پیش‌بینی ظرفیت باربری نهایی پی‌های سطحی واقع بر خاک‌های دانه‌ای با استفاده از مدل درختی M5P

نوع مقاله : پژوهشی

نویسندگان

1 قزوین

2 دانشگاه بین المللی امام خمینی (ره) قزوین

3 آزاد تهران شرق

چکیده

پیش‌بینی ظرفیت باربری نهایی پی‌های سطحی یکی از مسائل اساسی در مهندسی ژئوتکنیک است و تاکنون روش‌های متفاوتی برای پیش‌بینی دقیق آن ارائه شده است. در سال‌های اخیر، روش‌های محاسبات نرم مانند شبکه‌های عصبی مصنوعی (ANN) و ماشین‌های بردار پشتیبان (SVM) برای پیش‌بینی ظرفیت باربری نهایی پی‌های سطحی مورد استفاده قرار گرفته است. با این حال، در این روش‌ها فرآیند مدل‌سازی پیچیده است و استفاده از آنها مانند روش‌های تجربی آسان نیست. در این تحقیق، از مدل درختی M5P به عنوان یک روش محاسبات نرم جدید، برای پیش‌بینی ظرفیت باربری نهایی پی‌های سطحی استفاده شده است. مزیت اصلی مدل‌های درختی نسبت به شبکه‌های عصبی مصنوعی و ماشین‌های بردار پشتیبان، سادگیِ کاربرد و مهم‌تر از آن، قوانین ریاضی قابل ‌درک است. به منظور توسعه و ارزیابی مدل از نتایج آزمون‌های تجربی آزمایشگاهی پی‌های سطحی روی خاک‌های دانه‌ای با متغیرهای زاویۀ اصطکاک داخلی، وزن مخصوص خاک و هندسۀ پی شامل عمق، عرض و طول پی استفاده شده است. نتایج به دست آمده از مدل پیشنهادی با نتایج حاصل از فرمول‌های محاسباتی Meryehof، Hansen و Vesic مقایسه شده است. نتایج نشان می‌دهد که مدل درختی M5P نسبت به روش‌های نظری مذکور عملکرد بهتری دارد.

کلیدواژه‌ها


عنوان مقاله [English]

Prediction the Ultimate Bearing Capacity of Shallow Foundations on the Cohesionless Soils Using M5P Model Tree

نویسندگان [English]

  • vahid reza Koohestani 1
  • Mahmoud Hassanlourad 2
  • M.R Bazargan Lari 3
1 Central Tehran Branch, Islamic Azad University.
2 Imam Khomeini International University.
3 Islamic Azad University.
چکیده [English]

Bearing capacity prediction of shallow foundation is one of the most important problems in geotechnical engineering practices, with a wide variety range of methods which have been introduced to forecast it accurately. Recently, soft computing methods such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs) have been used for prediction of the ultimate bearing capacity of shallow foundation. However, in these methods the modeling process is complex and are not as easy to use as the empirical equations. In this paper, M5P model tree as a new soft computing method has been used for prediction of the ultimate bearing capacity of shallow foundation. The main advantage of model tree is that, compared to ANN and SVM, they are easier to use and more importantly they represent understandable mathematical rules. Laboratory experimental tests of shallow foundations on cohesionless soils were used with parameters of the internal friction angle, the unit weight of the soil, and the geometry of a foundation considers depth, width, and length to develop and test the model. The results achieved from the proposed model was compared with those obtained from the Meyerhof, Hansen and Vesic computation formulas. The results indicate that M5P model tree perform better than the mentioned theoretical methods.

کلیدواژه‌ها [English]

