PATLATMA KAYNAKLI TİTREŞİMLERİN YAPAY SİNİR AĞLARI KULLANILARAK TAHMİNİ

Bu çalışmada patlatma kaynaklı titreşim hızının tahmin edilmesinde yapay sinir ağları (YSA) kullanılmıştır. Bu kapsamda, İstanbul’da bulunan bir taşocağında yapılan patlatmalar izlenmiş ve patlatmalardan kaynaklanan titreşimler kayıt altına alınmıştır. İzlenen ilk 12 atımda kaydedilen 24 olaya ait maksimum parçacık hızları ile ölçekli mesafeler istatiksel analize tabi tutulmuş ve sahanın spesifik titreşim yayılım denklemi elde edilmiştir. Bu veri seti ayrıca, ölçekli mesafenin giriş, maksimum parçacık hızının ise çıkış olduğu bir YSA modelinin eğitilmesinde kullanılmış; ve ilgili sahada patlatma kaynaklı titreşimlerin tahmin edilmesinde kullanılan yeni bir model geliştirilmiştir. Titreşim yayılım denklemi ve geliştirilen YSA modeli kullanılarak, sonradan izlenen 19 atım için titreşim hızı tahminleri yapılmış, elde edilen değerler ile kaydedilen 37 olay karşılaştırılmıştır. Titreşim yayılım denklemi ile hesaplanan değerler ile kaydedilen olaylar arasında yüksek korelasyonlu doğrusal bir ilişki olduğu; YSA modelinin çıkışları ile kaydedilen olaylar arasında ise daha yüksek korelasyonlu doğrusal bir ilişki olduğu görülmüştür.

PREDICTION OF BLAST INDUCED GROUND VIBRATIONS BY USING ARTIFICIAL NEURAL NETWORKS

In this study, artificial neural networks (ANN) were used as a tool for estimation of blast-inducedvibrations. For this purpose, the blast shots carried out in a quarry in Istanbul were monitored andthe blast-induced vibrations were recorded.Peak Particle Velocities (PPV) and Scaled Distances (SD) of 24 events were recorded in thefirst 12 shots, subjected to statistical analysis and the site-specific ground vibration propagationequation was obtained. This data set was also used to train an ANN model while SD was aninput and PPV was an output; and a new model, that used to estimate blast-induced vibrationsin the related field, was developed. Using the vibration propagation equation and the developedANN model, blast-induced vibrations were estimated for 19 shots performed subsequently, andthe results were compared with 37 recorded vibration data. It was seen that there was linearrelationship with a high correlation between the values calculated with the equation and recordeddata; and there was linear relationship with a higher correlation between outputs of ANN modeland recorded data.

