Geomechanics and Engineering

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Predicting unconfined compression strength and split tensile strength of soil-cement via artificial neural networks

  • Luis Pereira (University of Coimbra, ISISE, ARISE, Department of Civil Engineering) ;
  • Luis Godinho (University of Coimbra, ISISE, ARISE, Department of Civil Engineering) ;
  • Fernando G. Branco (University of Coimbra, ISISE, ARISE, Department of Civil Engineering)
  • Received : 2022.03.24
  • Accepted : 2023.05.11
  • Published : 2023.06.25
⟨ Previous Next ⟩

Abstract

Soil properties make it attractive as a building material due to its mechanical strength, aesthetically appearance, plasticity, and low cost. However, it is frequently necessary to improve and stabilize the soil mechanical properties with binders. Soil-cement is applied for purposes ranging from housing to dams, roads and foundations. Unconfined compression strength (UCS) and split tensile strength (CD) are essential mechanical parameters for ascertaining the aptitude of soil-cement for a given application. However, quantifying these parameters requires specimen preparation, testing, and several weeks. Methodologies that allowed accurate estimation of mechanical parameters in shorter time would represent an important advance in order to ensure shorter deliverable timeline and reduce the amount of laboratory work. In this work, an extensive campaign of UCS and CD tests was carried out in a sandy soil from the Leiria region (Portugal). Then, using the machine learning tool Neural Pattern Recognition of the MATLAB software, a prediction of these two parameters based on six input parameters was made. The results, especially those obtained with resource to a Bayesian regularization-backpropagation algorithm, are frankly positive, with a forecast success percentage over 90% and very low root mean square error (RMSE).

Keywords

Acknowledgement

This work was partly financed by FCT / MCTES through national funds (PIDDAC) under the R&D Unit Institute for Sustainability and Innovation in Structural Engineering (ISISE), under reference UIDB / 04029/2020, and under the Associate Laboratory Advanced Production and Intelligent Systems ARISE under reference LA/P/0112/2020. This work is financed by national funds through FCT - Foundation for Science and Technology, under grant agreement 2022.12096.BD attributed to the 1 st author.

