RF Optimizer Model for Predicting Compressive Strength of Recycled Concrete

Abstract

Traditional machine learning (ML) encounters the challenge of parameter adjustment when predicting the compressive strength of reclaimed concrete. To address this issue, we introduce two optimized hybrid models: the Bayesian optimization model (B-RF) and the optimal model (Stacking model). These models are applied to a data set comprising 438 observations with five input variables, with the aim of predicting the compressive strength of reclaimed concrete. Furthermore, we evaluate the performance of the optimized models in comparison to traditional machine learning models, such as support vector regression (SVR), decision tree (DT), and random forest (RF). The results reveal that the Stacking model exhibits superior predictive performance, with evaluation indices including R ²=0.825, MAE=2.818 and MSE=14.265, surpassing the traditional models. Moreover, we also performed a characteristic importance analysis on the input variables, and we concluded that cement had the greatest influence on the compressive strength of reclaimed concrete, followed by water. Therefore, the Stacking model can be recommended as a compressive strength prediction tool to partially replace laboratory compressive strength testing, resulting in time and cost savings.

References

[1] Farooq F, Ahmed W, Akbar A, et al.. Predictive Modeling for Sustainable High-Performance Concrete from Industrial Wastes: A Comparison and Optimization of Models Using Ensemble Learners[J]. Journal of Cleaner Production, 2021, 292: 126 032

[2] Wang X, Liu W, Wei D, et al.. A Simple Mix Proportion Design Method Based on Frost Durability for Recycled High Performance Concrete Using Fully Coarse Recycled Aggregate[J]. Journal of Wuhan University of Technology-Mater. Sci. Ed., 2017, 32(5): 1 119-1 124

[3] Wu J, Zhang Y, Zhu P, et al.. Mechanical Properties and ITZ Microstructure of Recycled Aggregate Concrete Using Carbonated Recycled Coarse Aggregate[J]. Journal of Wuhan University of Technology-Mater. Sci. Ed., 2018, 33(3): 648-653

[4] Guo H, Shi C, Guan X, et al.. Durability of Recycled Aggregate Con-crete-A Review[J]. Cement and Concrete Composites, 2018, 89: 251259

[5] Shi C, Li Y, Zhang J, et al.. Performance Enhancement of Recycled Concrete Aggregate-A Review[J]. Journal of Cleaner Production, 2016, 112: 466-472

[6] Wang J, Yang S, Liu F, et al.. Prediction of Early Crack Resistance of Concrete Based on Random Forest Algorithm[J]. Journal of Xinyang Normal University (Natural Science Edition), 2021, 34(01): 158-165

[7] Cao F, Zhou M, Wang C, et al.. An Improved Support Vector Regression Method for Concrete Strength Prediction[J]. Bulletin of the Chinese Ceramic Society, 2021, 40(01): 90-97

[8] Tang F, Wu Y, Zhou Y. Hybridizing Grid Search and Support Vector Regression to Predict the Compressive Strength of Fly Ash Con-crete[J]. Advances in Civil Engineering, 2022(1): 3 601 914

[9] Azimi-Pour M, Eskandari-Naddaf H, Pakzad A. Linear and Non-Linear SVM Prediction for Fresh Properties and Compressive Strength of High Volume Fly Ash Self-Compacting Concrete[J]. Construction and Building Materials, 2020, 230: 117 021.1-117 021.15

[10] Al-Shamiri A K, Kim J H, Yuan T F, et al.. Modeling the Compres-sive Strength of High-Strength Concrete: An Extreme Learning Ap-proach[J]. Construction and Building Materials, 2019, 208: 204-219

[11] Zhang J, Kang Z, Zhang Y. Prediction of Compressive Strength of Recycled Concrete Based on BP Neural Network[J]. Jiangsu Construction, 2022(05): 84–88

[12] Luo Y, Li X, Liang Y, et al. Superiority Analysis of Recycled Concrete Strength Prediction Model Based on Bayesian Theory[J]. Sichuan Cement, 2023(01): 17–19

[13] Ling H, Qian C, Kang W, et al.. Combination of Support Vector Machine and K-Fold Cross Validation to Predict Compressive Strength of Concrete in Marine Environment[J]. Construction and Building Materials, 2019, 206: 355-363

[14] Luo W, Wang H, Gan K, et al.. Research on Forecast Method about the Compressive Strength of Recycled Concrete[J]. Shanxi Architecture, 2021, 47(20): 128-130

[15] Zheng C, Lou C, Du G, et al.. Mechanical Properties of Recycled Concrete with Demolished Waste Concrete Aggregate and Clay Brick Aggregate[J]. Results in Physics, 2018, 9: 1 317-1 322

[16] Liao X, Huang X, Shi J, et al.. Forecast Model about Compressive Strength of Recycled Aggregate Concrete Based on BP Neutral Net-work[J]. Journal of Nanjing Forestry University (Natural Science Edition), 2010, 34(05): 105-108

[17] Thomas C, Sosa I, Setien J, et al.. Evaluation of the Fatigue Behavior of Recycled Aggregate Concrete[J]. Journal of Cleaner Production, 2014, 65: 397-405

[18] Huo H, Fan C, Chen A, et al. Influences of Recycled Aggregate with Different Strength on Recycled Concrete[J]. Concrete, 2017(02): 60–62

[19] Zhang L. Experimental Investigation on Meterial Properties of Recycled Aggregate Concrete, 2009, Hefei, Hefei University of Technology [D]

[20] Xu X. Research on Mixture Ratio Design and Physical and Mechanical Properties of Recycled Concrete, 2015, Nanning, Guangxi University of Science and Technology [D]

