Influential Parameters in Estimating Soil Properties from Cone Penetrating Test: An Artificial Neural Network Study

Authors: Ahmed G. Mahgoub, Dahlia H. Hafez, Mostafa A. Abu Kiefa

Abstract:

The Cone Penetration Test (CPT) is a common in-situ test which generally investigates a much greater volume of soil more quickly than possible from sampling and laboratory tests. Therefore, it has the potential to realize both cost savings and assessment of soil properties rapidly and continuously. The principle objective of this paper is to demonstrate the feasibility and efficiency of using artificial neural networks (ANNs) to predict the soil angle of internal friction (Φ) and the soil modulus of elasticity (E) from CPT results considering the uncertainties and non-linearities of the soil. In addition, ANNs are used to study the influence of different parameters and recommend which parameters should be included as input parameters to improve the prediction. Neural networks discover relationships in the input data sets through the iterative presentation of the data and intrinsic mapping characteristics of neural topologies. General Regression Neural Network (GRNN) is one of the powerful neural network architectures which is utilized in this study. A large amount of field and experimental data including CPT results, plate load tests, direct shear box, grain size distribution and calculated data of overburden pressure was obtained from a large project in the United Arab Emirates. This data was used for the training and the validation of the neural network. A comparison was made between the obtained results from the ANN's approach, and some common traditional correlations that predict Φ and E from CPT results with respect to the actual results of the collected data. The results show that the ANN is a very powerful tool. Very good agreement was obtained between estimated results from ANN and actual measured results with comparison to other correlations available in the literature. The study recommends some easily available parameters that should be included in the estimation of the soil properties to improve the prediction models. It is shown that the use of friction ration in the estimation of Φ and the use of fines content in the estimation of E considerable improve the prediction models.

Keywords: Angle of internal friction, Cone penetrating test, General regression neural network, Soil modulus of elasticity.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1099830

References:

[1] Robertson, P.K.., Guide to Cone Penetration Testing. Signal Hill: Gregg Drilling & Testing, 2010.
[2] Zervogiannis, C.S. and Kalteziotis, N.A. (1988), “Experience and Relationships from Penetration Testing in Greece”, International Symposium on Penetration Testing, ISOPT-1, Orlando, 2, 1063-71, Balkema Pub., Rotterdam.
[3] Burt Look, "Handbook of Geotechnical Investigation and Design Tables." (2007)
[4] Cem Ozan July 2003, "Estimation of Grain Characteristics of Soils by Using Cone Penetration Test (Cpt) Data." MSc. Thesis, The Graduate School of Natural and Applied Sciences of The Middle East Technical University, Turkey.
[5] Salehzadeh H., Hozouri A., Golestani A.R., "Correlation between Cone and Standard Penetration tests." 5th SASTech 2011, Khavaran Highereducation Institute, Mashhad, Iran. May 12-14.
[6] Abu Kiefa M.A (1997), “Prediciting The Driven Pile Capacity on Cohessionless Soil by Neural Networks. Pro. Of 3rd Int. Geotechnical Eng. Cof., Cairo University, 5-8 January, Cairo Egypt, pp.227-240.
[7] Abu Kiefa M.A (1998a), “General Regression Neural Networks for Driven Piles in Cohessionless Soil.” Journal of Geotechnical and Geoenvironmental Engineering, ASCE, Vol. 124, No. 12, Dec., pp. 1177-1185.
[8] Abu Kiefa M.A (1998b), “Artificial Neural Networks: A New Tool for Solving Geotechnical Engineering Problems.” 8th Int. Colloquium on Structural and Geotechnical Engineering, Ain Shams University, Dec. 15-17, Vol. III, pp. 16-26.
[9] Abu Kiefa M.A (1998c), “Evaluation of Bearing Capacity Failure Modes in Shallow Foundations using Fuzzy Logic” 8th Int. Colloquium on Structural and Geotechnical Engineering, Ain Shams University, Cairo, Egypt, pp. 39-50.
[10] Abu Kiefa M.A (2000a), “Stage Construction Control of Embankment on Soft Subsoil by Neural Network. ” 4th Int. Geotechnical Eng. Conf., Cairo University, 24-27 January, Cairo, Egypt.
[11] Abu Kiefa M.A (2000a), “Applications of Networks in Geotechnical Engineering,” State of Art Research Submitted to obtain Scientific degree of Professorship, Cairo University.
[12] Abu El Naga, H.M. (2001), “Calibration of Dynamic Con Results in Cohessionless Soils Using Artificial Neural Network,” M. Sc. Thesis, Cairo University, Egypt.
[13] Gribb, M.M., and Gribb, G.W.(1994), “Use of Neural Networks for Hydraulic Conductivity Determination in Unsaturated Soil.” Proc. 2nd International Conference on Ground Water Ecology, Atlanta (eds. Standford, J.A Vallet H.M.), Bethesda MD: Amer, Water Resources., pp.155-163.
[14] V. Varghese, S. S. Babu, R. Bijukumar, S. Cyrus _ B. M. Abraham, "Artificial Neural Networks: A Solution to the Ambiguity in Prediction of Engineering Properties of Fine-Grained Soils", Springer Science, Geotech Geol Eng (2013) 31, April 2013.
[15] F. Isik, G. Ozden, "Estimating compaction parameters of fine- and coarse-grained", Springer-Verlag Berlin Heidelberg 2012, Environ Earth Sci (2013) 69:2287–2297, Oct. 2012.
[16] Bozbey, E. Togrol, "Correlation of standard penetration test and pressuremeter data: a case study from Istanbul, Turkey", Springer- Verlag 2009, Bull Eng Geol Environ (2010) 69:505–515, Oct. 2009.
[17] Bojana Dolinar, "Predicting the normalized, undrained shear strength of saturated fine-grained soils using plasticity-value correlations soils by means of artificial neural networks", 2009 Elsevier B.V, University of Maribor.
[18] D. Singh, M.Zaman and s. Commuri, "Artificial Neural Network Modeling for Dynamic Modulus of Hot Mix Asphalt Using Aggregate Shape Properties", Journal of Geotechnical and Geoenvironmental Engineering, ASCE, Civ. Eng. 2013.25, Jan. 2013, pp 54-62.
[19] Ceryan, N, Okkan, U, and Kesimal, A. (2012) "Application of Generalized Regression Neural Networks in Predicting the Unconfined Compressive Strength of Carbonate Rocks" Rock Mech Rock Eng, V45: 1055-1072.
[20] Hasanadehshooiili, H. Lakirouhani, A. and Medzvieckas, J. (2012) "Superiority of Artificial Neural Networks over Statistical methods in prediction of the optimal length of Rock Bolts", V18(5):655-661.
[21] Akca, N. 2003. Correlation of SPT-CPT Data From United Arab Emarites. Engineering Geology. V67. 219-231.
[22] Chin, C.T., Duann, S.W. and Kao, T.C. (1988), “SPT-CPT Correlations for Granular Soils”, International Symposium on Penetration Testing, ISOPT-1, Orlando, 1, 335-9.
[23] Danziger, F.A.B. et al. 1998. "CPT-SPT Correlations for some Barazilian Residual Soils." In Rebertson & Mayne (eds), Geotechnical site characterization: 907-912. Rotterdam: Balkema.
[24] Mahmoud Elbanna and Joseph Quinn (2011), "SPT – CPT Correlations for Oilsands Tailings Sand." Klohn Crippen Berger Ltd., Canada.
[25] Hykin, S. (1994), “Neural Networks: A Comprehesive Foundation” NY: Macmillan, pp. 2.
[26] Lin, Lee, "Neuro-fuzzy synergism to intelligent systems", National Chiao Tung University, 1996.
[27] Goh, A.T.C. (1995a), “Back propagation Neural Networks for Modeling Complex System,” Artificial Intelligence in Engineering, Vol.9, no.3, PP.143-151.
[28] Goh, A.T.C. (1995b), “Empirical Design in Geotechnics using Neural Networks,” Geotechnique, Vol.45, no.4, pp.709-714.
[29] Goh, A.T.C. (1995c), “Modeling Soil Correlations using Neural Networks” Journal of Computing in Civil Engineering, Vol.9, no.4, pp.275-278.
[30] Specht, D.F. 1991. "A general regression neural network." IEEE Trans. Neural Networks, 2(6), 568-576.