Harran Kili Şişme Potansiyelinin Belirlenmesinde Yapay Sinir Ağları Ve Çoklu Regresyon Modellerinin Kullanımı

Bu calısmada, Sanlıurfa Harran ovasında 33 ayrı lokasyondan elde edilen zemin orneklerinin sisme potansiyeli, farklı yontemlerle değerlendirilmistir. Standart Proctor enerji seviyesinde her bir numune icin ayrı ayrı belirlenen sıkışma eğrisi uzerinde optimum, optimumun ıslak (+%2) ve kuru yonundeki (-%2) su muhtevalarında sıkıstırılarak hazırlanan numunelerin sisme potansiyeli doğrudan deneylerle belirlenmistir. Elde edilen veriler, coklu regresyon ve yapay sinir ağları (YSA) esasında modeller olusturarak birlikte değerlendirilmistir. Sonucta, killerin sisme potansiyelinin tahmininde hem YSA hem de regresyon modellerinin oldukça etkili olduğu, ozellikle YSA modeli sonuclarının deney sonuclarına daha yakın değerler verdiği gorulmustur.

Anahtar Kelimeler:

Sisen zemin, yapay sinir ağları, çoklu regresyon.

Determination Of Swelling Potential Of Harran Clay Using Artifıcial Neural Network And Regression Models

In this study, the values of swelling potentiall of soils obtained from 33 different locations at the Sanlıurfa and Harran plains in Turkey are estimated by means of different methods. Swelling potential of soil samples compacted on the optimum, wet side (+2%) and dry side (-2%) on the compaction curve at the standard compaction effort were determined by using direct methods. The data obtained from direct measurements were evaluated with multiple regression (MRA) and artificial neural network (ANN) analyses. The results showed that both MRA and ANN are very efficient in predicting clay swelling potential. Furthermore, It was noted that the ANN is superior to MRA.

Keywords:

Swelling soil, artificial neural network, multiple regression,

PDF

___

[1] J.C., Parker, D.F., Amos and D.L., Kaster, “An evaluation of several methods of estimating soil volume change”, Soil Science Society of America Journal, Vol.41, pp.1059-1064, 1977
[2] F.H., Chen, “Foundation on Expansive Soils”, Elsevier, Amsterdam, The Netherlands, 1988.
[3] A.A.,Basma, A.S., Al-Hamoud, and A., Husein, “Laboratory assessment of swelling pressure of expansive soils”, Applied Clay Science 9, pp.355-365, 1995.
[4] W.S., Abdullah, K.A., Alshibli, and M.S., Al-Zou’bi, “Influence of pore water chemistry on the swelling behavior of compacted clays”, Applied Clay Science, 15, pp.447-462, 1999.
[5] A.A., Al-Rawas, R., Taha, J.D., Nelson, T.B., Al-Shap, and H., Al-Siyabi, “A comparative evaluation of various additives used in the stabilization of expansive soils”, Geotechnical Testing Journal, GTJODJ, Vol. 25, No.2, pp. 199-209, 2002.
[6] Y., Du, S., Li, and S., Hayashi, “Swell–shrinkage properties and soil improvement of compacted expansive soil, Ning-Liang Highway, China”, Engineering Geology, 53 , pp.351-358, 1999.
[7] H., Tosun, M., Türköz, Đ., Zorluer, ve A., Arslan, “Sıkısma kontrolü ile sisme potansiyelinin önlenmesi ve Harran killerinde (V.kısım) yapılan uygulamalar”, 3.GAP Mühendislik Kongresi, Bildiriler Kitabı, s.425-432, 24-26 Mayıs 2000, Sanlıurfa.
[8] Y. E.-A., Mohamedzein, R., Ibrahim, and A., Alsanosi, “Prediction of swelling pressure of expansive soils using Neural Networks”, Expansive Soils: Recent advances in characterization and treatment, Ed. Al-Rawas, A.A.,and Goosen,F.A., Chapter 17, pp.245-256, 2007.
[9] A. T. C., Goh, “Empirical design in geotechnics using neural networks.” Geotechnique, 45(4), pp.709-714, 1995b. [10] A. T. C., Goh, K. S., Wong, and B. B., Broms, “Estimation of lateral wall movements in braced excavation using neural networks.” Canadian Geotech. J., 32, pp.1059-1064, 1995.
[11] Y. M., Najjar, and H. E., Ali, “CPT-based liquefaction potential assessment: A neuronet approach.” Geotechnical Special Publication, ASCE, 1, pp.542-553, 1998.
[12] H. TOSUN, “Hafif su yapıları açısından sızan killerin önemi ve bir uygulama” Mühendislik Jeolojisi Türk Milli Komitesi Dergisi, sayı:14, s:94-109, 1992.
[13] J.A, Anderson, “Cognitive and psychological computation with neural models”, IEEE Transactions on Systems, Man and Cybernetics, V.SMC-13, pp:799-814, 1983.
[14] S.W., Liu, J.H., Huang, J.C., Sung, and C.C., Lee, “Detection of cracks using neural networks and computational mechanics”, Computer Methods in Applied Mechanics Engineering ;191, pp.2831-2845, 2002.
[15] J.J., Hopfield, “Neural networks and physical systems with emergent collective computational abilities”, Proc. Nat. Acad. Sci., 79, pp.2554-2558, 1982.
[16] P.J., Thomas, J.C., Baker, L.W., Zelazny, and D.R.,Hatch, “Relationship of map unit variability to shrink-swell indicators”, Soil Sci. Soc. Am. J., Vol.64, pp. 262-268, 2000.
[17] A., Komornik, and D., David, “ Prediction of swelling pressure of clays”, Journal of SMFE Div., ASCE, Vol. 95, No. SM1, pp. 209-225, 1969.