BibTex RIS Cite

Yapay Sinir Ağı Kullanılarak CPT Tabanlı Sıvılaşma Değerlendirme Abağının Geliştirilmesi.

Year 2015, , 45 - 59, 23.12.2015
https://doi.org/10.17824/yrb.47944

Abstract

Depremler sırasında suya doygun kohezyonsuz (veya düşük kohezyonlu) zeminlerde gelişen sıvılaşma olayı etkilediğialanlarda yapısal hasarları arttırarak çok sayıda can ve mal kayıplarına neden olmaktadır. Yeraltı su seviyesininyüzeye yakın olduğu ve depremselliği yüksek bölgelerdeki suya doygun kumlu ve siltli toprak zeminlerin,sıvılaşmaya olan yatkınlığı bilinmektedir. Bununla birlikte, bu tür zeminlerde zeminin sıkılığını da yansıtan standartpenetrasyon testi (SPT) ve/veya konik penetrasyon testi (CPT), makaslama dalgası hızı (Vs) gibi yerinde uygulanandeney verilerinin de girdi olarak kullanıldığı yöntemlerle zeminlerin sıvılaşmaya karşı güvenlik katsayısı (FL) hesaplanabilmektedir.SPT, CPT ve Vs verilerini girdi olarak kullanan bu yöntemler ampirik yaklaşımlar olup, her ampirikyöntemde olduğu gibi artan veri sayısına bağlı olarak bu yöntemler de gelişmeye açıktırlar. Bu ampirik yaklaşımlarınşekillendirilmesinde kullanılan veriler sıvılaşmaya duyarlı alanlarda meydana gelen depremler sonucunda eldeedildikleri için, yapay olarak üretilmeleri zor olup, bu nedenle verilerin bilimsel değerleri de oldukça yüksektir. SPT,CPT ve Vs verilerinin girdi olarak kullanıldığı üç yöntemde de sıvılaşmanın varlığı ile yokluğu arasındaki sınır eğrilerimevcut gerçek verilere uydurularak çizilmiş olup, analizlerde kullanılmak üzere bazı eşitliklerle tanımlanmışlardır.Diğer bir ifadeyle, bu eğrisel sınırların çizilmesinde analitik (veya bir hesabı dikkate alan) yaklaşımdan ziyade veriyedayalı uzmanların görüşleri kullanılmıştır.Bu çalışma kapsamında, 1999 yılında Tayvan’daki Chi-Chi depremi sonrasında CPT deneylerinin de yapıldığı, sıvılaşmagözlenen ve gözlenmeyen sahalara ait olan ve Ku vd. (2004) tarafından raporlanan veri tabanı kullanılmıştır.Robertson ve Wride (1998) tarafından önerilen CPT tabanlı yaklaşımdaki normalize edilmiş konik uç direnci (qc1N)ve çevrimsel gerilim oranı (CSR7.5) girdi parametreleri olarak kullanılırken, sıvılaşmanın varlık (1) ve yokluk (0) bilgisiise çıktı olarak kullanılmıştır. qc1N ve CSR7.5 girdilerine bağlı olarak sıvılaşmanın varlığı (1) veya yokluğu (0) bilgisineanalitik olarak ulaşmak için son yıllarda yerbilimleri alanında da başarıyla uygulanan yapay sinir ağı (Artificial NeuralNetwork, ANN) öğrenme yöntemi kullanılmıştır. Öğrenme aşamasının devamında ise CPT tabanlı abaktaki qc1N veCSR7.5 değerlerinin olası kombinasyonları ANN modelinde girdi parametresi olarak kullanılarak 1 ile 0 arasında çıktıolarak elde edilen sıvılaşma varlığı veya yokluğuna yatkınlık değerleri ile hesaplanmıştır. Öğrenme sonrasında ANNmodeliyle tüm abağı kapsayarak üretilen veri seti kullanılarak CPT tabanlı sıvılaşma değerlendirme abağı geliştirilmiştir.

