Computers and Concrete

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Predicting strength development of RMSM using ultrasonic pulse velocity and artificial neural network

  • Sheen, Nain Y. (Department of Civil Engineering, National Kaohsiung University of Applied Sciences) ;
  • Huang, Jeng L. (Department of Civil Engineering, National Kaohsiung University of Applied Sciences) ;
  • Le, Hien D. (Department of Civil Engineering, National Kaohsiung University of Applied Sciences)
  • Received : 2012.10.04
  • Accepted : 2013.08.31
  • Published : 2013.12.25
⟨ Previous Next ⟩

Abstract

Ready-mixed soil material, known as a kind of controlled low-strength material, is a new way of soil cement combination. It can be used as backfill materials. In this paper, artificial neural network and nonlinear regression approach were applied to predict the compressive strength of ready-mixed soil material containing Portland cement, slag, sand, and soil in mixture. The data used for analyzing were obtained from our testing program. In the experiment, we carried out a mix design with three proportions of sand to soil (e.g., 6:4, 5:5, and 4:6). In addition, blast furnace slag partially replaced cement to improve workability, whereas the water-to-binder ratio was fixed. Testing was conducted on samples to estimate its engineering properties as per ASTM such as flowability, strength, and pulse velocity. Based on testing data, the empirical pulse velocity-strength correlation was established by regression method. Next, three topologies of neural network were developed to predict the strength, namely ANN-I, ANN-II, and ANN-III. The first two models are back-propagation feed-forward networks, and the other one is radial basis neural network. The results show that the compressive strength of ready-mixed soil material can be well-predicted from neural networks. Among all currently proposed neural network models, the ANN-I gives the best prediction because it is closest to the actual strength. Moreover, considering combination of pulse velocity and other factors, viz. curing time, and material contents in mixture, the proposed neural networks offer better evaluation than interpolated from pulse velocity only.

