Skip to main content
SpringerLink
Log in

Prediction of swelling pressures of expansive soils using soft computing methods

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Lateral and vertical swelling pressures associated with expansive soils cause damages on structures. These pressures must be predicted before the structures are constructed in order to prevent the damages. The magnitude of the stresses can decrease rapidly when volume changes are partly allowed. Therefore, a material, which has a high compressibility, must be placed between expansive soils and the structures in both horizontal and vertical directions in order to decrease transmitted swelling pressure on structures. There are numerous techniques recommended for estimating the swelling pressures. However, these techniques are very complex and time-consuming. In this study, a new estimation model to predict the pressures is developed using experimental data. The data were collected in the laboratory using a newly developed device and experimental setup also. In the experimental setup, a rigid steel box was designed to measure transmitted swelling pressures in lateral and vertical directions. In the estimation model, approaches of artificial neural network (ANN) and adaptive neuro-fuzzy inference systems (ANFIS) are employed. In the first stage of the study, the lateral and vertical swelling pressures were measured with different thicknesses of expanded polystyrene geofoam placed between one of the vertical walls of the steel box and the expansive soil in the laboratory. Then, ANN and ANFIS approaches were trained using these results of the tests measured in the laboratory as input for the prediction of transmitted lateral and vertical swelling pressures. Results obtained showed that ANN-based prediction and ANFIS approaches could satisfactorily be used to estimate the transmitted lateral and vertical swelling pressures of expansive soils.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Abbreviations

a :

Scaling factor

a i :

The parameter set which changes the shape of the MF degree

A 1 :

MFs for inputs

A 2 :

MFs for inputs

AARE:

Average absolute relative error

A i :

Linguistic fuzzy set associated with node

ANFIS:

Adaptive neuro-fuzzy inference systems

ANN:

Artificial neural network

b :

Scaling factor

B 1 :

MFs for inputs

B 2 :

MFs for inputs

b i :

The parameter set which changes the shape of the MF degree

B i−2 :

Linguistic fuzzy set associated with node

BPNN:

Back propagation neural network

c i :

The parameter set which changes the shape of the MF degree

e :

Vector of network errors

EPS:

Expanded polystyrene

FIS:

Fuzzy inference systems

g :

Gradient

H :

Hessian matrix

i :

Layer

j :

Layer

J :

Jacobian Matrix

J T :

Transpose of the Jacobian matrix

k :

Layer

LM:

Levenberg–Marquardt algorithm

MFs:

Membership functions

MLP:

Multi-layer perceptron

N :

Number of data

\( O_{1,\,i} \) :

Output of ANFIS

P :

Swelling pressure

p 1 :

The parameter of the output function of ANFIS

p 2 :

The parameter of the output function of ANFIS

P measured :

Measured swelling pressure

P predicted :

Predicted swelling pressure

q 1 :

The parameter of the output function of ANFIS

q 2 :

The parameter of the output function of ANFIS

r 1 :

The parameter of the output function of ANFIS

r 2 :

The parameter of the output function of ANFIS

R 2 :

Determination coefficient

RE:

Relative error

RMSE:

Root mean square error

W :

Interconnection strengths, or weights

\( W_{ij} \) :

Interconnection weights

\( W_{jk} \) :

Interconnection weights

x :

Input for ANFIS

x k :

Parameter vector

x k+1 :

Parameter vector

\( x_{\hbox{min} } \) :

Minimum of the training and test data

\( x_{\hbox{max} } \) :

Maximum of the training and test data

y :

Input for ANFIS

μ:

Membership grades

μ Ai :

Membership grades of an input parameter

References

  1. Ashayeri I, Yasrebi S (2009) Free-swell and swelling pressure of unsaturated compacted clays; experiments and neural networks modeling. Geotech Geol Eng 27:137–153

    Google Scholar 

  2. ASTM-C 578 (2003) Standard specification for rigid, cellular polystyrene thermal insulation. Annual Book of ASTM Standards C578, 04.06, 6

  3. Attoh-Okine NO (1998) Artificial intelligence and mathematical methods in pavement and geomechanical systems. In: Proceedings of the workshop at Florida International University, North Miami, Florida, 5–6. Balkema