References

  1. Abbaszadeh Shahri, A. (2016), "An optimized artificial neural network structure to predict clay sensitivity in a high landslide prone area using piezocone penetration test (CPTu) data: a case study in southwest of Sweden", Geotech. Geol. Eng., 34, 745-758. https://doi.org/10.1007/s10706-016-9976-y
  2. Armaghani, D.J., Mamou, A., Maraveas, C., Roussis, P.C., Siorikis, V.G., Skentou, A.D. and Asteris, P.G. (2021), "Predicting the unconfined compressive strength of granite using only two non-destructive test indexes", Geomech. Eng., 25(4), 317-330. https://doi.org/10.12989/gae.2021.25.4.317.
  3. Asteris, P.G. and Mokos, V.G. (2020), "Concrete compressive strength using artificial neural networks", Neural Comput. Appl., 32(15), 11807-11826. https://doi.org/10.1007/s00521-019-04663-2.
  4. ASTM. (2010), Standard practice for classification of soils for engineering purposes, Unified Soil Classification System (D2487-06). ASTM International, 06.
  5. Bejarbaneh, B.Y., Bejarbaneh, E.Y., Amin, M.F.M., Fahimifar, A., Jahed Armaghani, D. and Majid, M.Z.A. (2018), "Intelligent modelling of sandstone deformation behaviour using fuzzy logic and neural network systems", Bull. Eng. Geol. Environ., 77, 345-361. https://doi.org/10.1007/s10064-016-0983-2.
  6. Bunawan, A.R., Momeni, E., Armaghani, D.J., Nissa binti Mat Said, K. and Rashid, A.S.A. (2018), "Experimental and intelligent techniques to estimate bearing capacity of cohesive soft soils reinforced with soil-cement columns", Measurement: J. Int. Measurement Confederation, 124, 529-538. https://doi.org/10.1016/j.measurement.2018.04.057.
  7. Bunyamin, S.A., Ijimdiya, T S., Eberemu, A.O. and Osinubi, K.J. (2018), "Artificial neural networks prediction of compaction characteristics of black cotton soil stabilized with cement kiln dust", J. Soft Comput. Civil Eng., 2(3), 50-71.
  8. Burden, F. and Winkler, D. (2009), "Bayesian regularization of neural networks", Artif. Neural Networks: Method. Appl., 23-42.
  9. Consoli, N.C., Cruz, R.C., Floss, M.F. and Festugato, L. (2010), "Parameters controlling tensile and compressive strength of artificially cemented sand", J. Geotech. Geoenviron. Eng., 136(5), 759-763. https://doi.org/10.1061/(asce)gt.1943-5606.0000278.
  10. Correia, A.A.S., Venda Oliveira, P.J. and Lemos, L.J.L. (2013), "Prediction of the unconfined compressive strength in soft soil chemically stabilized", Proceedings of the 18th International Conference on Soil Mechanics and Geotechnical Engineering: Challenges and Innovations in Geotechnics, ICSMGE 2013.
  11. Dan Foresee, F. and Hagan, M.T. (1997), "Gauss-Newton approximation to bayesian learning", IEEE International Conference on Neural Networks - Conference Proceedings, 3, 1930-1935. https://doi.org/10.1109/ICNN.1997.614194
  12. Debnath, P. and Dey, A.K. (2017), "Prediction of laboratory peak shear stress along the cohesive soil-geosynthetic interface using artificial neural network", Geotech. Geol. Eng,, 35, 445-461. https://doi.org/10.1007/s10706-016-0119-2
  13. Erzin, Y. and Gul, T.O. (2013), "The use of neural networks for the prediction of the settlement of pad footings on cohesionless soils based on standard penetration test", Geomech. Eng., 5(6), 541-564. https://doi.org/10.12989/gae.2013.5.6.541.
  14. Flores, J.A. (2021), Focus on artificial neural networks. In Focus on Artificial Neural Networks. Nova Science Publishers.
  15. Gazzarrini, P., Kokan, M. and Jungaro, S. (2005), "Case History of Jet-Grouting in British Columbia. Underpinning of CN Rail Tunnel in North Vancouver", Geoteh. News -Vancouver, 23(4), 47.
  16. Gouravaraju, S., Narayan, J., Sauer, R.A. and Gautam, S.S. (2020), A bayesian regularization-backpropagation neural network model for peeling computations. arXiv 2020. ArXiv Preprint ArXiv:2006.16409.
  17. Hagan, M.T. and Menhaj, M.B. (1994), "Training feedforward networks with the marquardt algorithm", IEEE T. Neural Networ., 5(6), 989-993. https://doi.org/10.1109/72.329697
  18. Humphries, M.D. and Gurney, K.N. (1997), An introduction to neural networks (Routledge (Ed.)).
  19. ISO 13320-1. (1999), Particle Size Analysis-Laser Diffraction Methods-Part 1: General Principles.
  20. Jahed Armaghani, D., Tonnizam Mohamad, E., Momeni, E., Narayanasamy, M.S. and Mohd Amin, M.F. (2015), "An adaptive neuro-fuzzy inference system for predicting unconfined compressive strength and Young's modulus: a study on Main Range granite", Bull. Eng. Geol. Environ., 74(4), 1301-1319. https://doi.org/10.1007/s10064-014-0687-4.
  21. Javadi, A.A. and Rezania, M. (2009), "Applications of artificial intelligence and data mining techniques in soil modeling", Geomech. Eng., 1(1), 53-74. https://doi.org/10.12989/gae.2009.1.1.053.
  22. Jong, S.C., Ong, D.E.L. and Oh, E. (2021), "State-of-the-art review of geotechnical-driven artificial intelligence techniques in underground soil-structure interaction", Tunn. Undergr. Sp. Tech., 113. https://doi.org/10.1016/j.tust.2021.103946.
  23. Jong, S.C., Ong, D.E.L. and Oh, E. (2022), "A novel Bayesian inference method for predicting optimum strength gain in sustainable geomaterials for greener construction", Constr. Build. Mater., 344. https://doi.org/10.1016/j.conbuildmat.2022.128255.
  24. Kalogirou, S.A. (2000), "Artificial neural networks in renewable energy systems applications: A review", Renew. Sust. Energ. Rev., 5(4), 373-401. https://doi.org/10.1016/S1364-0321(01)00006-5.
  25. Leong, H.Y., Ong, D.E.L., Sanjayan, J.G. and Nazari, A. (2015), "A genetic programming predictive model for parametric study of factors affecting strength of geopolymers", RSC Advances, 5(104), 85630-85639. https://doi.org/10.1039/C5RA16286F