References

  • Aksoy, H., ve Ercanoğlu, M., 2006. Determina- tion of the rockfall source in an urban settlement area by using a rule-based fuzzy evaluation, Natural Hazards and Earth System Science, 6, 941-954.
  • Alvarez Grima, M., 2000. Neuro-fuzzy Modelling in Engineering Geology, Balkema, Rot- terdam, 244p.
  • Ambraseys, N., 1985. Intensity-attenuation and magnitude-intensity relationships for northwest European earthquakes. Journal of Earthquake Engineering & Structural Dynamics, 3, 733-778.
  • Andrus, R. D., ve Stokoe, K. H., 2000. Liquefac- tion resistance of soils from shear-wave velocity, Journal of Geotechnical and Geoenviromental Engineering, ASCE, 126, 11, 1015-1025.
  • Arango, I., 1996. Magnitude scaling factors for soil liquefaction evaluations, Journal of Geotechnical Engineering, ASCE, 122, 11, 929-936.
  • Aydan, Ö., Ulusay, R., Kumsar, H. ve Tuncay, E., 2000. Site investigation and enginee- ring evaluation of the Düzce-Bolu Eart- hquake of November 12, 1999, Turkish Earthquake Foundation, TDV/DR 095- 51, 307.
  • Basheer, I.A., ve Hajmeer, M., 2000. Artificial neural networks: fundamentals, com- puting, design, and application, Journal of Microbiological Methods, 43, 3-31.
  • Çetin, K.Ö., Der Kiureghian, A., ve Seed, R.B., 2002. Probabilistic models for the initi- ation of seismic soil liquefaction, Struc- tural Safety, 24, 67-82.
  • Çetin, K.Ö. ve Ozan, C., 2009. CPT-Based Probabilistic Soil Characterization and Classification, Journal of Geotechnical and Geoenvironmental Engineering, 135, 1, 84-107.
  • Ercanoğlu, M., 2005. Landslide susceptibility assessment of SE Bartın (West Black Sea Region, Turkey) by artificial neural networks, Natural Hazards and Earth System Science, 5, 979-992.
  • Ermini, L., Catani, F., ve Casagli, N., 2005. Arti- ficial Neural Networks applied to land- slide susceptibility assessment, Geo- morphology, 66, 327-343.
  • Goh, A.T.C., Wong, K.S., ve Broms, B.B., 1995. Estimation of lateral wall movements in braced excavations using neural net- works, Can Geotechnical Journal, 32, 1059-1064.
  • Gomez, H., ve Kavzoğlu, T., 2005. Assessment of shallow landslide susceptibility using artificial neural networks in Jabonosa River Basin, Venezuela, Engineering Geology, 78, 11-27.
  • Hecht-Nielsen, R., 1987. Kolmogorov’s map- ping neural network existence theorem, Proceedings of the First IEEE Interna- tional Conference on Neural Networks, USA, 11-14.
  • Huang, Y., ve Wanstedt, S., 1998. Application of Kalman learning algorithm multila- yer neural network to estimates of ore grades, International Journal of Mining, Reclamation and Environment, 12, 19- 27.
  • Hush, D.R., 1989. Classification with neural net- works: a performance analysis, Proc. of the IEEE International Conference on Systems Engineering, USA, 277-280.
  • Kaastra, I., ve Boyd, M., 1996. Designing a neu- ral network for forecasting financial and economic time series, Neurocomputing, 10, 3, 215-236.
  • Kanellopoulas, I., ve Wilkinson, G.G., 1997. Strategies and best practice for neural network image classification, Interna- tional Journal of Remote Sensing, 18, 711-725.
  • Kayen, R., Moss, R.E.S., Thompson, E.M.,. Seed, R.B., Çetin, K.Ö., Der Kiureghian, A., Tanaka, Y., ve Tokimatsu, K., 2013. Shear-Wave Velocity–Based Probabi- listic and Deterministic Assessment of Seismic Soil Liquefaction Potential, Jo- urnal of Geotechnical and Geoenviron- mental Engineering, 140,4, 07014006.
