Zeminlerin dispersibilite sınıfının XRF analiz sonuçlarına dayalı olarak Genetik Programlama (GP) ile tahmini

Öz

Dispersif zeminler, dolgu barajların çekirdek yapısında kullanıldığında erozyon hassasiyetlerinin çok yüksek olması nedeniyle içsel erozyona neden olarak bu tür barajların göçmesine neden olmaktadırlar. Bu tür zeminlerin tasarım aşamasında belirlenerek dolgu barajların inşaatında kullanılmaması gerekmektedir. Dispersif zeminler; fiziksel (dağılma deneyi, çifte hidrometre deneyi ve iğne deliği deneyi) ve kimyasal (boşluk sıvısının kimyasal içeriği) deneyler ile belirlenebilmektedir. Bu çalışmada ise alternatif bir yöntem olarak XRF (X-Işını Floresans) analiz sonuçları kullanılarak genetik programlama (GP) yardımıyla zeminlerin dispersibilite sınıfının tahmin edilebilmesi için bilgisayar modelleri geliştirilmiştir. Genetik İfade Programlama (GİP) ile oluşturulan tahmin modellerinde kullanılan 181 adet verinin % 66.9’u eğitim verisi; geri kalan ise ise test verisi olarak kullanılmıştır. Majör (SiO2, Al2O3) ve minör (MgO, CaO, Na2O, K2O) oksitlerin girdi verisi olarak kullanıldığı bilgisayar modellerinde zeminler dispersif (D) ve dispersif olmayan zeminler (ND) olarak yüksek oranlarda başarılı bir şekilde tahmin edilmektedir. En başarılı tahmin modeli tüm veri seti içinde SiO2, Al2O3, MgO, CaO ve Na2O girdi verilerinden oluşan modeldir.

Anahtar Kelimeler

• XRF analizi
• Dolgu baraj
• Dispersif zemin
• Genetik programlama
• XRF analizi

Prediction of dispersibility class of soils with Genetic Programming (GP) based on XRF analysis results

Abstract

When dispersive soils are used in the core structure of embankment dams, due to their high erosion sensitivity, they cause internal erosion and cause such dams to collapse. Such soils should be determined at the design stage and not used in the construction of fill dams. Dispersive soils can be determined by physical (Crumb test, double hydrometer test and pinhole test) and chemical (chemical content of the pore fluid) experiments. In this study, as an alternative method, computer models have been developed to predict the dispersibility class of soils with the help of genetic programming (GP) using XRF (X-Ray Fluorescence) analysis results. 66.9% of the 181 data used in prediction models created with Genetic Expression Programming (GEP) are training data; the remainder was used as test data. In computer models where major (SiO2, Al2O3) and minor (MgO, CaO, Na2O, K2O) oxides are used as input data, soils are successfully predicted as dispersive (D) and non-dispersive soils (ND) at high rates. The most successful forecasting model is the one that consists of SiO2, Al2O3, MgO, CaO and Na2O input data in the entire data set.

Keywords

• Embankment dam
• Dispersive soil
• Genetic programming
• XRF analysis

Kaynakça

1. H.E. Middleton, 1930, The properties of soils which influence erosion, Tech. Bull, U.S. Dept. Agri., 178: 1-16,1930.
2. G.M. Volk, Method of determination of degree of dispersion of the clay fraction of soils, Proceedings Soil Science Society of America, 2, 561-567,1937.
3. A. Maharaj and P. Paige-Green, P., The SCS double hydrometer test in dispersive soil identification, In The 18th International Conference on Soil Mechanics and Geotechnical Engineering, Paris, 2-6, France, 2013.
4. R.S. Decker and L.P. Dunnigan, L.P., Development and use of the Soil Conservation Service Dispersion Test, J. Sherard, R. Decker (Eds), In STP623-EB Dispersive Clays, Related Piping, and Erosion in Geotechnical Projects, West Conshohocken, PA: ASTM International, 94-109, 1977.
5. G.D. Aitchison, O.G. Ingles and C.C. Wood C.C, Post-construction deflocculation as a contributory factor in the failure of earth dams, In: Fourth Australia-New Zealand conference on soil mechanics and foundation engineering, Australia, 275-279, 1963,
6. F.A. Gerber, and V.M. Harmse, Proposed procedure for identification of dispersive soils by chemical testing, Civil Engineer in South Africa, 29(10), 397-399, 1987.
7. P. Paige-Green, Dispersive and erodible soils – Fundamental differences, SAIEG/ SAICE Problem Soils Conference, 59-67, Midrand, November 2008.
8. W.W. Emerson, A Classification of soil aggregates based on their coherence in water, Australian Journal of Soil Research 5, 47-57, 1967.

