Geotechnical and Geological Engineering

, Volume 27, Issue 3, pp 289–304 | Cite as

Rockfill Strength Evaluation Using Cascade Correlation Networks

  • Silvia R. García
  • Miguel P. Romo
Original Paper


Performing comprehensive laboratory test programs to estimate rockfill strength for rockfill dam projects is a lengthy and onerous task because of the large sample-size. Accordingly, it has become a common practice to carry out limited experimental investigation, and extrapolate the results to the expected conditions in actual embankments. A number of investigators have established a function of the type τ = ασβ, where τ and σ are the shear and normal stresses, respectively, and the constants α and β, which result from a fitting procedure, have no physical meaning. Results of laboratory tests on a variety of rockfills have shown that in addition to effective confining stresses the relative density, uniformity coefficient, maximum particle size and particle-breaking load influence rockfill strength. Thus these parameters must be included in any function for computing rockfill strength. Other parameters, whose influence is understood partially, are not included here. Given the non linear-multidimensional nature of the problem, in this paper a neuronal procedure is developed. This approach takes into account the influence of each of the parameters mentioned before. The network used in this article was defined after comparing the results obtained with a variety of algorithms. After several attempts, the Cascade Correlation Network (CCN) was found to yield most accurate strength predictions.


Cascade correlation algorithm Coarse granular materials behavior Fuzzy clustering Neural networks Rockfill strength 



The authors are grateful to CONACyT for the support provided throughout the grant 33032 LI. Also they acknowledge the skillful editing by Eng. Mercedes Ortega, Arturo Paz and Roberto Soto.


  1. Alberro J, Gaziev E (2000) Resistencia y compresibilidad de los enrocamientos. Internal Report. Institute of Engineering, UNAM. MéxicoGoogle Scholar
  2. Barton N, Kjaernski B (1981) Shear strength of rockfill. J Geotech Eng Div Am Soc Civ Engrs 107(GT7):873–891Google Scholar
  3. Breiman L, Friedman J, Olshen R, Stone C (1995) Classification and regression tree1s, Wadsworth International Group, Belmont CA (1986), cited in Gallant SI, Neural network learning and expert systems, The MIT Press, Third printingGoogle Scholar
  4. Charles JA, Watts KS (1980) The influence of confining pressure on the shear strength of compacted rockfill. Géotechnique 30(4):353–367Google Scholar
  5. De Mello VFB (1977) Reflexions on design decisions of practical significance to embankment dams. Géotechnique 27(3):279–355Google Scholar
  6. Fahlman SE (1988) An empirical study of learning speed in back-propagation networks. CMU Technical Report CMU-CS–88-162Google Scholar
  7. Fahlman SE, Lebière C (1991) The cascade-correlation learning architecture, CUV-CS-90–100, School of Computer Science. Carnegie Mellon University, Pittsburgh, PAGoogle Scholar
  8. Franklin JA (1971) Triaxial strength of rock materials. Rock Mech 3(2):86–98CrossRefGoogle Scholar
  9. Frean M (1990) The upstart algorithm: a method for constructing and training feed forward neural networks. Neural Comput 2:198–209CrossRefGoogle Scholar
  10. Gallant SI (1986) Three constructive algorithms for network learning, Proceedings, eighth annual conference of the cognitive science society, Amherst, MA, August 15–17, pp 652–660Google Scholar
  11. Gallant SI (1990) Perceptron-based learning algorithm. IEEE Trans Neural Netw 1(2):179–192CrossRefGoogle Scholar
  12. García SR, Romo MP, Taboada-Urtuzuástegui V, Mendoza M (2000) Sand behavior modeling using static and dynamic artificial neural networks. Serie de Investigación y Desarrollo, Institute of Engineering, UNAM, SID/631, MéxicoGoogle Scholar
  13. García SR, Romo MR, Botero E (2007) A neurofuzzy system to analyze liquefaction-induced lateral spread. Soil Dyn Earthquake Eng 28(3):169–180CrossRefGoogle Scholar
  14. Gaziev E (2001) Out energy evaluation for brittle materials. Int J Solids Struct 38(42–43):7681–7690CrossRefGoogle Scholar
  15. Ghaboussi J, Sidarta DE (1998) New nested adaptive neural networks (NANN) for constitutive modeling. Comp Geotech 22(1):29–71CrossRefGoogle Scholar
  16. Ghaboussi J, Garret JH, Wu X (1991) Knowledge-based modeling of material behavior with neural networks. J Eng Mech Div Am Soc Civ Engrs 117(EM1):133–157Google Scholar
  17. Indraratna B, Wijewardena LSS, Balasubramanian AS (1993) Large-scale triaxial testing of greywacke rockfill. Géotechnique 43(1):37–51CrossRefGoogle Scholar
  18. Marachi ND, Chan CK, Seed HB (1972) Evaluation of properties of rock materials. J Soil Mech Fdns Div Am Soc Civ Engrs 98(SM1):95–114Google Scholar
  19. Marsal RJ, Ramírez de Arellano L (1967) Performance of El Infiernillo dam, 1963–1966. J Soil Mech Fdns Div Am Soc Civ Engrs 93(SM4):265–297Google Scholar
  20. Mézard M, Nadal JP (1989) Learning feed forward layered networks: the tiling algorithm. J Phys A: Math Gen 22(22):2191–2203CrossRefGoogle Scholar
  21. Rahman MS (2002) Fuzzy neural network for liquefaction prediction. Soil Dny Earthquake Eng 22(8):685–694CrossRefGoogle Scholar
  22. Romo MP (1999) Earthquake geotechnical engineering and artificial neural networks: 4th Arthur Casagrande Lecture, Proceedings of XI Pan American Conference on Soil Mechanics and Geotechnical Engineering, Special Volume.Google Scholar
  23. Romo MP, García SR, Mendoza M, Taboada-Urtuzuástegui V (2001) Recurrent and constructive-algorithm networks for sand behavior modeling. Int J Geomech 1(4):371–387CrossRefGoogle Scholar
  24. Rumelhart DE, Hinton GE, Williams RJ (1986) In: Rumelhart DE, McClelland JL (eds) Learning internal representations by error propagation, parallel distributed processing: explorations in the microstructure of cognition, vol 1. MIT Press, Cambridge, pp 318–362Google Scholar
  25. Specht D (1991) A general regression neural network. IEEE Trans Neural Netw 2(6):568–576CrossRefGoogle Scholar
  26. Theodoridis S, Koutroumbas K (1999) Pattern recognition. Academic Press, Elsevier Science, USAGoogle Scholar
  27. Vega Pinto AA (1983) Previsao do comportamento structural de barragens de enrocamento. Laboratorio Nacional de Engenharia Civil, LisboaGoogle Scholar
  28. Vouille G, Laurent D (1969) Étude de la courbe intrenséque de quelque granites. Revue de l’Industrie Minérale, Paris, Numero special, 25–28Google Scholar
  29. Yoshida K, Hayashi Y, Imura AA (1989) Neural network expert system for diagnosing hepatobiliary disorders, MEDINFO ’89. Proceedings of the sixth conference on medical informatics, Beijing, October 16–20, cited in Gallant SI, Neural network learning and expert systems, The MIT Press, Third printing, pp 116–120Google Scholar

Copyright information

© Springer Science+Business Media B.V. 2008

Authors and Affiliations

  1. 1.Instituto de IngenieríaUniversidad Nacional Autónoma de MéxicoMexicoMexico

Personalised recommendations