  • Ku, C.S., Lee, D.H., ve Wu, J.H., 2004. Evalu- ation of soil liquefaction in the Chi-Chi,
  • Taiwan earthquake using CPT, Soil
  • Dynamics and Earthquake Engineering 24, 9-10, 659-673.
  • Lee, S., Ryu, J.H., Lee, M.J., ve Won, J.S., 2003. Use of an artificial neural network for analysis of the susceptibility to landsli- des at Boun, Korea, Environmental Ge- ology, 44, 820-833.
  • Masters, T., 1994. Practical Neural Network Re- cipes in C++, Academic Press, ISBN 0-12-479040-2.
  • Neaupane, K.M., ve Achet, S.H., 2004. Use of backpropagation neural network for landslide monitoring: a case study in the higher Himalaya, Engineering Geo- logy, 74, 213-236.
  • Ripley, B.D., 1993. Statistical aspects of neu- ral net-works, In: Barndoff-Neilsen OE,
  • Jensen JL, Kendall WS (Eds.), Networks
  • and Chaos-Statistical and Probabilistic
  • Aspects, Chapman&Hall, London, 40- 123.
  • Robertson, P.K., ve Wride, C.E., 1998. Evalua- ting Cyclic Liquefaction Potential Using the Cone Penetration Test, Canadian Geotechnical Journal, 35, 442-459.
  • Seed, H.B., ve Idriss, I.M., 1971. Simplified Pro- cedure for Evaluating Soil Liquefaction Potential, ASCE Journal of Geotechni- cal Engineering, 97, 9, 1249-1273.
  • Seed, H. B., ve Idriss, I. M., 1982. Ground mo- tions and soil liquefaction during earth- quakes, Earthquake Engineering Re- search Institute Monograph, Oakland, California.
  • Shi, J., Ortiago, J.A.R., ve Bai, J., 1998. Modu- lar neural networks for predicting sett- lements during tunnelling, Journal of Geotechnical and Geoenvironmental Engineering. ASCE, 124, 5, 389-394.
  • Sönmez, H., Gökçeoğlu C., Medley, E.W., Tun- cay, E., ve Nefeslioglu, H.A., 2006. Estimating the uniaxial compressive strength of a volcanic “bimrock”, In- ternational Journal of Rock Mechanics and Mining Science, 43, 554-561.
  • Sönmez, H., Coşkun, A., Ercanoğlu, M., Türer, D., Kasapoğlu, K.E., ve Tunusluoğ- lu, C., 2014. Artificial Neural Network (ANN) Based Model for Predicting of Overall Strength of Volcanic Bimrock, Proc ISRM European Rock Mechanics Symposium, EUROCK 2014, Spain, 83- 87.
  • Ulusay, R., 2010. Uygulamalı Jeoteknik Bilgiler,
  • TMMOB Jeoloji Mühendisleri Odası Ya
  • yınları, No: 38, Ankara.
  • Wang, C., 1994. A theory of generalization in learning machines with neural appli- cation, PhD Thesis, The University of Pennsylvania, USA.
  • Yeşilnacar, E.K., ve Topal, T., 2005. Landslide Susceptibility Mapping: comparison between logistic regression and neu- ral networks in a medium scale study, Hendek region TURKEY, Engineering Geology, 79, 251-266.
  • Youd, T.L., ve Idriss, I.M., 2001. Liquefaction Resistance of Soils: Summary Report from the 1996 NCEER and 1998 NCE- ER/NSF Workshop on Evaluation of Li- quefaction Resistance of Soils, ASCE Journal of Geotechnical Engineering, 127, 4, 297-313.
  • Youd, T. L., ve Noble, S. K., 1997. Liquefaction criteria based on statistical and proba- bilistic analyses, Proceedings, NCEER Workshop on Evaluation of Liquefacti- on Resistance of Soils, National Centre for Earthquake Engineering Research, State University of New York at Buffalo, 201-215.
Year 2015, , 45 - 59, 23.12.2015
https://doi.org/10.17824/yrb.47944

