تخمین ضریب فشار جانبی ماسه ها با استفاده از آزمایش نفوذ مخروط در محفظه کالیبراسیون و شبکه عصبی مصنوعی

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشکده مهندسی عمران، دانشگاه صنعتی شریف، تهران، ایران

چکیده

تعیین دقیق و مناسب پارامترهای خاک همواره در طراحی‌های ژئوتکنیکی مورد توجه بوده است. پیش بینی دقیق پارامترهای تاثیرگذار ماسه از آزمایشات برجا نظیر (CPT)، یکی از چالشی‌ترین مسایل در مهندسی ژئوتکنیک است. در این تحقیق با استفاده از نتایج آزمایش کالیبراسیون نفوذ مخروط که در دانشگاه‌ها و موسسات معتبر انجام شده‌اند و همچنین سیستمی متشکل از سه نوع شبکه عصبی مصنوعی، پارامتر ضریب فشار جانبی ماسه در حالت سکون(K0) برای انواع مختلف ماسه‌های موجود در پایگاه داده جمع‌آوری شده، به طور نسبتا دقیقی پیش بینی شده است. در این سیستم مجموعه‌ای از شبکه‌های عصبی به طور سری وظایفی انجام می‌دهند و در نهایت با ترکیب مناسب این شبکه‌ها، سیستم قادر خواهد بود که پارامتر(K0) را با دقت مناسب برای خاک‌های ماسه‌ای مورد بررسی در پایگاه داده، پیش‌بینی نماید. در این روش از شبکه عصبی خودسازمانده (SOM) برای خوشه‌بندی مناسب داده‌ها، از شبکه عصبی احتمالاتی (PNN) برای کلاسه‌بندی ماسه و در نهایت از شبکه عصبی چندلایه با الگوریتم پس انتشار(BP) برای مدل نهایی، استفاده می‌گردد. جزییات ایجاد و به کارگیری چنین سیستمی در مقاله شرح داده شده و همچنین در پایان، نتایج بدست آمده از این سیستم با نتایج سایر محققین مقایسه گردیده است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Determination of Coefficient of Lateral Earth Pressure at Rest for Sandy Soil Using Cone Penetration Test and Artificial Neural Network

نویسندگان [English]

  • M. M. Ahmadi
  • N. Besharat
Department of Civil Engineering, Sharif University of Technology, Tehran, Iran
چکیده [English]

The estimation of soil parameters in geotechnical practice is always an important step. Accurate prediction of sands parameters from insitu tests such as CPT is one of the most challenging problems in geotechnical engineering. In this study, using a series of reliable CPT calibration chamber test data and a system consisting of three types of neural networks, the coefficient of lateral pressure of sandy soil at rest (K0) is predicted while it has good agreement with measured data gathered in database. In this system, a series of neural networks perform some tasks and finally by strategically combining of networks, the system will be able to predict parameter (K0) with reasonable accuracy. The proposed system uses Self Organizing Map (SOM) for clustering data into training, testing and validating sets and probabilistic neural networks for classifying of sands and back propagation neural networks for conclusive function approximation. Details on the development of such a system are described in the present paper and finally results obtained by this system are compared to the available relations suggested by other researchers.

کلیدواژه‌ها [English]

