International Journal of Smart Energy Technology and Environmental Engineering

Behavior Analysis of High-Performance Concrete Using Data Mining Techniques

Document Type : Original Article

Authors

1 Independent Researcher, Imperial College Business School, Toronto, Canada

2 Assistant Professor, Department of Mechanical Engineering, Islamic Azad University, Tehran, IRAN

Abstract

This study tried to predict mechanical behavior of high-performance concrete (HPC), specially the compressive strength of HPC using different data mining methods. HPC is a highly complex composite material and modelling of its dynamics is a real challenge. Moreover, compressive strength of HPC is nonlinear function of its ingredients. The results of several studies have represented that compressive strength of HPC depends on not only water/cement ratio but also some other additive ingredients. It is actually a function of cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate and age. The quantitative analysis in this study were conducted by using Principal components analysis (PCA) and Multiple Regression (MR) methods. For this purpose, some effective statistical analysis and modeling software such as MATLAB, MINITAB and R has been used. Analytical results suggested that Multiple Regression is effective for predicting behavior of HPC based on its compressive strength with respect to different ages.

Keywords

  1. Oh, J., Lee, I., Kim, J., and Lee, G. (1999). “Applications of neural networks for proportioning of concrete mixes.” ACI Mater. J., 96(1), 51–59.
  2. Mostofi, D., and Samaee, A. (1995). “HPC strength prediction using artificial neural network.” J. Comput. Civ. Eng., 9(4), 44–49.
  3. Naresh Kumar Nagwani and Shirish V. Deo, ‘’ Estimating the Concrete Compressive Strength Using Hard Clustering and Fuzzy Clustering Based Regression Techniques,’’ National Institute of Technology Raipur, Raipur, Chhattisgarh 492010, India, Hindawi Publishing Corporation, The Scientific World Journal, Volum2014, Article ID 381549.
  4. Jui-Sheng Chou, “Concrete compressive strength analysis using a combined classification and regression technique,” Department of Construction Engineering, National Taiwan University of Science and Technology, 43 Sec.4, Keelung Road, Taipei, Taiwan, Automation in Construction 24 (2012) 52–60
  5. -C. Yeh, “MODELING OF STRENGTH OF HIGH-PERFORMANCE CONCRETE USING  ARTIFICIAL  NEURAL  NETWORKS,” Department of Civil Engineering, Chung-Hua University, 30 Tung Shiang, Hsin Chu, 30067, Taiwan, Republic of China, Received July 3, 1998; in final form September 14, 1998.
  6. F. M. Zain, Suhad M. Abd, K. Sopian, M. Jamil1 , Che-Ani A.I, “Mathematical Regression Model for the Prediction of Concrete Strength,” Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor Darul Ehsan, Malaysia
  7. F.M Zain and S.M.Abd, “Multiple Regression Model for Compressive Strength Prediction of High Performance Concrete,” Department of Civil Engineering, Diyala University, Iraq, Journal of Applied Science 9(1):155-160, 2009.
  8. Atici, “Prediction of the strength of mineral admixture concrete using multivariable regression analysis and an artificial neural network,” Engineering Faculty, Nigde University, Nigde 51245, Turkey, Expert Systems with Applications 38 (2011) 9609–9618.
  9. Kasperkiewicz, J., and Dubrawski, A. (1995). “HPC strength prediction using artificial neural network.” J. Comput. Civ. Eng., 9(4), 279–284.
  10. Kasperkiewicz, J., and Dubrawski, A. (1995). “HPC strength prediction using artificial neural network.” J. Comput. Civ. Eng., 9(4), 279–284.
  11. Fazel Zarandi, M. H., Türksen, I. B., Sobhani, J., and Ramezanianpour, (2008). “Fuzzy polynomial neural networks for approximation of the compressive strength of concrete.” Appl. Soft Comput., 8(1), 488–498.
  12. Trtnik, G., Kavcic, F., and Turk, G. (2009). “Prediction of concrete strength using ultrasonic pulse velocity and artificial neural networks.” Ultrasonics, 49(1), 53–60.
  13. Gupta, R., Kewalramani, M. A., and Goel, A. (2006). “Prediction of concrete strength using neural-expert system.” J. Mater. Civ. Eng.,18(3), 462–466.
  14. Amir Hossein Alavi Amir Hossein Gandomi,"A robust data mining approach for formulation of geotechnical engineering systems", Engineering Computations, Vol. 28 Iss 3 pp. 242 – 274, 2011
  15. Mehrnoosh Ebrahimi, and Ali Akbar Niknafs, “Increasing Cement Strength Using Data Mining Techniques,” International Conference Data Mining, Civil and Mechanical Engineering (ICDMCME’2015) Feb. 1- 2,Bali, Indonesia,2015
  16. Jui-Sheng Chou, Chih-Fong Tsai, “Concrete compressive strength analysis using a combined classification and Regression technique,” Department of Construction Engineering, National Taiwan University of Science and Technology, 43 Sec.4, Keelung Road, Taipei, Taiwan, Automation in Construction 24 (2012)
  17. Ramin Hosseini Kupaei, U. Johnson Alengaram, and Mohd Zamin Jumaat, “The Effect of Different Parameters on the Development of Compressive Strength of Oil Palm Shell Geopolymer Concrete,” Department of Civil Engineering, Faculty of Engineering, University of Malaya, 50603 Kuala Lumpur, Malaysia, Received 1 July 2014; Accepted 27 August 2014; Published 28 October 2014
  18. Jui-Sheng Chou, Chien-Kuo Chiu, Mahmoud Farfoura, Ismail Al- Taharwa, “Optimizing the Prediction Accuracy of Concrete Compressive Strength Based on a Comparison of Data-Mining Techniques,” JOURNAL OF COMPUTING IN CIVIL ENGINEERING © ASCE / MAY/JUNE 2011 / 253
  19. Rakesh A. More* and Prof. S.K. Dubey, “Effect of Different Types of Water on Compressive Strength of Concrete,” International Journal on Emerging Technologies 5(2): 40-50(2014)
International Journal of Smart Energy Technology and Environmental Engineering
Volume 2, Issue 2 - Serial Number 4
September 2023
Pages 154-174
  • Receive Date: 05 May 2023
  • Revise Date: 14 May 2023
  • Accept Date: 15 May 2023