Abstract

References

  • Aksoy, H., ve Ercanoğlu, M., 2006. Determina- tion of the rockfall source in an urban settlement area by using a rule-based fuzzy evaluation, Natural Hazards and Earth System Science, 6, 941-954.
  • Alvarez Grima, M., 2000. Neuro-fuzzy Modelling in Engineering Geology, Balkema, Rot- terdam, 244p.
  • Ambraseys, N., 1985. Intensity-attenuation and magnitude-intensity relationships for northwest European earthquakes. Journal of Earthquake Engineering & Structural Dynamics, 3, 733-778.
  • Andrus, R. D., ve Stokoe, K. H., 2000. Liquefac- tion resistance of soils from shear-wave velocity, Journal of Geotechnical and Geoenviromental Engineering, ASCE, 126, 11, 1015-1025.
  • Arango, I., 1996. Magnitude scaling factors for soil liquefaction evaluations, Journal of Geotechnical Engineering, ASCE, 122, 11, 929-936.
  • Aydan, Ö., Ulusay, R., Kumsar, H. ve Tuncay, E., 2000. Site investigation and enginee- ring evaluation of the Düzce-Bolu Eart- hquake of November 12, 1999, Turkish Earthquake Foundation, TDV/DR 095- 51, 307.
  • Basheer, I.A., ve Hajmeer, M., 2000. Artificial neural networks: fundamentals, com- puting, design, and application, Journal of Microbiological Methods, 43, 3-31.
  • Çetin, K.Ö., Der Kiureghian, A., ve Seed, R.B., 2002. Probabilistic models for the initi- ation of seismic soil liquefaction, Struc- tural Safety, 24, 67-82.
  • Çetin, K.Ö. ve Ozan, C., 2009. CPT-Based Probabilistic Soil Characterization and Classification, Journal of Geotechnical and Geoenvironmental Engineering, 135, 1, 84-107.
  • Ercanoğlu, M., 2005. Landslide susceptibility assessment of SE Bartın (West Black Sea Region, Turkey) by artificial neural networks, Natural Hazards and Earth System Science, 5, 979-992.
  • Ermini, L., Catani, F., ve Casagli, N., 2005. Arti- ficial Neural Networks applied to land- slide susceptibility assessment, Geo- morphology, 66, 327-343.
  • Goh, A.T.C., Wong, K.S., ve Broms, B.B., 1995. Estimation of lateral wall movements in braced excavations using neural net- works, Can Geotechnical Journal, 32, 1059-1064.
  • Gomez, H., ve Kavzoğlu, T., 2005. Assessment of shallow landslide susceptibility using artificial neural networks in Jabonosa River Basin, Venezuela, Engineering Geology, 78, 11-27.
  • Hecht-Nielsen, R., 1987. Kolmogorov’s map- ping neural network existence theorem, Proceedings of the First IEEE Interna- tional Conference on Neural Networks, USA, 11-14.
  • Huang, Y., ve Wanstedt, S., 1998. Application of Kalman learning algorithm multila- yer neural network to estimates of ore grades, International Journal of Mining, Reclamation and Environment, 12, 19- 27.
  • Hush, D.R., 1989. Classification with neural net- works: a performance analysis, Proc. of the IEEE International Conference on Systems Engineering, USA, 277-280.
  • Kaastra, I., ve Boyd, M., 1996. Designing a neu- ral network for forecasting financial and economic time series, Neurocomputing, 10, 3, 215-236.
  • Kanellopoulas, I., ve Wilkinson, G.G., 1997. Strategies and best practice for neural network image classification, Interna- tional Journal of Remote Sensing, 18, 711-725.
  • Kayen, R., Moss, R.E.S., Thompson, E.M.,. Seed, R.B., Çetin, K.Ö., Der Kiureghian, A., Tanaka, Y., ve Tokimatsu, K., 2013. Shear-Wave Velocity–Based Probabi- listic and Deterministic Assessment of Seismic Soil Liquefaction Potential, Jo- urnal of Geotechnical and Geoenviron- mental Engineering, 140,4, 07014006.
  • Ku, C.S., Lee, D.H., ve Wu, J.H., 2004. Evalu- ation of soil liquefaction in the Chi-Chi,