[21] Gao W. Influencing Factors and Deep Learning Prediction Model of Compression Strength of Recycled Concrete[J]. Concrete, 2018(11): 58–61

[22] Zhang H, Zheng J. Influencing Factors on Compressive Strength and Working Properties of Recycled Concrete[J]. Journal of Fuzhou University (Natural Science Edition), 2012, 40(04): 508-514

[23] Wang J, Zheng C, Jin B, et al.. Effect of Fly Ash / Different Aggregates on the Mechanical Properties of Fiber Reinforced Self-Compacting Recycled Concrete[J]. Journal of Functional Materials, 2022, 53(09): 9 209-9 218

[24] Gayarre F L, Perez L C, Lopez M A S, et al.. The Effect of Curing Conditions on the Compressive Strength of Recycled Aggregate Con-crete[J]. Construction & Building Materials, 2014, 53: 260-266

[25] Huang Y. Research on Action Mechanism of Recycled Aggregate on Concrete Structure Durability, 2012, Nanning, Guangxi University [D]

[26] Wu L. Experimental Analysis and Study of Axial Compressive Strength of Recycled Concrete Cubes[J]. Engineering Technology Research, 2018 (06): 20–21

[27] Zeng Y, Cheng M, Yang H, et al.. Experimental Analysis on Influence of Recycled Coarse Aggregate on Compressive Strength of Con-crete[J]. Journal of Foshan University (Natural Science Edition), 2021, 39(1): 8-12

[28] Andreu G, Miren E. Experimental Analysis of Properties of High Performance Recycled Aggregate Concrete[J]. Construction & Building Materials, 2014, 52: 227-235 feb.

[29] Duan H Z, Poon S C. Properties of Recycled Aggregate Concrete Made with Recycled Aggregates with Different Amounts of Old Adhered Mortars[J]. Materials & Design, 2014, 58(1): 19-29

[30] Guo Y, Liu Y, Wang W, et al. Prediction of Concrete Compressive Strength of Regenerated Thermal Insulation Concrete Based on BP Neural Network[J]. Concrete, 2018(10): 33–35

[31] Chen Y, Liu J, Wu H, et al.. Mechanical Properties and Strength Index Conversion of Recycled Aggregate Concrete under Direct Shear[J]. Journal of Composite Materials, 2021, 38(11): 3 962-3 970

[32] Kim K, Shin M, Cha S. Combined Effects of Recycled Aggregate and Fly Ash Towards Concrete Sustainability - ScienceDirect[J]. Construction and Building Materials, 2013, 48(19): 499-507

[33] Butler L, West J S, Tighe S L. Effect of Recycled Concrete Coarse Aggregate from Multiple Sources on the Hardened Properties of Concrete with Equivalent Compressive Strength[J]. Construction & Building Materials, 2013, 47: 1 292-1 301 oct.

[34] Wang G, Qi S, Li J, et al. Experimental Investigation on Mechanical Properties of Recycled Aggregate Concrete[J]. Concrete, 2020(3): 168171

[35] Xu Q, Ye L, You Y, et al.. Research on Basic Mechanical Properties of Recycled Aggregate Concrete[J]. Journal of Harbin University of Commerce (Natural Science Edition), 2020, 36(01): 65-72

[36] Ismail S, Ramli M. Engineering Properties of Treated Recycled Concrete Aggregate (RCA) for Structural Applications[J]. Construction & Building Materials, 2013, 44: 464-476

[37] Barbudo A, Brito J D, Evangelista L, et al.. Influence of Water-Reducing Admixtures on the Mechanical Performance of Recycled Con-crete[J]. Journal of Cleaner Production, 2013, 59: 93-98

[38] Hoffmann C, Schubert S, Leemann A, et al.. Recycled Concrete and Mixed Rubble as Aggregates: Influence of Variations in Composition on the Concrete Properties and Their Use as Structural Material[J]. Construction & Building Materials, 2012, 35: 701-709

[39] Zhang Y, Xu Y, Yao Z, et al.. Effect of Mix Design Method on Life Cycle Assessment of Recycled Aggregate Concrete[J]. Journal of Zhejiang University of Technology, 2020, 48(06): 648-653

[40] Kou S, Poon C, Etxeberria M. Influence of Recycled Aggregates on Long Term Mechanical Properties and Pore Size Distribution of Con-crete[J]. Cement and Concrete Composites, 2011, 33(2): 286-291

[41] Shi Z, Li Y. Experimental Study of Recycling Concrete and Its Application in Engineering[J]. Fly Ash, 2004, (04): 3–4

[42] Chen B. Experimental Study on the Preparation of Recycled Concrete from Recycled Coarse Aggregate from Waste Materials of Reconstruction Projects[J]. Sichuan Cement, 2023, (08): 23–24

[43] Gu L, Yang B. Preliminary Study on Mix Ratio Design and Engineering Application of Recycled Concrete from Construction Waste[J]. Engineering Construction and Design, 2021(19): 186–188

[44] Chaabene W B, Flah M, Nehdi M L. Machine Learning Prediction of Mechanical Properties of Concrete: Critical Review[J]. Construction and Building Materials, 2020, 260: 1-18

[45] Han B, Wu Y, Liu L. Prediction and Uncertainty Quantification of Compressive Strength of High-Strength Concrete Using Optimized Machine Learning Algorithms[J]. Structural Concrete, 2022: 1–14

[46] Nguyen M S T, Kim S E. A Hybrid Machine Learning Approach in Prediction and Uncertainty Quantification of Ultimate Compressive Strength of RCFST Columns[J]. Construction and Building Materials, 2021, 302: 124 208

RIGHTS & PERMISSIONS

Wuhan University of Technology and Springer-Verlag GmbH Germany, Part of Springer Nature