Journal of the Computational Structural Engineering Institute of Korea (한국전산구조공학회논문집)

Computational Structural Engineering Institute of Korea (한국전산구조공학회)
권호 표지
DOI QR코드

DOI QR Code

Development of a High-Performance Concrete Compressive-Strength Prediction Model Using an Ensemble Machine-Learning Method Based on Bagging and Stacking

배깅 및 스태킹 기반 앙상블 기계학습법을 이용한 고성능 콘크리트 압축강도 예측모델 개발

  • Yun-Ji Kwak (Department of Civil & Environmental Engineering, Hanbat National University) ;
  • Chaeyeon Go (Department of Civil & Environmental Engineering, Hanbat National University) ;
  • Shinyoung Kwag (Department of Civil & Environmental Engineering, Hanbat National University) ;
  • Seunghyun Eem (Department of Convergence and Fusion System Engineering, Kyungpook National University)
  • 곽윤지 (국립 한밭대학교 건설환경공학과) ;
  • 고채연 (국립 한밭대학교 건설환경공학과) ;
  • 곽신영 (국립 한밭대학교 건설환경공학과 ) ;
  • 임승현 (경북대학교 융복합시스템공학과 플랜트시스템전공 )
  • Received : 2022.08.11
  • Accepted : 2022.12.27
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Predicting the compressive strength of high-performance concrete (HPC) is challenging because of the use of additional cementitious materials; thus, the development of improved predictive models is essential. The purpose of this study was to develop an HPC compressive-strength prediction model using an ensemble machine-learning method of combined bagging and stacking techniques. The result is a new ensemble technique that integrates the existing ensemble methods of bagging and stacking to solve the problems of a single machine-learning model and improve the prediction performance of the model. The nonlinear regression, support vector machine, artificial neural network, and Gaussian process regression approaches were used as single machine-learning methods and bagging and stacking techniques as ensemble machine-learning methods. As a result, the model of the proposed method showed improved accuracy results compared with single machine-learning models, an individual bagging technique model, and a stacking technique model. This was confirmed through a comparison of four representative performance indicators, verifying the effectiveness of the method.

고성능 콘크리트(HPC) 압축강도는 추가적인 시멘트질 재료의 사용으로 인해 예측하기 어렵고, 개선된 예측 모델의 개발이 필수적이다. 따라서, 본 연구의 목적은 배깅과 스태킹을 결합한 앙상블 기법을 사용하여 HPC 압축강도 예측 모델을 개발하는 것이다. 이 논문의 핵심적 기여는 기존 앙상블 기법인 배깅과 스태킹을 통합하여 새로운 앙상블 기법을 제시하고, 단일 기계학습 모델의 문제점을 해결하여 모델 예측 성능을 높이고자 한다. 단일 기계학습법으로 비선형 회귀분석, 서포트 벡터 머신, 인공신경망, 가우시안 프로세스 회귀를 사용하고, 앙상블 기법으로 배깅, 스태킹을 이용하였다. 결과적으로 본 연구에서 제안된 모델이 단일 기계학습 모델, 배깅 및 스태킹 모델보다 높은 정확도를 보였다. 이는 대표적인 4가지 성능 지표 비교를 통해 확인하였고, 제안된 방법의 유효성을 검증하였다.

Keywords

Acknowledgement

이 논문은 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원(No. RS-2022-00144328)을 받아 수행되었습니다.