  • Taiwan earthquake using CPT, Soil
  • Dynamics and Earthquake Engineering 24, 9-10, 659-673.
  • Lee, S., Ryu, J.H., Lee, M.J., ve Won, J.S., 2003. Use of an artificial neural network for analysis of the susceptibility to landsli- des at Boun, Korea, Environmental Ge- ology, 44, 820-833.
  • Masters, T., 1994. Practical Neural Network Re- cipes in C++, Academic Press, ISBN 0-12-479040-2.
  • Neaupane, K.M., ve Achet, S.H., 2004. Use of backpropagation neural network for landslide monitoring: a case study in the higher Himalaya, Engineering Geo- logy, 74, 213-236.
  • Ripley, B.D., 1993. Statistical aspects of neu- ral net-works, In: Barndoff-Neilsen OE,
  • Jensen JL, Kendall WS (Eds.), Networks
  • and Chaos-Statistical and Probabilistic
  • Aspects, Chapman&Hall, London, 40- 123.
  • Robertson, P.K., ve Wride, C.E., 1998. Evalua- ting Cyclic Liquefaction Potential Using the Cone Penetration Test, Canadian Geotechnical Journal, 35, 442-459.
  • Seed, H.B., ve Idriss, I.M., 1971. Simplified Pro- cedure for Evaluating Soil Liquefaction Potential, ASCE Journal of Geotechni- cal Engineering, 97, 9, 1249-1273.
  • Seed, H. B., ve Idriss, I. M., 1982. Ground mo- tions and soil liquefaction during earth- quakes, Earthquake Engineering Re- search Institute Monograph, Oakland, California.
  • Shi, J., Ortiago, J.A.R., ve Bai, J., 1998. Modu- lar neural networks for predicting sett- lements during tunnelling, Journal of Geotechnical and Geoenvironmental Engineering. ASCE, 124, 5, 389-394.
  • Sönmez, H., Gökçeoğlu C., Medley, E.W., Tun- cay, E., ve Nefeslioglu, H.A., 2006. Estimating the uniaxial compressive strength of a volcanic “bimrock”, In- ternational Journal of Rock Mechanics and Mining Science, 43, 554-561.
  • Sönmez, H., Coşkun, A., Ercanoğlu, M., Türer, D., Kasapoğlu, K.E., ve Tunusluoğ- lu, C., 2014. Artificial Neural Network (ANN) Based Model for Predicting of Overall Strength of Volcanic Bimrock, Proc ISRM European Rock Mechanics Symposium, EUROCK 2014, Spain, 83- 87.
  • Ulusay, R., 2010. Uygulamalı Jeoteknik Bilgiler,
  • TMMOB Jeoloji Mühendisleri Odası Ya
  • yınları, No: 38, Ankara.
  • Wang, C., 1994. A theory of generalization in learning machines with neural appli- cation, PhD Thesis, The University of Pennsylvania, USA.
  • Yeşilnacar, E.K., ve Topal, T., 2005. Landslide Susceptibility Mapping: comparison between logistic regression and neu- ral networks in a medium scale study, Hendek region TURKEY, Engineering Geology, 79, 251-266.
  • Youd, T.L., ve Idriss, I.M., 2001. Liquefaction Resistance of Soils: Summary Report from the 1996 NCEER and 1998 NCE- ER/NSF Workshop on Evaluation of Li- quefaction Resistance of Soils, ASCE Journal of Geotechnical Engineering, 127, 4, 297-313.
  • Youd, T. L., ve Noble, S. K., 1997. Liquefaction criteria based on statistical and proba- bilistic analyses, Proceedings, NCEER Workshop on Evaluation of Liquefacti- on Resistance of Soils, National Centre for Earthquake Engineering Research, State University of New York at Buffalo, 201-215.
There are 42 citations in total.

Details

Primary Language English
Journal Section Articles
Authors

Bora Sönmez This is me

Gülseren Dağdelenler This is me

Nazlı Tunar Özcan This is me

Murat Ercanoğlu This is me

Harun Sönmez

Publication Date December 23, 2015
Submission Date December 23, 2015
Published in Issue Year 2015

Cite

EndNote Sönmez B, Dağdelenler G, Tunar Özcan N, Ercanoğlu M, Sönmez H (December 1, 2015) Yapay Sinir Ağı Kullanılarak CPT Tabanlı Sıvılaşma Değerlendirme Abağının Geliştirilmesi. Yerbilimleri 36 2 45–59.