  • Soft computing methods
  • M5P model tree
  • Shallow foundations
  • Ultimate bearing capacity
1. Terzaghi, K., "Theoretical soil mechanics", John Wiley & Sons, New York, (1943).
2. Meyerhof, G.G., "Some recent research on the bearing capacity of foundations", Canadian Geotechnical Journal, vol. 1, pp. 16-26, (1963).
3. Hansen, J.B., "A revised and extended formula for bearing capacity", Geoteknisk Institut, (1970).
4. Vesic, A.S. "Analysis of ultimate loads of shallow foundations", Journal of The Soil Mechanics and Foundations Division, ASCE, vol. 91, pp. 45-73, (1974).
5. Silvestri, V., "A limit equilibrium solution for bearing capacity of strip foundations on sand", Canadian geotechnical journal, vol. 40, pp. 351-361, (2003).
6. Bolton, M. and Lau, C., "Vertical bearing capacity factors for circular and strip footings on Mohr-Coulomb soil", Canadian Geotechnical Journal, vol. 30, pp. 1024-1033, (1993).
7. Soubra, A.H., "Upper-bound solutions for bearing capacity of foundations", Journal of Geotechnical and Geoenvironmental Engineering, vol. 125, pp. 59-68, (1999).
8. Griffiths, D., "Computation of bearing capacity factors using finite elements", Geotechnique, vol. 32, pp. 195-202, (1982).
9. Kohestani, V.R. and Hassanlourad, M., "Modeling the Mechanical Behavior of Carbonate Sands Using Artificial Neural Networks and Support Vector Machines", International Journal of Geomechanics, vol. 16, pp.04015038, (2015).
10. Ardakani, A. and Kohestani, V.R., "Evaluation of liquefaction potential based on CPT results using C4.5 decision tree", Journal of AI and Data Mining, vol. 3(1), pp. 82-89, (2015).
11. Kohestani, V.R., Hassanlourad, M., and Ardakani, A., "Evaluation of liquefaction potential based on CPT data using random forest", Natural Hazards, pp. 1-11 (2015).
12. Kalinli, A., Acar, M.C., and Gündüz, Z., "New approaches to determine the ultimate bearing capacity of shallow foundations based on artificial neural networks and ant colony optimization", Engineering Geology, vol. 117, pp. 29-38, (2011).
13. Padmini, D., Ilamparuthi, K., and Sudheer, K., "Ultimate bearing capacity prediction of shallow foundations on cohesionless soils using neurofuzzy models", Computers and Geotechnics, vol. 35, pp. 33-46, (2008).
14. Samui, P., "Application of statistical learning algorithms to ultimate bearing capacity of shallow foundation on cohesionless soil", International Journal for Numerical and Analytical Methods in Geomechanics, vol. 36, pp. 100-110, (2012).
15. Tsai, H. C., et al., "Determining ultimate bearing capacity of shallow foundations using a genetic programming system", Neural Computing and Applications, vol. 23, pp. 2073-2084, (2013).
16. Bonakdar, L. and Etemad-Shahidi, A., "Predicting wave run-up on rubble-mound structures using M5 model tree", Ocean Engineering, vol. 38, pp. 111-118, (2011).
17. Etemad-Shahidi, A. and Mahjoobi, J., "Comparison between M5′ model tree and neural networks for prediction of significant wave height in Lake Superior", Ocean Engineering, vol. 36, pp. 1175-1181, (2009).
18. Rahimikhoob, A., "Comparison between M5 Model Tree and Neural Networks for Estimating Reference Evapotranspiration in an Arid Environment", Water Resources Management, vol. 28, pp. 1-13, (2014).
19. Wolfs, V. and Willems, P., "Development of discharge-stage curves affected by hysteresis using time varying models, model trees and neural networks", Environmental Modelling & Software, vol. 55, pp. 107-119, (2014).
20. Larose, D.T., "Discovering knowledge in data: an introduction to data mining", John Wiley & Sons, (2005).
21. Quinlan, J.R., "Learning with continuous classes", in Proceedings of the 5th Australian joint Conference on Artificial Intelligence. Hobart: Singapore, (1992).
22. Wang, Y. and Witten, I.H., "Inducing model trees for continuous classes", in Proceedings of the Ninth European Conference on Machine Learning. Prague, Czech Republic: Springer, (1997).
23. Foye, K., Salgado, R., and Scott, B., "Assessment of variable uncertainties for reliability-based design of foundations", Journal of geotechnical and geoenvironmental engineering, vol. 132, pp. 1197-1207, (2006).
24. Gandhi, G., "Study of bearing capacity factors developed from lab. Experiments on shallow footings on cohesionless soils", Ph. D. Thesis, Shri GS Institute of Tech and Science, Indore (MP), (2003).
25. Shahin, M.A., Maier, H.R., and Jaksa, M.B., "Data division for developing neural networks applied to geotechnical engineering", Journal of Computing in Civil Engineering, vol. 18, pp. 105-114, (2004).
26. Witten, I.H. and Frank, E., "Data Mining: Practical machine learning tools and techniques", Morgan Kaufman, (2005).
CAPTCHA Image