References

  1. Ahmad, S., Alghamdi, S.A. (2014) A Statistical approach to Optimizing Concrete Mixture Design, The Scientific World J., 2014.
  2. Alpaydin, E. (2020) Introduction to Machine Learning, MIT Press, p.683.
  3. Apostolopoulou, M., Armaghani, D.J., Bakolas, A., Douvika, M. G., Moropoulou, A., Asteris, P.G. (2019) Compressive Strength of Natural Hydraulic Lime Mortars using Soft Computing Techniques, Procedia Struct. Integr., 17, pp.914~923. https://doi.org/10.1016/j.prostr.2019.08.122
  4. Asteris, P.G., Kolovos, K.G., Douvika, M.G., Roinos, K. (2016) Prediction of Self-Compacting Concrete Strength using Artificial Neural Networks, Eur. J. Environ. & Civil Eng., 20(sup1), pp.s102~s122. https://doi.org/10.1080/19648189.2016.1246693
  5. Asteris, P.G., Mokos, V.G. (2020) Concrete Compressive Strength using Artificial Neural Networks, Neural Comput. & Appl., 32(15), pp.11807~11826. https://doi.org/10.1007/s00521-019-04663-2
  6. Asteris, P.G., Skentou, A.D., Bardhan, A., Samui, P., Pilakoutas, K. (2021) Predicting Concrete Compressive Strength using Hybrid Ensembling of Surrogate Machine Learning Models, Cement & Concr. Res., 145, 106449.
  7. Atici, U. (2011) Prediction of the Strength of Mineral Admixture Concrete using Multivariable Regression Analysis and an Artificial Neural Network, Expert Syst. with Appl., 38(8), pp.9609~9618. https://doi.org/10.1016/j.eswa.2011.01.156
  8. Breiman, L. (1996) Bagging Predictors, Mach. Learn., 24(2), pp.123~140.
  9. Burges, C.J. (1998) A Tutorial on Support Vector Machines for Pattern Recognition, Data Min. & Knowl. Discov., 2(2), pp. 121~167. https://doi.org/10.1023/A:1009715923555
  10. Cheng, M.Y., Chou, J.S., Roy, A.F., Wu, Y.W. (2012) High-Performance Concrete Compressive Strength Prediction using Time-Weighted Evolutionary Fuzzy Support Vector Machines Inference Model, Automat. Constr., 28, pp.106~115. https://doi.org/10.1016/j.autcon.2012.07.004
  11. Chou, J.S., Chiu, C.K ., Farfoura, M., Al-Taharwa, I. (2011) Optimizing the Prediction Accuracy of Concrete Compressive Strength based on a Comparison of Data-Mining Techniques, J. Comput. Civil Eng., 25(3), pp.242~253. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000088
  12. Gartner, E. (2004) Industrially Interesting Approaches to "low-CO2" Cements, Cem. & Concr. Res., 34(9), pp.1489~1498. https://doi.org/10.1016/j.cemconres.2004.01.021
  13. Jerath, S. (1983) Computer-aided Concrete Mix Proportioning, J. Proc., 80(4), pp.312~317.
  14. Juenger, M.C.G., Winnefeld, F., Provis, J.L., Ideker, J.H. (2011) Advances in Alternative Cementitious Binders, Cem. & Concr. Res., 41(12), pp.1232~1243. https://doi.org/10.1016/j.cemconres.2010.11.012
  15. Kasperkiewicz, J., Racz, J., Dubrawski, A. (1995) HPC Strength Prediction using Artificial Neural Network, J. Comput. Civil Eng., 9(4), pp.279~284. https://doi.org/10.1061/(ASCE)0887-3801(1995)9:4(279)
  16. Kwag, S., Gupta, A., Dinh, N. (2018) Probabilistic Risk Assessment based Model Validation Method using Bayesian Network, Reliab. Eng. & Syst. Safety, 169, pp.380~393. https://doi.org/10.1016/j.ress.2017.09.013
  17. Lam, L., Wong, Y.L., Poon, C.S. (1998) Effect of Fly Ash and Silica Fume on Compressive and Fracture behaviors of Concrete, Cem. & Concr. Res., 28(2), pp.271~283. https://doi.org/10.1016/S0008-8846(97)00269-X
  18. McClelland, J.L., Rumelhart, D.E., Hinton, G.E. (1986) The Appeal of Parallel Distributed Processing, MIT Press, Cambridge MA, 3, 44.
  19. Neshat, M., Adeli, A., Sepidnam, G., Sargolzaei, M. (2012) Predication of Concrete Mix Design using Adaptive Neural Fuzzy Inference Systems and Fuzzy Inference Systems, Int. J.
  20. Adv. Manuf. Technol., 63(1), pp.373~390. Ozbay, E., Gesoglu, M., Guneyisi, E. (2011) Transport Properties Based Multi-Objective Mix Proportioning Optimization of High Performance Concretes, Mater. & Struct., 44(1), pp. 139~154. https://doi.org/10.1617/s11527-010-9615-7
  21. Oztas, A., Pala, M., Ozbay, E., Kanca, E., Caglar, N., Bhatti, M. A. (2006) Predicting the Compressive Strength and Slump of High Strength Concrete using Neural Network, Constr. & Build. Mater., 20(9), pp.769~775. https://doi.org/10.1016/j.conbuildmat.2005.01.054
  22. Rasmussen, C.E. (2003) Summer School on Machine Learning, Gaussian Processes in Machine Learning, Springer, Berlin, Heidelberg. pp.63~71.
  23. Rutkowska, G., Wichowski, P., Franus, M., Mendryk, M., Fronczyk, J. (2020) Modification of Ordinary Concrete using Fly Ash from Combustion of Municipal Sewage Sludge, Mater., 13(2), 487.
  24. Sun, L., Koopialipoor, M., Jahed Armaghani, D., Tarinejad, R., Tahir, M.M. (2021) Applying a Meta-Heuristic Algorithm to Predict and Optimize Compressive Strength of Concrete Samples, Eng. Comput., 37(2), pp.1133~1145. https://doi.org/10.1007/s00366-019-00875-1
  25. Syarif, I., Zaluska, E., Prugel-Bennett, A., Wills, G. (2012) Application of Bagging, Boosting and Stacking to Intrusion Detection, In International Workshop on Machine Learning and Data Mining in Pattern Recognition, Springer, Berlin, Heidelberg, pp.593~602.
  26. Yeh, I.C. (1998) Modeling of Strength of High-Performance Concrete using Artificial Neural Networks, Cem. & Concr. Res., 28(12), pp.1797~1808. https://doi.org/10.1016/S0008-8846(98)00165-3
  27. Yilmaz, I., Erik, N.Y., Kaynar, O. (2010) Different Types of Learning Algorithms of Artificial Neural Network (ANN) Models for Prediction of Gross Calorific Value (GCV) of Coals, Sci. Res. & Essays, 5(16), pp.2242~2249.
  28. Zain, F.M., Abd, M.S. (2009) Multiple Regression Model for Compressive Strength Prediction of High Performance Concrete, J. Appl. Sci., 9(1), pp.155~160. https://doi.org/10.3923/jas.2009.155.160
  29. Zhang, J., Huang, Y., Wang, Y., Ma, G. (2020) Multi-Objective Optimization of Concrete Mixture Proportions using Machine Learning and Metaheuristic Algorithms, Constr. & Build. Mater., 253, 119208.