___

  • Adeli, H., Wu, M., 1998. Regularization Neural Network For Construction Cost Estimation. Journal of Construction Engineering and Management, Vol. 124, Issue 1.
  • Ak, H., Iphar, M., Yavuz M., Konuk, A., 2009. Evaluation of Ground Vibration Effect of Blasting Operations in a Magnesite Mine. Soil Dynamics and Earthquake Engineering, 29: 4: 669-676.
  • Allahverdi, N., 2002. Uzman Sistemler: Bir Yapay Zeka Uygulaması. Atlas Yayın Dağıtım, İstanbul.
  • Ambraseys, N.R., Hendron A.J., 1968. Dynamic Behaviour of Rock Masses, in: Rock Mechanics in Engineering Practice.
  • Ambrozic, T., Turk, G., 2003. Prediction of Subsidence Due to Underground Mining. Computers & Geosciences, Vol. 29, Issue 5.
  • Baghirli, O., 2015, Comparison of Lavenberg Marquardt, Scaled Conjugate Gradient and Bayes Regularization Backpropagation Algorithms for Multistep Ahead Wind Speed Forecasting Using Multilayer Perceptron Feedforward Neural Network. Master Thesis, Ippsala University Department of Earth Sciences, Campus Gotland.
  • Chapra, S.C., Canale, R.P., 2015, Yazılım ve Programlama Uygulamalarıyla Mühendisler Için Sayısal Yöntemler. Literatür Yayıncılık, Çevirenler: Hasan Heperkan, Uğur Kesgin, ISBN:978-975-8431-83-0.
  • Cheng, L., Yang, Y., Xiong, Y., 2005. Study of Mine Ventilation System Assessment Based on Artificial Neural Network. China safety science journal.
  • Dowding, C.H., 1985. Blast Vibration Monitoring and Control. Prentice-Hall, USA.
  • Düzgün, H.S.B., 2005. Analysis of Roof Fall Hazards and Risk Assessment for Zonguldak Coal Basin Underground Mines. International Journal of Coal Geology 64.
  • Elmas, Ç., 2011. Yapay Sinir Ağları. Seçkin Yayıncılık, Ankara, 2003, s. 23.
  • Ghosh, A., Daemen, J.J.K., 1983. A Simple New Blast Vibration Predictore (based on wave propagation laws). 24 th U.S. Symp. on Rock Mechanics, June, 151-161
  • Guo D.Y., Wang Y.B., Wei X.J., Wang X.Y, 2009. Early Warning of Coal and Gas Outburst by GIS and Neural Network. J Univ Sci Technol Beijing 2009;31(01):15–24.
  • Gupta, R.N., Roy, P.P., Singh B., 1988. On a Blast Induced Blast Vibration Predictor for Efficient Blasting. Safety in Mines Research Proceedings of the 22nd International Conference of Safety in Mines Reseach Institutes.
  • He, G.J., Liu S.Y., Sun Y.B. 2009. Theory and Practice of Coal Mine Accident Hidden Danger Monitoring and Early Warning. J China Coal Soc 2009;34(2):212–7.
  • Hu, D.H., 2010. Analysis on Coal Mine Safety Accident Causes and Forewarning Management Research. Beijing: China University of Geosciences; 2010.
  • Jimeno, C.L., Jimeno, E.L., Carcedo, F.J.A., 1995. Drilling and blasting of rocks. A.A., Balkema Publishers, Brookfield, ISBN: 90 5410 1977, Rotterdam Pp 390,
  • Mathworks, 2017, Matlab Documentations.
  • Karadoğan, A., Özer, Ü., Kahriman, A., 2012. Patlatma Kaynaklı Titreşimlerin Tahmini İçin Farklı Kayaların Saha Sabitlerinin Belirlenmesi. İstanbul Yerbilimleri Dergisi, C.25, S.1, SS. 9-23.
  • Khandelwal, M., Singh, T.N., 2006. Prediction of Blast Induced Ground Vibrations and Frequency in Opencast Mine: A Neural Network Approach. J Sound Vib, 289. (4–5):711–25.
  • Kuzu, C., 2008, The Importance of Site Specific Characters in Prediction Models for Blast Induced Ground Vibrations. Soil Dynamics and Earthquake Engineering, 28: 5: 405-414.
  • Lee, S., Park, I., Choi, J.K., 2012. Spatial Prediction of Ground Subsidence Susceptinility Using an Artificil Neural Network. Environ Manage, Feb;49(2):347-58. doi: 10.1007/s00267-011-9766-5. Epub 2011 Oct 18.
  • Leu, S., Chen, C., Chang, S., 2001. Data Mining Fortunnel Support Stability: Neural Network Approach. Automation in Construction, Vol. 10, Issue 4, Pg. 429- 411.
  • Liu, L., 2014. Modeling and Evaluation of the Safety Control Capability of coal Mine Based on System Safety. Journal of Cleaner Production 84.
  • Mohammad, M.T., 2009. Artificial Neural Network for Prediction and Control of Blasting Vibration in Assiut (Egypt) Limestone Quarry. International Journal of Rock Mechanics and Mining Science, 46, pp. 426–431.
  • Nicholls, H.R., Johnson C.F., Duvall, W.L., 1971. Blasting Vibrations and Their Effects on Structure. United States Department of Interior, USBM, Bulletin 656.
  • Özer, Ü., Karadoğan, A., Özyurt, M.C., Şahinoğlu Ü.K., Sertabipoğlu, S., 2019. Environmentally Sensitive Blasting Design Based on Risk Analysis by Using Artificial Neural Networks, Arabian Journal of Geosciences, Vol. 12, Issue 2.
  • Özyurt, M.C., 2018. Yeraltı Üretim Yöntemi Seçiminde Yapay Sinir Ağları ve Oyun Teorisinin Kullanılabilirliğinin Araştırılması. Doktora Tezi, İstanbul Üniversitesi, Fen Bilimleri Enstitüsü.
  • Özyurt, M.C., Karadoğan, A., 2018. Evaluation of the Feasibility of Fully Mechanized Excavation by Artificial Neural Networks. UYAK 2018, 13-14th September 2018, Istanbul, Turkey, 299-306.
  • Özyurt, M.C., Karadoğan, A., 2019. Developing a Model Based on the Strata Control Parameter in the Selection of Underground Mining Method by Using Artificial Neural Networks. Istanbul Yerbilimleri Dergisi, Volume 30, No 1, 14-24.
  • Öztemel, E., 2016. Yapay Sinir Ağları. Papatya Yayıncılık, 4.Basim, 230s.
  • Pan, X., Lee, B., Zhang, C., 2013. A Comparison of Neural Network Backpropagation Algorithms For Electricity Load Forecasting. Intelligent Energy Systems (IWIES), 2013 IEEE, vol., no., pp.22,27, 14-14 Nov.
  • Sawmliana, C., Roy, P., Singh, R.K., Singh, T.N., 2007. Blast Induced Air Overpressure and its Prediction Using Artificial Neural Network. International Journal of Mining Technology, 116, pp. 41–48.
  • Singh, T.N., Dontha, L.K., Bharadwaj, V., 2008. A study Into Blast Vibration And Frequency Using ANFIS and MVRA Mining Technology (TIMM A). UK, 117 (3), pp. 116–121.
  • Singh, T.N., Kanchan, R., Verma, A.K., 2004. Prediction of Blast Induced Ground Vibration and Frequency Using An Artificial Intelligent Technique. Blast Induced Ground Vibration and Frequency, 7–15.
  • Singh, T.N., Singh, V., 2005. An Intelligent Approach to Prediction and Control Ground Vibration in Mines. Geotechnical and Geological Engineering, 23, pp. 249–262.
  • Yılmaz, I., 2009. Landslide Susceptibility Mapping Using Frequency Ratio, Logistic Regression, Artificial Neural Networks and Their Comprasion: a Case Study From Kat Landslides (Tokat-Turkey). Computer and Geosciences, 35.
  • Yue, Y. Rue, H., 2011. Bayesian Inference For Additive Mixed Quantile Regression Models. Computational Statistics and Data Anaylsis, 55, 84-96.
  • Zhang, X., Wang, H., Yu, H. 2007. Neural Network Based Algorithm and Simulation of Information Fusion in the Coal Mine. Journal of China University of Mining and Technology, Vol. 7, Issue 4, Pg. 595-598.