  • "Coefficient of lateral pressure of sandy soil at rest"
  • "Cone Penetration Test"
  • "Calibration Chamber"
  • "Self-Organizing Map (SOM)"
  • "Probabilistic Neural Network (PNN)"
[1] P, Karambakhsh, Determination of lateral pressure of sandy soil using results of calibration of cone penetration test, MSc thesis, Sharif University of Technology, Iran,2008 (in Persian).
[2] M. M., Ahmadi, P., Karambakhsh, A. A., Golestani, Horizontal Stress Estimation Using CPT: A Database Approach, Sharif Journal-Civil Engineering, 2010. (In Persian)
[3] M. B., Menhaj, Computational Intelligence-Volume I: Fundamentals of Neural Networks, Amirkabir university of technology Pub., 2009.
[4] J., Ghaboussi; J. H., Garrett; X., Wu; Knowledge Based Modeling of Material Behavior with Neural Networks, Journal of Engineering Mechanics, ASCE, Vol. 117, No.1, pp. 132-53, 1991.
[5] R. W., Meier; G. J., Rix; Backcalculation of Flexible Pavement Moduli Using Artificial Neural Networks, Transportation Research Record 1448, National Research Council, Washington, D.C., pp. 75-82, 1994.
[6] G., Agrawal; J. L., Chameau; P. L., Bourdeau; Assessingthe Liquefaction Susceptibility at a Site Based on Information from Penetration Testing, Artificial Neural Networks for Civil Engineers: Fundamentals and Applications, ASCE Monograph, New York, pp. 185-214, 1995.
[7] Y. M., Najjar; I. A., Basheer; R., McReynold; Neural Modelling of Kansas Soil Swelling, Transportation Research Record 1526, National Research Council, Washington, D.C., pp. 14-9, 1996.
[8] S. H., Ni; P. C., Lu; C. H., Juang; A Fuzzy Neural Network Approach to Evaluation of Slope Failure Potential, Microcomputers in Civil Engineering, Vol. 11,pp. 59-66, 1996.
[9] C. H., Juang; C. J., Chen; CPT-based Liquefaction Evaluation Using Artificial Neural Networks, Journal of Computer-Aided Civil and Infrastructure Engineering,Vol. 14, No. 2, pp. 221-229, 1999.
[10] C. H., Juang; C. J., Chen; Y. M., Tien; Appraising CPT Based Liquefaction Resistance Evaluation Method Artificial Neural Network Approach, Canadian Geotechnical Journal, Vol. 36, pp. 443-54, 1999.
[11] C. H., Juang; P. C., Lu; Predicting Geotechnical Parameters of Sands from CPT Measurements Using Neural Networks, Computer-Aided Civil and Infrastructure Engineering, Vol. 17, pp. 31-42, 2002.
[12] G., Baldi; R., Bellotti; V., Ghionna; M., Jamiolkowski; E., Pasqualini; Interpretations of CPT’s and CPTU’s, 2nd Part: Drained Penetration of Sands, 4th International Conference on Field Instrumentation and In-situ Measurements, Singapore, pp. 143-156, 1986.
[13] A. K., Parkin; The Calibration of Cone Penetrometers, Proceedings of the 1st International Symposium on Penetration Testing (ISOPT), Vol. 1, pp. 221-243, 1988.
[14] G. T., Houlsby; R. C., Hitchman; Calibration Tests of Cone Penetrometers in Sand, Géotechnique, Vol. 38, No. 1, pp. 39-44, 1988.
[15] M., Jamiolkowski; G., Baldi; R., Bellotti; V., Ghionna; E., Pasqualini; Penetration Resistance and Liquefaction of Sands, Proc. 11th Int. Conf. on Soil Mech. and Found. Eng., A. A. Balkema, Rotterdam, Netherlands, pp. 1891-186, 1985
[16] P. W., Mayne; Tentative Method for Estimating σh0 from qc Data in Sands, Proc. 1st Int. Symposium on Calibration Chamber Testing, Potsdam, NY, Elsevier, Amsterdam, pp. 249-256, 1991.
[17] M. M., Ahmadi; P., Karambakhsh; K0 Determination of Sand Using CPT Calibration Chamber, 2nd Int. Symposium on CPT, Huntington Beach, California, Paper No. 2-14, 2010.
[18] R., Salgado; Analysis of Penetration Resistance in Sands, Ph.D. Thesis, Dept. of Civ. Engineering, University of California, Berkeley, Calif., 1993.
[19] T., Lunne; P. K., Robertson; J. M., Powell; Cone Penetration Testing in Geotechnical Practice, Blackie Academic and Professional, London, UK, 1997.
[20] P. W., Mayne; F. H., Kulhawy; Calibration Chamber Data Base and Boundary Effects Correction for CPT Data, Proceedings of the 1st International Symposium on Calibration Chamber Testing, Potsdam, New York, pp.257-264, 1991.
[21] K., Been; J. H. A., Crooks; L. A., Rothenburg; Critical Appraisal of CPT Calibration Chamber Tests, Proceeding of the 1st International Symposium on Penetration Testing (ISOPT), Vol. 2, pp. 651-660, 1988.
[22] K., Iwasaki; F., Tanizawa; S., Zhou; F., Taksuoka; Cone Resistance and Liquefaction Strength of Sand, Proc. 1stInt. Symp. on Penetration Testing, Vol. 2, Rotterdam:Balkema, pp. 785-791, 1988.
[23] M., Jamiolkowski; D. C. F., Lo-Presti; M., Manassero; Evaluation of Relative Density and Shear Strength of Sands from CPT and DMT, Soil Behavior and Soft Ground Construction, ASCE Geotechnical Special Publication, Vol. 119, pp. 201-238, 2003.
[24] M. M., Ahmadi; P. K., Robertson; A Numerical Study of Chamber Size and Boundary Effects on CPT Tip Resistance in NC Sand, Scientia Iranica, Vol. 15, No. 5, pp. 541-553.
[25] M., Pournaghiazar; A. R., Russel; N., Khalili; Linking Cone Penetration Resistances Measured in Calibration Chambers and the Field, Geotechnique Letters, Vol. 2,pp. 29-35, 2012.
[26] M. A., Shahin; M. B., Jaksa; H. R., Maier; Artificial Neural Network Application in Geotechnical Engineering, Australian Geomechanics, Vol. 36, No. 1,pp. 49-62, 2001.
[27] M. A., Shahin; M. B., Jaksa; H. R., Maier; Data Division for Developing Neural Networks Applied to Geotechnical Engineering, Journal of Computing in Civil Engineering, ASCE, Vol. 18, No. 2, pp. 105-114, 2004.
[28] H., Demuth; M., Beale; Neural Network Toolbox,User’s Guide, Version 3, The Mathworks, Inc., Natick, MA, 1998.
[29] G. J., Bowden; H. R., Maier; G. C., Dandy; Optimal Division of Data for Neural Network Models in Water Resources Applications, Water Resource. Res., Vol. 2, pp.1-11, 2002.