9. J.L. Sherard, E.F. Steele, R.S. Decker and L.P. Dunnigan, Pinhole test for identifying dispersive soils, Journal of the Geotechnical Engineering Division, 102(1), 69-85, 1976.
10. J.L. Sherard, L.P. Dunnigan and R.S. Decker, Identification and nature of dispersive soils, Journal of the Geotechnical Engineering Division, 102, No. GT4, 298-312. 1976.
11. H. Savaş, 2008, Development on pinhole test adopted to identify the dispersive clays used for earthfill dams and a comparative study, Ph.D. Thesis, Department of Civil Engineering, Eskişehir Osmangazi University, Turkey (In Turkısh).
12. I. Zorluer, Y. Icaga, S. Yurtcu and H. Tosun, Application of a fuzzy rule-based method for the determination of clay dispersibility, Geoderma, 160(2), 189-196, 2010. https://doi.org/10.1016/j.geoderma.2010.09.017.
13. P. Rengasamy and A. Marchuk, A., 2011, Cation ratio of soil structural stability (CROSS), Soil Research, 49(3), 280-285, 2011.
14. P. Rengasamy, P.E. Tavakkoli and G.K. McDonald, Exchangeable cations and clay dispersion: net dispersive charge, a new concept for dispersive soil, European Journal of Soil science, 67(5), 659-665. 2016. https://doi.org/10.1111/ejss.12369.
15. A. Turgut, N.S. Isik and K.E. Kasapoglu, Investigation of factors affecting the dispersibility of clays and estimation of dispersivity, Bulletin of Engineering Geology and the Environment, 76(3), 1051-1073, 2017. https://doi.org/10.1007/s10064-016-0935-x.
16. A.A.R. Heshmati, H. Salehzade, A.H. Alavi, A.H. Gandomi, A. Badkobeh and A. Ghasemi, A., On the applicability of linear genetic programming for the formulation of soil classification, American-Eurasian J. Agric. Environ. Sci, 45, 575-583. 2008.
17. S.K. Das, P.K. Muduli, Evaluation of liquefaction potential of soil using genetic programming, In Proceedings of the Golden Jubilee Indian Geotechnical Conference, Kochi, India, 827- 830, 2011.
18. G.D. Öget, Estimating Swelling Characteristics of Clays Using Methylene Blue Test -A Machine Learning Approach, The Degree of Master of Science, Civil Engineering Department, Middle East Technical University, 2014.
19. E. Çöleri, Relationship Between Resilient Modulus and Soil Index Properties of Unbound Materials, The Degree of Master of Science, Civil Engineering Department, Middle East Technical University, 2007.
20. L. Scrucca, GA: A package for genetic algorithms in R, Journal of Statistical Software, 53(1), 1-37, 2013. https://doi.org/10.18637/jss.v053.i04.
21. J.R. Koza, Genetic Programming, The MIT Press, Cambridge, Massachusetts, 1992.
22. A. Pourzangbar, Determination of the most effective parameters on scour depth at seawalls using genetic programming (GP). In The 10th International Conference on Coasts, Ports and Marine Structures (ICOPMASS 2012), Tehran, Iran, 9p, November 2012.
23. C. Ferreira, Gene expression programming: a new adaptive algorithm for solving problems, Complex Systems,13,87-129,2001. https://doi.org/10.48550/ arXiv.cs/0102027.
24. P. Brouwer, Theory of XRF, PANalytical BV, Almelo, Netherlands, 2006.
25. H. Tosun, İ. Zorluer, H. Tozluk, ve H. Savaş, Toprak Dolgu Barajlarda Dispersif Killerin Kullanımı ve Tasarım ve Kontrol Kriterlerinin Araştırılması, TÜBİTAK, İNTAG-719, 2001.
26. R. Fell, Geotechnical Engineering of Dams, CRC press, Boca Raton, 2005.
27. J. K. Mitchell and K. Soga, Fundamentals of Soil Behavior (Vol. 3), John Wiley & Sons, New York, 2005.
28. P. S. Nayak and B. K. Singh, Instrumental characterization of clay by XRF, XRD and FTIR, Bulletin of Materials Science, 30(3), 235-238, 2007. https://doi.org/10.1007/s12034-007-0042-5.
29. F. G. Bell and D. J. H. Walker, A further examination of the nature of dispersive soils in Natal, South Africa, Quarterly Journal of Engineering Geology and Hydrogeology, 33(3), 187-199, 2000. https://doi.org/10.1144/qjegh.33.3.187.