Keywords

Acknowledgement

Supported by : National Science Council

References

  1. ACI Committee 229 (2005), Controlled Low-Strength Materials, American Concrete Institute, Farmington Hills, MI, USA.
  2. Alshihri, M.M. and Azmy, A.M. (2009), "Neural networks for predicting compressive strength of structural light weight concrete", J. Construct. Build Mater., 23, 2214-2219. https://doi.org/10.1016/j.conbuildmat.2008.12.003
  3. Arafa, M., Alqedra, M. and An-Najjar, H. (2011), "Neural network model for predicting shear strength of reinforced normal and high-strength concrete deep beams", J. Appl. Sci., 11(2), 266-274. https://doi.org/10.3923/jas.2011.266.274
  4. ASTM C150 (2002), Standard specification for Portland cement.
  5. ASTM C33 (2003), Standard specification for concrete aggregates.
  6. ASTM C597 (2009), Standard test method for pulse velocity through concrete.
  7. ASTM D4832 (2002), Standard test method for preparation and testing of controlled low strength material (CLSM) test cylinders.
  8. ASTM D6103 (1997), Standard test method for flow consistency of controlled low strength material.
  9. Beale, M.H., Hagan, M.T. and Demuth, H.B. (2012), Neural network toolbox user's guide, Mathworks.
  10. Bilgehan, M. and Turgut, P. (2010), "The use of neural networks in concrete compressive strength estimation", J. Comput. Concr., 7(3), 271-283. https://doi.org/10.12989/cac.2010.7.3.271
  11. Bouikni, A., Swamy, R.N. and Bali, A. (2009), "Durability properties of concrete containing 50% and 65% slag", J. Construct. Build Mater., 23, 2836-2845. https://doi.org/10.1016/j.conbuildmat.2009.02.040
  12. Chen, J.W. and Chang, C.F. (2006), "Development and application of the ready-mixed soil material", J. Mater. Civil Eng., 18(6), 792-799. https://doi.org/10.1061/(ASCE)0899-1561(2006)18:6(792)
  13. Das, B.M. (2007), Principles of Geotechnical Engineering, (7th Edition), Cengage Learning.
  14. Finney, A.J., Shorey, E.F. and Anderson, J. (2008), "Use of native soil in place of aggregate in controlled low strength material (CLSM)", International Pipelines Conference 2008, Atlanta, United States, 1-13.
  15. Green, B.H. (1999), Development of soil-based controlled low-strength materials. Technical report INP-SL-2, prepared for U.S. Army Corps of Engineers.
  16. Gunaydin, O., Gokoglu, A. and Fener, M. (2010), "Prediction of artificial soil's unconfined compression strength test using statistical analyses and artificial neural networks", J. Adv. Eng. Softw., (41), 1115-1123. https://doi.org/10.1016/j.advengsoft.2010.06.008
  17. Haykin, S. (1999), Neural networks, a comprehensive foundation, (2nd Edition), Prentice Hall.
  18. Jaksa, M.B. and Maier, H.R. (2008), "Future challenges for artificial neural network modeling in geotechnical engineering", The 12th International Conference of International Association for Computer Methods and Advances in Geomechanics (IACMAG), India.
  19. Kawalramani, M.A. and Gupta, R. (2006), "Concrete compressive strength prediction using ultrasonic pulse velocity through artificial neuron networks", J. Automat. Construct., 15, 374-379. https://doi.org/10.1016/j.autcon.2005.07.003
  20. Lachemi, M., Sahmaran, M., Hossain, K.M.A., Lotfy, A. and Shehata, M. (2010), "Properties of controlled low-strength materials incorporating cement kiln dust and slag", J. Cement Concrete Compos., 32(8), 623-629. https://doi.org/10.1016/j.cemconcomp.2010.07.011
  21. Muhmood, L., Vitta, S. and Venkateswaran, D. (2009), "Cementitious and pozzolanic behavior of electric arc furnace steel slags", J. Cement Concrete Res., 39, 102-109. https://doi.org/10.1016/j.cemconres.2008.11.002
  22. Oztekin, E. and Ozgan, K. (2012), "Analysis of thick plates on elastic foundation by back-propagation artificial neural network using one parameter foundation model", J. Eng. Appl. Sci., 4(1), 66-76.
  23. Oztekin, E. (2012), "Prediction of confined compressive strength of square concrete columns by artificial neural networks", J. Eng. Appl. Sci., 4(3), 17-35.
  24. Samarasinghe, S. (2007), Neural Networks for Applied Sciences and Engineering, Auerbach Publications.
  25. Saridemir, M. (2009), "Prediction of compressive strength of concretes containing meta-kaolin and silica fume by artificial neural networks", J. Adv. Eng. Softw., 40, 350-355. https://doi.org/10.1016/j.advengsoft.2008.05.002
  26. Sazli, M.H. (2006), "A brief review of feed-forward neural network", Commun. Fac. Sci. Univ. Ank, Series A2-A3, 50(1), 11-17.
  27. Shah, A.A., Alsayed, S.H., Abbas, H.Y. and Al-Salloum, A. (2012), "Predicting residual strength of non-linear ultrasonically evaluated damaged concrete using artificial neural network", J. Construct. Build. Mater., 29, 42-50. https://doi.org/10.1016/j.conbuildmat.2011.10.038
  28. Sheen, Y.N., Huang, L.J., Le, D.H. and Zhang, L.H. (2012), "Application of artificial neural networks in predicting concrete compressive strength from pulse velocity tests", The Eleventh National Conference on Structural Engineering, Taiwan, September.
  29. Taha, R.A., Alnuaimi, A.S., Al-Jabri, K.S. and Al-Harthy, A.S. (2007), "Evaluation of controlled low strength materials containing industrial by-products", J. Build Environ., 42, 3366-3372. https://doi.org/10.1016/j.buildenv.2006.07.028
  30. Trtnik, G., Kavcic, F. and Turk, G. (2009), "Prediction of concrete strength using ultrasonic pulse velocity and artificial neural networks", J. Ultrasonic, 49, 53-60. https://doi.org/10.1016/j.ultras.2008.05.001
  31. Wang, H.Y. and Tsai, K.C. (2006), "Engineering properties of lightweight aggregate concrete made from dredged silt", J. Cement Concrete Compos., 28, 481-485. https://doi.org/10.1016/j.cemconcomp.2005.12.005
  32. Wu, J.Y. (2005), "Soil-based flowable fill for pipeline construction", ASCE, Proceedings of Pipelines 2005: Optimizing Pipeline Design, Operations, and Maintenance in Today's Economy, Houston, Texas, USA.
  33. Wu, J.Y. and Lee, M.Z. (2011), "Beneficial reuse of construction surplus clay in CLSM", Int. J. Pavement Res. Technol., 4(5), 293-300.
  34. Wu, J.Y. and Lin, Y.J. (2011), "Experimental study of reservoir siltation as CLSM for backfill applications", Proceeding of Geo-Frontiers, Texas, March, 1217-1226.
  35. Wu, J.Y. and Tsai, M. (2009), "Feasibility study of a soil-based rubberized CLSM", J. Waste Manag., 29, 636-642. https://doi.org/10.1016/j.wasman.2008.06.017
  36. Wu, Y. and Wang, H. (2012), Using Radial Basis Function Networks for Function Approximation and Classification, International Scholarly Research Network, ISRN Applied Mathematics, Article ID 324194, 34 pages.
  37. Yilmaz, I. and Kaynar, O. (2011), "Multi regression ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils", J. Exp. Syst. Appl., 38, 5958-5966. https://doi.org/10.1016/j.eswa.2010.11.027

Cited by

  1. Feed-Forward Neural Network Prediction of the Mechanical Properties of Sandcrete Materials vol.17, pp.6, 2017, https://doi.org/10.3390/s17061344
  2. Prediction of Hybrid fibre-added concrete strength using artificial neural networks vol.15, pp.4, 2015, https://doi.org/10.12989/cac.2015.15.4.503
  3. Guided wave analysis of air-coupled impact-echo in concrete slab vol.20, pp.3, 2017, https://doi.org/10.12989/cac.2017.20.3.257
  4. Artificial neural networks applied for solidified soils data prediction: a bibliometric and systematic review vol.38, pp.7, 2013, https://doi.org/10.1108/ec-10-2020-0576