Concr. Res. 2022, 33, 463–469. [Google Scholar] [CrossRef]
- Nunez, I.; Marani, A.; Flah, M.; Nehdi, M.L. Estimating compressive strength of modern concrete mixtures using computational intelligence: A systematic review. Constr. Build. Mater. 2021, 310, 125279. [Google Scholar] [CrossRef]
- Fasihihour, N.; Abad, J.M.N.; Karimipour, A.; Mohebbi, M.R. Experimental and numerical model for mechanical properties of concrete containing fly ash: Systematic review. Measurement 2022, 188, 110547. [Google Scholar] [CrossRef]
- Deepak, C. Learning Algorithms Using BPNN & SFS for Prediction of Compressive Strength of Ultra-High Performance Concrete. Mach. Learn. Res. 2019, 4, 27. [Google Scholar]
- Imran, W.M.; Plevris, V.; Mir, J.; Chairman, N.; Ahmad, A. An alternative approach for measuring the mechanical properties of hybrid concrete through image processing and machine learning. Constr. Build. Mater. 2022, 328, 126899. [Google Scholar] [CrossRef]
- Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef] [Green Version]
- Ge, Q.; Liu, Z.Q.; Sun, H.Y.; Lang, D.; Shuai, F.X.; Shang, Y.Q.; Zhang, Y.Q. Robust design of self-starting drains using Random Forest. J. Mt. Sci. 2021, 18, 973–989. [Google Scholar] [CrossRef]
- Cihan, M.T. Comparison of artificial intelligence methods for predicting compressive strength of concrete. Građevinar 2021, 73, 617–632. [Google Scholar]
- Senagi, K.; Jouandeau, N. Parallel construction of Random Forest on GPU. J. Supercomput. 2022, 78, 10480–10500. [Google Scholar] [CrossRef]
- Churiwala, G.R.A.R. An Introduction to Machine Learning; Springer: Cham, Switzerland, 2019. [Google Scholar] [CrossRef]
- Chen, X.; Ishwaran, H. Random forests for genomic data analysis. Genomics 2012, 99, 323–329. [Google Scholar] [CrossRef] [Green Version]
- Chongchong, Q.; Wei, Z.; Xiang, L.; Huaiting, L.; Binh, T.P.; Zaher, M.Y. Particulate matter concentration from open-cut coal mines: A hybrid machine learning estimation. Environ. Pollut. 2020, 263, 114517. [Google Scholar]
- Sun, Y.; Li, G.; Zhang, N.; Chang, Q.; Xu, J.; Zhang, J. Development of ensemble learning models to evaluate the strength of coal-grout materials. Int. J. Min. Sci. Technol. 2021, 31, 153–162. [Google Scholar] [CrossRef]
- Ashley, C.; Jonathon, R.; David, K.; Angelica, W.; Anna, F.; Daniel, J. A High-Performance Computing Implementation of Iterative Random Forest for the Creation of Predictive Expression Networks. Genes 2019, 10, 996. [Google Scholar]
- Ringnér, M. What is principal component analysis? Nat. Biotechnol. 2008, 26, 303–304. [Google Scholar] [CrossRef]
- Jolliffe, I.T. Principal Component Analysis. Technometrics 2005. [Google Scholar] [CrossRef]
- Abdi, H.; Williams, L.J. Principal component analysis. Wiley interdisciplinary reviews. Comput. Stat. 2010, 2, 433–459. [Google Scholar] [CrossRef]
- Emerson, R.W. A Look at Principal Component Analysis. J. Vis. Impair. Blind. 2020, 114, 240–241. [Google Scholar] [CrossRef]
- Mohammed, M.H.; Mohamed, K.A.; Wajdi, J.B.; Mohammed, A.A. Incorporation of artificial neural network with principal component analysis and cross-validation technique to predict high-performance concrete compressive strength. Asian J. Civ. Eng. 2021, 22, 1019–1031. [Google Scholar]
- Jolliffe, I.T.; Cadima, J. Principal component analysis: A review and recent developments. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 2016, 374, 20150202. [Google Scholar] [CrossRef] [PubMed]