30. S. Alam, B.K. Das and S. K. Das, Dispersion and sedimentation characteristics of red mud, Journal of Hazardous, Toxic, and Radioactive Waste, 22(4), 04018025(1-10),2018. https://doi.org/10.1061/(ASCE) HZ.2153-5515.0000420.
31. M. Belen ve E. Pınarcı, Atatürk Barajı kil çekirdeğinde kullanılan malzemenin dispersivite özelliğinin araştırılması, MÜHJEO’2017: Ulusal Mühendislik Jeolojisi ve Jeoteknik Sempozyumu, sayfa 277-284, Adana, Türkiye, 12-14 Ekim 2017.
32. M. Y. Evans, The Geology, sedimentology, geochronology and palaeo-environmental reconstruction of the Heelbo Hillslope deposit, free state province, South Africa, Ph.D Thesis, University of the Witwatersrand, Johannesburg,South Africa, 2015.
33. S. Matsumoto, S. Ogata, H. Shimada, T. Sasaoka, A. Hamanaka and G.J. Kusuma, Effects of pH-induced changes in soil physical characteristics on the development of soil water erosion, Geosciences, 8(4), 134(1-13),2018. https://doi.org/10.3390/geosciences 8040134.
34. S. Mohanty, N. Roy, S.P. Singh and P. Sihag, Effect of industrial by-products on the strength of stabilized dispersive soil, International Journal of Geotechnical Engineering, 15(4), 405-417, 2021. https://doi.org/ 10.1080/19386362.2019.1654281.
35. W. E. Worrall, Clays and ceramic raw materials, Elsevier Applied Science, New York, 1986.
36. S. Nasseh, G.R. Lashkaripour and M. Ghafoori, Evaluation of Mineralogical Characteristics and Erosion of Tous Historic Mud Wall, Ne of Iranl, Australian Journal of Basic and Applied Sciences, 5(5), 919-925, 2011.
37. A. K. Panda, B.G. Mishra, D.K. Mishra, and R.K. Singh, Effect of sulphuric acid treatment on the physico-chemical characteristics of kaolin clay. Colloids and Surfaces A: Physicochemical and Engineering Aspects, 363(1-3),98-104,2010. https://doi.org/10.1016/ j.colsurfa.2010.04.022.
38. N.S. Phillips, Disaggregation of soil during slurry pipe jacking, Ph.D Thesis, University of London, London, U. Kingdom, 2015.
39. P.T Shourijeh, A. Soroush and A.H. Daneshi-Sadr, The effects of lime, bentonite and nano-clay on erosion characteristics of clay soils, European Journal of Environmental and Civil Engineering, 26(9), 3762-3787, 2022. https://doi.org/10.1080/19648189.2020.1818629.
40. A.H. Vakili, M.R. bin Selamat, H.B.A Aziz, A. Mojiri, Z. Ahmad and M. Safarzadeh, Treatment of dispersive clay soil by ZELIAC, Geoderma, 285, 270-279, 2017. https://doi.org/10.1016/j.geoderma.2016.10.009.
41. A. H. Vakili, M. Kaedi, M. Mokhberi, M.R. bin Selamat and M. Salimi, Treatment of highly dispersive clay by lignosulfonate addition and electroosmosis application, Applied Clay Science, 152, 1-8, 2018, https://doi.org/10.1016/j.clay.2017.11.039.
42. A.H. Vakili, J. Ghasemi, M.R. bin Selamat, M. Salimi and M.S. Farhadi, Internal erosional behaviour of dispersive clay stabilized with lignosulfonate and reinforced with polypropylene fiber, Construction and Building Materials, 193, 405-415, 2018. https://doi.org/10.1016/j.conbuildmat.2018.10.213.
43. A. H. Vakili, S.I. Shojaei, M. Salimi, M.R. bin Selamat and M.S. Farhadi, Contact erosional behaviour of foundation of pavement embankment constructed with nanosilica-treated dispersive soils, Soils and Foundations, 60(1), 167-178, 2020. https://doi.org/ 10.1016/j.sandf.2020.02.001.
44. S. Topçu, İnce Daneli Zeminlerin Farklı Gerilme Koşullarında İçsel Erozyon Davranışının Mukayeseli Analizi, Doktora Tezi, Eskişehir Osmangazi Üniversitesi Fen Bilimleri Enstitüsü, Türkiye, 2020.
45. G. Sankar, K.V. Ajay, S.L. Kuriakose, P.R. Prasobh, C. Deepa and K. Eldhose, Studies on soil piping in the highlands and foot hills of Kerala to avoid the disaster, Final Report NCESS-PR-01-2020, January 2020.
46. A.J. Bloodworth, D.E. Highley and C.J. Mitchell, Industrial minerals laboratory manual: Kaolin, British Geological Survey, Technical Report WG/93/1, 1993.