  4. Basma AA, Barakat SA, Omar M (2003) Modeling time dependent swell of clays using sequential artificial neural networks. Environ Eng Geosci 9(3):279–288

    Article  Google Scholar 

  5. Beinbrech G, Hillmann R (1997) EPS in road construction—current situation in Germany. Geotext Geomembr 15(1–3):39–57

    Article  Google Scholar 

  6. Bianchini M, Gori M (1996) Optimal learning in artificial neural networks: a review of theoretical results. Neurocomputing 13:313–346

    Article  Google Scholar 

  7. Data Collection will Clarify Clayboard Doubts (1991) In ground engineering. Thomas Telford, UK

    Google Scholar 

  8. Dawson WC, Wilby R (1998) An artificial neural network approach to rainfall-runoff modeling. Hydrol Sci J 43(1):47–66

    Article  Google Scholar 

  9. Doris JJ, Rizzo MD, Dewoolkar MM (2008) Forecasting vertical ground surface movement from shrinking/swelling soils with artificial neural networks. Int J Numer Anal Methods Geomech 32:1229–1245

    Article  MATH  Google Scholar 

  10. Goh ATC (1996) Neural-network modeling of CPT seismic liquefaction data. J Geotech Eng 122(1):70–73

    Article  Google Scholar 

  11. Goh ATC, Wong KS, Broms BB (1995) Estimation of lateral wall movements in braced excavation using neural networks. Can Geotech J 32:1059–1064

    Article  Google Scholar 

  12. Hagan MT, Menhaj M (1994) Training feedforward networks with the Marquardt algorithm. IEEE Trans Neural Netw 5(6):989–993

    Article  Google Scholar 

  13. Haykin S (1999) Neural networks: a comprehensive foundation, 2nd edn. Prentice-Hall, Upper Saddle River, pp 26–32

    MATH  Google Scholar 

  14. Horvath JS (1997) The compressible inclusion function of EPS geofoam. Geotext Geomembr 15:77–120

    Article  Google Scholar 

  15. Ikizler SB, Aytekin M, Nas E (2008) Laboratory study of expanded polystyrene (EPS) geofoam used with expansive soils. Geotext Geomembr 26(2):189–195

    Article  Google Scholar 

  16. Ikizler SB, Aytekin M, Kocabaş F, Vekli M (2010) Prediction of swelling pressures of expansive soils using artificial neural networks. Adv Eng Softw 41(4):647–655

    Article  MATH  Google Scholar 

  17. Jang JSR (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23(3):665–685

    Article  Google Scholar 

  18. Jeon J (2007) Fuzzy and neural network models for analyses of piles. PhD thesis, North Carolina State University, USA

  19. Joshi RP, Katti RK (1980) Lateral pressure development under surcharges. In: Proceedings of the 4th international conference on expansive soils, Denver, USA, pp 227–241

  20. Lee C, Sterling R (1992) Identifying probable failure modes for underground openings using a neural network. Int J Rock Mech Min Sci Geomech Abstr 29(1):49–67

    Article  Google Scholar 

  21. Lee IM, Lee JH (1996) Prediction of pile bearing capacity using artificial neural networks. Comput Geotech 18(3):189–200

    Article  Google Scholar 

  22. Meisina C, Najjar Y (2004) An artificial neural network approach for predicting swelling/shrinking parameters of Italian clay soils. Eur Geosci Union Geophys Res Abstr 6:03295. http://www.cosis.net/abstracts/EGU04/03295/EGU04-J-03295.pdf

  23. Moosavi M, Yazdanpanah MJ, Doostmohammadi R (2006) Modeling the cyclic swelling pressure of mudrock using artificial neural Networks. Eng Geol 87:178–194

    Article  Google Scholar 

  24. Moré JJ (1977) Lecture notes in mathematics. The Levenberg–Marquardt algorithm: implementation and theory. In: Watson GA (ed) Numerical analysis, vol 630. Springer, Berlin, pp 105–116

    Chapter  Google Scholar 

  25. Najjar YM, Basheer IA, McReynolds R (1996) Neural modeling of Kansan soil swelling. Transp Res Rec 1526:14–19

    Article  Google Scholar 

  26. Najjar YM, Basheer IA (1998) Modeling of soil swelling via regression and neural network approaches. Final report, report no.: KS 98-1. Kansas Department of Transportation, p 37

