OSMAN GÜNAYDIN, BEKİR SAMİ TEZEKİCİ, Burak YILDIRIM, ALİ ÖZVAN

Kompaksiyon parametrelerinin yapay sinir ağları ile tahmini

Bu çalısmada zemin sınıflandırma deney sonuçları kullanılarak yapay sinir ağları (YSA) ile kompaksiyon parametreleri (maksimum kuru birim hacim ağırlık ve optimum su içeriği) tahmin edilmistir. Kompaksiyon parametreleri laboratuarda Proktor deneyleri ile belirlenmektedir. Sıkıstırılmıs zeminler; yol dolgularında, katı atık depolama alanlarında, toprak dolgu barajların çekirdeklerinde, istinat yapılarında ve buna benzer önemli mühendislik projelerinde yaygın olarak kullanılmaktadır. Dolayısıyla bu tür zeminler geotekniğin uygulama alanlarında oldukça önemli bir yere sahiptir. Bu çalısmada kompaksiyon parametrelerinin tahmininde kullanılan veriler Türkiye genelinde yapılan yol çalısmalarından temin edilmistir. Yapay sinir ağı modellerinde giris olarak, ince tane oranı, kum oranı, çakıl oranı, likit limit, plastik limit değerleri kullanılarak maksimum kuru birim hacim ağırlık ile optimum su içeriği belirlenmeye çalısılmıstır. Yapay sinir ağları ve zemin sınıflandırma deneyleri ile kompaksiyon parametreleri arasında güçlü korelasyonlar (R2=0.88-0.78-0.71) elde edilmistir. Yapay sinir ağları ile elde edilen bu korelasyonlar oldukça güvenilir sonuçlar vermektedir.

Estimation of compaction parameters using artificial neural networks

This study presents the application of artificial neural Networks (ANN) for the estimation of the compaction parameters (maximum dry unit weight and optimum moisture content) from classification properties of the soils. Compaction parameters can only be defined experimentally by Proctor tests. Compacted soils are used for many geotechnical applications such as engineered barriers for municipal solid waste, dams, embankment and roads; therefore they are important material for geotechnical purposes. The data collected from the road construction in some areas of Turkey were used for the estimation of soil compaction parameters. Different parameters, fine-grained ratio, sand ratio, gravel ratio, liquid limit, plastic limit, and maximum dry density (MDD) and optimum moisture content (OMC) were presented to ANN model as inputs. Artificial neural network estimation indicated strong correlations (R2=0.88-0.78-0.71) between the compaction parameters and soil classification properties. It has been shown that the correlation equations obtained as a result of artificial neural network analyses are in satisfactory agreement with the test results.

PDF

___

1. Holtz,R.D., Kovacs,W.D., “An Introduction to Geotechnical Engineering”, Prentice-Hall, Eaglewood Cliffs, 1981.
2. Jumikis,A.R., “Geology and soils of the Newark (NJ) metropolitan area”, J Soil Mech Found ASCE 93(SM2): 71–95, 1946.
3. Jumikis,A.R., “Geology and soils of the Newark (NJ) metropolitan area”, ASCE J Soil Mech Found Div 94(2), 1958.
4. McRae,J.L., “Index of compaction characteristics”, In: Symposium on application of soil testing in highway design and construction, ASTM Special Technical Publication No. 239, pp 119–127, 1958.
5. Joslin,J.G., “Ohio’s typical moisture-density curve”, ASTM STP 239:111–118, 1959.
6. Johnson,A.W. and Sallberg,J.R., “Factors Influencing Compaction Results”, Highway Research Board Bulletin, No. 319, 125, 1962.
7. Foreman,E.D. and Daniel,D.E., “Permeation of Compacted Clay With Organic Chemicals”, Journal of the Geotechnical Engineering Division, ASCE, 112, No. 7, 669– 681, 1986.
8. Sridharan,A., Rao,S.M. and Joshi,S., “Classification of Expansive Soils by Sediment Volume Method”, Geotechnical Testing Journal, 13, No. 4, 375–380, 1990.
9. Benson,C.H. and Trast,J.M., “Hydraulic Conductivity of Thirteen Compacted Clays”, Clays and Clay Minerals, 43, No. 6, 669–68, 1995.
10. Sridharan,A., Nagaraj,H.B., “Plastic Limit and Compaction Characteristics of Finegrained Soils”, Ground Improvement, 9, No. 1, 17-22, 2005.
11. Al-Khafaji,A.N., “A Simple Approach to the Estimation of Soil Compaction Parameters”, Quarterly Journal of Engineering Geology, 20, 15-30, 1987.
12. Hausmann,M.R., “Engineering Principals of Ground Modification”, McGraw- Hill Book Co., Singapore, 1990.
13. Nagaraj,H.B., “Prediction of engineering properties of finegrained soils from their index properties”, PhD Thesis, Indian Institute of Science, Banalore, 2000.
14. Sridharan,A., Gurtug,Y., “Compressibility characteristics of soils”, Geotechn Geol Eng 23:615–634, 2005.
15. Najjar,Y.M., Basheer,I.A., Naouss,W.A., “On the identification of compaction characteristics by neuronets”, Comput Geotech 18(3):167–187, 1996.
16. Lee,I.M., Lee,J.H., “Prediction of pile bearing capacity using artificial neural Networks” Comput Geotech 18(3):189-200, 1996.
17. Yuanyou,X., Yanming,X., Ruigeng,Z., “An engineering geology evaluation method based on an artificial neural network and its application”, Eng Geol 47:149- 156, 1997.
18. Yang,Y., Zhang,Q., “The applications of neural networks to rock engineering systems (RES)”, Int J Rock Mech Min Sci 35(6):727–745, 1998.
19. Hurtado,J.E., Londono,J.M., Meza,M.A., “On the applicability of neural networks for soil dynamic amplification analysis”, Soil Dyn Earthquake Eng 21:579- 91, 2001.
20. Rafiq,M.Y., Bugmann,G., Easterbrook,D.J., “Neural network design for engineering applications”, Comput Struct 79:1541–1552, 2001.
21. Lee,S.J., Lee,S.R., Kim,Y.S., “An approach to estimate unsaturated shear strength using artificial neural network and hyperbolic, formulation”, Comput Geotech 30:489–503, 2003.
22. Basma,A.A., Kalas,N., “Modeling soil collapse by artificial neural Networks”, Geotech Geol Eng. 22:427–438, 2004.
23. Günaydın,O., “Estimation of soil compaction parameters by using statistical analyses and artificial neural Networks”, Environ.Geol., DOI 10.1007/s00254-008- 1300-6.
24. Öztemel,E., “Yapay Sinir Ağları”, sf 29, Papatya Yayıncılık, İstanbul, 2003.
25. Smith,G.N., “Probability and statistics in civil engineering”, London, Collins, 1986.