- Zhang, Y.; Gong, D.; Sun, X.; Guo, Y. A PSO-based multi-objective multi-label feature selection method in classification. Sci. Rep. 2017, 7, 1–12. [Google Scholar] [CrossRef] [PubMed]
- Hassan, R.; Cohanim, B.; De Weck, O.; Venter, G. A comparison of particle swarm optimization and the genetic algorithm. In Proceedings of the 46th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference, Austin, TX, USA, 18–21 April 2005; p. 1897. [Google Scholar] [CrossRef]
- Poli, R. An Analysis of Publications on Particle Swarm Optimisation Applications; University of Essex: Essex, UK, 2007. [Google Scholar]
- Shah, M.I.; Memon, S.A.; Khan, N.M.S.; Amin, M.N.; Aslam, F.; Javed, M.F.; Zhang, J. Machine Learning-Based Modeling with Optimization Algorithm for Predicting Mechanical Properties of Sustainable Concrete. Adv. Civ. Eng. 2021, 15. [Google Scholar] [CrossRef]
- De-Cheng, F.; Zhen-Tao, L.; Xiao-Dan, W.; Yin, C.; Jia-Qi, C.; Dong-Fang, W.; Zhong-Ming, J. Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach. Constr. Build. Mater. 2020, 230, 117000. [Google Scholar]
- Li, Q.; Song, Z. High-performance concrete strength prediction based on ensemble learning. Constr. Build. Mater. 2022, 324, 126694. [Google Scholar] [CrossRef]
- Yang, L.; Shami, A. On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing 2020, 415, 295–316. [Google Scholar] [CrossRef]
- Yu, T.; Zhu, H. Hyper-Parameter Optimization: A Review of Algorithms and Applications. arXiv 2020, arXiv:2003.05689. [Google Scholar]
- Claesen, M.; De Moor, B. Hyperparameter Search in Machine Learning. arXiv 2015, arXiv:1502.02127. [Google Scholar]
- Sedgwick, P. Pearson’s correlation coefficient. BMJ 2012, 345, e4483. [Google Scholar] [CrossRef] [Green Version]
- Asuero, A.G.; Sayago, A.; González, A.G. The correlation coefficient: An overview. Crit. Rev. Anal. Chem. 2006, 36, 41–59. [Google Scholar] [CrossRef]
- Partha, P.R.; Kunal, R. On Some Aspects of Variable Selection for Partial Least Squares Regression Models. QSAR Comb. Sci. 2008, 27, 302–313. [Google Scholar]
- Chai, T.; Draxler, R.R. Root mean square error (RMSE) or mean absolute error (MAE)?—Arguments against avoiding RMSE in the literature. Geosci. Model Dev. 2014, 7, 1247–1250. [Google Scholar] [CrossRef] [Green Version]
- Saltelli, A. Sensitivity analysis for importance assessment. Risk Anal. 2002, 22, 575–590. [Google Scholar] [CrossRef]
- Han-Seung, L.; Xiao-Yong, W.; Li-Na, Z.; Kyung-Taek, K. Analysis of the Optimum Usage of Slag for the Compressive Strength of Concrete. Materials 2015, 8, 1213–1229. [Google Scholar]
- Jain, K.L.; Rajawat, L.S.; Sancheti, G. Mechanical Properties of Ground Granulated Blast Furnace Slag Made Concrete. In IOP Conference Series: Earth and Environmental Science; IOP Publishing: Bristol, UK, 2021; Volume 796, p. 12063. [Google Scholar] [CrossRef]
- Cho, Y.K.; Jung, S.H.; Choi, Y.C. Effects of chemical composition of fly ash on compressive strength of fly ash cement mortar. Constr. Build. Mater. 2019, 204, 255–264. [Google Scholar] [CrossRef]
- Hwang, K.; Noguchi, T.; Tomosawa, F. Prediction model of compressive strength development of fly-ash concrete. Cem. Concr. Res. 2004, 34, 2269–2276. [Google Scholar] [CrossRef]
- Hemalatha, T.; Ramaswamy, A. A review on fly ash characteristics–Towards promoting high volume utilization in developing sustainable concrete. J. Clean. Prod. 2017, 147, 546–559. [Google Scholar] [CrossRef]
- Chakraborty, J.; Banerjee, S. Replacement of Cement by Fly Ash in Concrete. Int. J. Civ. Eng. 2016, 3, 58–60. [Google Scholar] [CrossRef] [Green Version]