  27. Neocleous C, Schizas C (2002) Artificial neural network learning. A comparative review. Methods and applications of artificial intelligence, Lecture notes in computer science, vol 2308, pp 300–313

  28. Riad HL, Ricci AL, Osborn PW, Horvath JS (2003) Expanded polystyrene (EPS) geofoam for road embankments and other lightweight fills in urban environments. Soil and rock America 2003. In: 12th Panamerican conference on soil mechanics and geotechnical engineering/39th US rock mechanics symposium, Cambridge, MA, USA, pp 1767–1772

  29. Rizzo DM, Dougherty DE (1994) Application of artificial neural networks for site characterization using hard and soft information. In: Peters A et al (eds) Proceedings of the 10th international conference on computational methods in water resources, vol 12. Kluwer, Dordrecht, pp 793–799

    Google Scholar 

  30. Sivakugan N, Eckersley JD, Li H (1998) Settlement predictions using neural networks. Aust Civil Eng Trans 40:49–52

    Google Scholar 

  31. Stark TD, Arellano D, Horvath JS, Leshchinsky D (2004) Geofoam applications in the design and construction of highway embankments. NCHRP web document. Transportation Research Board, USA, p 65

  32. Suykens JAK (2001) Nonlinear modelling and support vector machines. In: Proceedings of the IEEE instrumentation and measurement technology conference, Budapest, Hungary, pp 287–294

  33. Teh CI, Wong KS, Goh ATC, Jaritngam S (1997) Prediction of pile capacity using neural networks. J Comput Civil Eng ASCE 11(2):129–138

    Article  Google Scholar 

  34. Turk G, Logar J, Majes B (2001) Modelling soil behaviour in unaxial strain conditions by neural networks. Adv Eng Softw 32:805–812

    Article  MATH  Google Scholar 

  35. Xu Q, Huang RQ (1994) Artificial neural network methods for spatial prediction of slope stability. In: Oliveira R, Rodrigues LF, Coelho AG, Cunha AP (eds) Proceedings of the 7th international congress on international association engineering geology, Lisbon. Balkema, Rotterdam, pp 4725–4728

    Google Scholar 

  36. Zarnani S, Bathurst RJ (2007) Experimental investigation of EPS geofoam seismic buffers using shaking table tests. Geosynth Int 14(3):165–177

    Article  Google Scholar 

  37. Zhu JH, Zaman MM, Anderson SA (1998) Modeling of soil behavior with a recurrent neural network. Can Geotech J 35(5):858–872

    Article  Google Scholar 

  38. Zou Y, Small JC, Leo CJ (2000) Behaviour of EPS geofoam in model test on pavements. Geosynth Int 7(1):1–22

    Google Scholar 

Download references

Acknowledgments

The authors gratefully acknowledge the support given by the Turkish Polystyrene Manufacturers Association (PUD).

Author information

Authors and Affiliations

  1. Civil Engineering Department, Karadeniz Technical University, 61080, Trabzon, Turkey

    S. Banu Ikizler

  2. Civil Engineering Department, Bozok University, Yozgat, Turkey

    Mustafa Vekli

  3. Civil Engineering Department, Engineering Faculty, Sakarya University, Esentepe Campus, 54187, Sakarya, Turkey

    Emrah Dogan

  4. Department of Civil Engineering and Architecture, University of Bahrain, Isa Town, Kingdom of Bahrain

    Mustafa Aytekin

  5. Civil Engineering Department, Bartin University, Bartin, Turkey

    Fikret Kocabas

Authors
  1. S. Banu Ikizler
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mustafa Vekli
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Emrah Dogan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mustafa Aytekin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Fikret Kocabas
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to S. Banu Ikizler.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ikizler, S.B., Vekli, M., Dogan, E. et al. Prediction of swelling pressures of expansive soils using soft computing methods. Neural Comput & Applic 24, 473–485 (2014). https://doi.org/10.1007/s00521-012-1254-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-012-1254-1

Keywords

Search

Navigation