  26. Lisboa, P.J. and Taktak, A.F.G. (2006), "The use of artificial neural networks in decision support in cancer: A systematic review", Neural Networks, 19(4), 408-415. https://doi.org/10.1016/j.neunet.2005.10.007.
  27. LNEC:264. (1972), Solo-cimento - ensaio de compressao.
  28. LNEC. (1967), Documentacao normativa Especificacao do LNEC E 195-1966: Solos - Preparacao por via seca de amostras para ensaios de identificacao.
  29. Luat, N.V., Lee, K. and Thai, D.K. (2020), "Application of artificial neural networks in settlement prediction of shallow foundations on sandy soils", Geomech. Eng., 20(5), 385-397. https://doi.org/10.12989/gae.2020.20.5.385.
  30. Meireles, M.R.G., Almeida, P.E.M. and Simoes, M.G. (2003), "A comprehensive review for industrial applicability of artificial neural networks", IEEE T. Ind. Electron., 50(3), 585-601. https://doi.org/10.1109/TIE.2003.812470.
  31. Moller, M.F. (1993), "A scaled conjugate gradient algorithm for fast supervised learning", Neural Networks, 6(4), 525-533. https://doi.org/10.1016/S0893-6080(05)80056-5.
  32. Narloch, P., Hassanat, A., Tarawneh, A.S., Anysz, H., Kotowski, J., and Almohammadi, K. (2019), "Predicting compressive strength of cement-stabilized rammed earth based on SEM images using computer vision and deep learning", Appl. Sci., 9(23), 5131. https://doi.org/10.3390/app9235131.
  33. Ngo, H.T.T., Pham, T.A., Vu, H.L.T. and Van Giap, L. (2021), "Application of artificial intelligence to determined unconfined compressive strength of cement-stabilized soil in Vietnam", Appl. Sci., 11(4), 1-20. https://doi.org/10.3390/app11041949.
  34. NLT 304-89. (1989), NLT-304-89. Diametral compressive strength of materials treated with hydraulic binders.
  35. Pereira, L.F.M. (2021), Estudo do comportamento mecanico de dois solos estabilizados com cimento. Universidade de Coimbra.
  36. Pham, V.N., Oh, E. and Ong, D.E.L. (2022), "Effects of binder types and other significant variables on the unconfined compressive strength of chemical-stabilized clayey soil using gene-expression programming", Neural Comput. Appl., 34(11), 9103-9121. https://doi.org/10.1007/s00521-022-06931-0.
  37. Pham, V.N., Do, H.D., Oh, E. and Ong, D.E.L. (2021), "Prediction of unconfined compressive strength of cement-stabilized sandy soil in Vietnam using artificial neural networks (ANNs) model", Int. J. Geotech. Eng., 15(9), 1177-1187. https://doi.org/10.1080/19386362.2020.1862539.
  38. Ren, Q., Wang, G., Li, M. and Han, S. (2019), "Prediction of rock compressive strength using machine learning algorithms based on spectrum analysis of geological hammer", Geotech. Geol. Eng., 37(1), 475-489. https://doi.org/10.1007/s10706-018-0624-6.
  39. Shi, X., Liu, Q. and Xiujuan, L. (2012), "Application of SVM in predicting the strength of cement stabilized soil", Appl. Mech. Mater., 160, 313-317. https://doi.org/10.4028/www.scientific.net/AMM.160.313.
  40. Shibazaki, M. (2003), State of practice of jet grouting. In Grouting and Ground Treatment.
  41. Suman, S., Mahamaya, M. and Das, S.K. (2016), "Prediction of maximum dry density and unconfined compressive strength of cement stabilised soil using artificial intelligence techniques", Int. J. Geosynth. Ground Eng., 2(2), 1-11. https://doi.org/10.1007/s40891-016-0051-9.
  42. Teixeira, J.P., Pereira, M. and Teixeira, J.A. (2019), Circular Economy in the Civil Construction Sector I. Lisbon and Tagus Valley Regional Coordination and Development Commission.
  43. Tinoco, J., Alberto, A., da Venda, P., Gomes Correia, A. and Lemos, L. (2020), "A novel approach based on soft computing techniques for unconfined compression strength prediction of soil cement mixtures", Neural Comput. Appl., 32(13), 8985-8991. https://doi.org/10.1007/s00521-019-04399-z.
  44. Tinoco, J., Correia, A.G. and Cortez, P. (2011), "Application of data mining techniques in the estimation of the uniaxial compressive strength of jet grouting columns over time", Constr. Build. Mater., 25(3), 1257-1262. https://doi.org/10.1016/j.conbuildmat.2010.09.027.
  45. Tinoco, J., Gomes Correia, A., Cortez, P. and Toll, D.G. (2018), "Data-driven model for stability condition prediction of soil embankments based on visual data features", J. Comput. Civil Eng., 32(4), 4018027.
  46. Tola, S., Tinoco, J., Matos, J.C. and Obrien, E. (2023), "Scour detection with monitoring methods and machine learning algorithms - A critical review", Appl. Sci., 13(3), 1661.
  47. Venda Oliveira, P.J., Correia, A.A.S. and Cajada, J.C.A. (2018), "Effect of the type of soil on the cyclic behaviour of chemically stabilised soils unreinforced and reinforced with polypropylene fibres", Soil Dyn. Earthq. Eng., 115, 336-343. https://doi.org/10.1016/j.soildyn.2018.09.005.
  48. Wang, L. (2002), Cementitious Stabilization of Soils in the Presence of Sulfate. In Journal of Chemical Information and Modeling. Louisiana State University and Agricultural & Mechanical College.
  49. Waszczyszyn, Z. (2011). "Artificial neural networks in civil engineering: Another five years of research in Poland", Comput .Assisted Mech. Eng. Sci., 18(3), 131-146. https://cames.ippt.pan.pl/index.php/cames/article/view/110.
  50. Zhang, G., Chen, C., Zhang, Y., Zhao, H., Wang, Y. and Wang, X. (2022), "Optimised neural network prediction of interface bond strength for GFRP tendon reinforced cemented soil", Geomech. Eng., 28(6), 599-611. https://doi.org/10.12989/gae.2022.28.6.599.
  51. Zhang, Z. and Friedrich, K. (2003), "Artificial neural networks applied to polymer composites: A review", Compos. Sci. Tech., 63(14), 2029-2044. https://doi.org/10.1016/S0266-3538(03)00106-4.