- Li, G.; Zhao, X. Properties of concrete incorporating fly ash and ground granulated blast-furnace slag. Cem. Concr. Compos. 2003, 25, 293–299. [Google Scholar] [CrossRef]
- Zhang, S.Y.; Fan, Y.F.; Li, N.N. The Effect of Superplasticizer on Strength and Chloride Permeability of Concrete Containing GGBFS. Adv. Mater. Res. 2013, 804, 12–16. [Google Scholar] [CrossRef]
- Gołaszewski, J.; Szwabowski, J. Influence of superplasticizers on rheological behaviour of fresh cement mortars. Cem. Concr. Res. 2004, 34, 235–248. [Google Scholar] [CrossRef]
- Yang, L.; Yilmaz, E.; Li, J.; Liu, H.; Jiang, H. Effect of superplasticizer type and dosage on fluidity and strength behavior of cemented tailings backfill with different solid contents. Constr. Build. Mater. 2018, 187, 290–298. [Google Scholar] [CrossRef]
- Zhang, J.; Deng, H.; Taheri, A.; Deng, J.; Ke, B. Effects of Superplasticizer on the Hydration, Consistency, and Strength Development of Cemented Paste Backfill. Minerals 2018, 8, 381. [Google Scholar] [CrossRef] [Green Version]
- Zeyad, A.M.; Almalki, A. Influence of mixing time and superplasticizer dosage on self-consolidating concrete properties. J. Mater. Res. Technol. 2020, 9, 6101–6115. [Google Scholar] [CrossRef]
Parameter | Unit | Type | Mean | Minimum | Maximum | Range | SD |
---|---|---|---|---|---|---|---|
Cement | Input | 265.4 | 102.0 | 540.0 | 438.0 | 104.7 | |
Water | Input | 183.1 | 121.8 | 247.0 | 125.2 | 19.3 | |
Coarse aggregate | Input | 956.1 | 801.0 | 1145.0 | 344.0 | 83.8 | |
Fine aggregate | Input | 764.4 | 594.0 | 992.6 | 398.6 | 73.1 | |
Blast furnace slag | Input | 86.3 | 0.0 | 359.4 | 359.4 | 87.8 | |
Superplasticizer | Input | 7.0 | 0.0 | 32.2 | 32.2 | 5.4 | |
Fly ash | Input | 62.8 | 0.0 | 200.1 | 200.1 | 66.2 | |
Age | days | Input | 45.7 | 1.0 | 365.0 | 364.0 | 63.1 |
Compressive strength | Output | 35.8 | 2.33 | 82.6 | 80.27 | 16.7 |
Hyper-Parameters | Explanation | Type | Tuning Range | Dataset 1 | Dataset 2 |
---|---|---|---|---|---|
Max_depth | The maximum depth of each DT | Integer | 1–15 | 15 | 15 |
Number_DT | The number of DTs in the forest | Integer | 50–2000 | 1457 | 356 |
Min_samples_split | The minimum number of samples required to split an internal node | Integer | 2–15 | 2 | 2 |
Min_samples_leaf | The minimum number of samples at the leaf node | Integer | 1–15 | 1 | 1 |
Max_features | The number of features to be used when looking for the best split. | Float | 0.4–1 | 0.466 | 0.978 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Qi, C.; Huang, B.; Wu, M.; Wang, K.; Yang, S.; Li, G. Concrete Strength Prediction Using Different Machine Learning Processes: Effect of Slag, Fly Ash and Superplasticizer. Materials 2022, 15, 5369. https://doi.org/10.3390/ma15155369
Qi C, Huang B, Wu M, Wang K, Yang S, Li G. Concrete Strength Prediction Using Different Machine Learning Processes: Effect of Slag, Fly Ash and Superplasticizer. Materials. 2022; 15(15):5369. https://doi.org/10.3390/ma15155369
Chicago/Turabian StyleQi, Chongchong, Binhan Huang, Mengting Wu, Kun Wang, Shan Yang, and Guichen Li. 2022. "Concrete Strength Prediction Using Different Machine Learning Processes: Effect of Slag, Fly Ash and Superplasticizer" Materials 15, no. 15: 5369. https://doi.org/10.3390/ma15155369
APA StyleQi, C., Huang, B., Wu, M., Wang, K., Yang, S., & Li, G. (2022). Concrete Strength Prediction Using Different Machine Learning Processes: Effect of Slag, Fly Ash and Superplasticizer. Materials, 15(15), 5369. https://doi.org/10.3390/ma15155369