تخمین مدول تغییرشکل‌پذیری سنگ آهک آسماری با استفاده از سیستم عصبی- ژنتیک

نوع مقاله: مقاله پژوهشی

نویسندگان

1 کارشناس ارشد گرایش مکانیک سنگ، دانشگاه صنعتی امیرکبیر

2 استادیار دانشکده مهندسی معدن و متالوژی، دانشگاه امیرکبیر

چکیده

مدول تغییر شکل‌پذیری توده­سنگ (Em) به عنوان مهم‌ترین خصوصیت برای طراحی پروژه­های مهندسی سنگ مطرح است و بهترین نماینده برای رفتار مکانیکی پیش از شکست توده­سنگ است. به دلیل هزینه بالا و زمان­بر بودن و مشکلات اجرایی در انجام دقیق آزمایش­های برجا، روش­های غیرمستقیم مانند روابط تجربی و شبکه­های پس انتشار عصبی (BPN) جایگاه بهتری پیدا می­کنند. از این میان  BPN دارای کاربردی گسترده در تخمین خصوصیات توده سنگ از جمله Em است. محققین متعددی از روش سعی و خطا برای ایجاد یک BPN کارا  بهره گرفته­اند که نیاز به صرف زمان و مهارت کاربر دارد. اما در این مطالعه، از الگوریتم ژنتیک برای بهینه کردن پارامتری مؤثر BPN به منظور تخمین Em در رشته   کوه­های زاگرس ایران استفاده شد.  برای این منظور، یک بانک اطلاعاتی از پروژه­های مختلف رشته کوه­های زاگرس جمع‌آوری و Em سنگ آهک آسماری تخمین زده و در نهایت نتایج به دست آمده از روش عصبی - ژنتیک با روش عصبی سعی و خطا  مقایسه شد. که براساس نتایج به دست آمده روش عصبی- ژنتیک  دارای دقت و سرعت بالاتر در تخمین Em است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Estimation of the deformation modulus of Asmari limestone in Zagros Mountains, Iran, using a neural network –genetic model

نویسندگان [English]

  • Zeinab Aliabadian 1
  • Mostafa Sharifzadeh 2
1 Rock Mechanics Department, Amirkabir University of Technology
2 Rock Mechanics Department, Amirkabir University of Technology
چکیده [English]

The deformation modulus of rock mass (Em) is the most representative parameter of the pre-failure mechanical behavior of the rock material and of the rock mass .Due to the high cost and measurement difficulties of in situ tests, the predictive models using regression based statistical methods, back propagation neural networks (BPN) and fuzzy systems are recently employed for the indirect estimation of the modulus .Among these methods, the BPN has been reported to be very useful in modeling the rock material behavior, such as Em, by many researchers .Despite its extensive applications, design and structural optimization of BPN are still done via a time-consuming reiterative trial-and-error approach . However, in this research, the genetic algorithm (GA) is utilized to find the optimal parameters of BPN, such as the optimal number of neurons in hidden layer, learning rates and momentum coefficients of hidden and output layers of network. Then, the result is compared with that of trial-and-error procedure . For the purpose, a data base including118 data sets was employed from six dam sites locations in Zagros Mountains of Iran. According to the results, the GA -ANN model has higher accuracy than the trial-and-error model in the estimation of Em 

کلیدواژه‌ها [English]

  • Deformation modulus of rock mass
  • Zagros mountains
  • Back propagation neural network
  • Genetic Algorithm

Alvarez Grima, M., Babuska, R., 1999. Fuzzy model for the prediction of unconfined compressive strength of rock samples. International Journal of Rock Mechanica and Mining Sciences, 36: 339–349.

Bieniawski, Z.T. , 1993. Determining rock mass deformability:  experience Fromcase histories. International Journal of Rock Mechanica and Mining Sciences, 15: 237–247.

Fu, L.,  1995. Neural Networks in Computer Intelligence New York:McGraw-Hill.

Gokceoglu, C., 2002. A fuzzy triangular chart to predict the uniaxial compressive strength of the Ankara agglomerates from their petrographic composition. Engineering Geology, 66: 39–51.

Grimstad, E., Barton, N. , 1993. Updating the Q-system for NMT. Proceedings of the International Symposium on Sprayed Concrete Modern Use of Wet Mix Sprayed Concrete for Underground Support, Oslo, Norwegian Concrete Association.

Hassoun, M.H., 1995. Fundamentals of Artificial Neural Networks. CambridgeMA: MIT Press.

Hecht-Nielsen, R., 1987. Kolmogorov’s mapping neural network existence theorem; Proceedings of the first IEEE international conference on neural networks, San Diego CA, USA, pp. 11–14.

Henseler, J., 1995, Backpropagation. In: Braspenning P.J., Thuijsman, F., Weijters, A.J.M.M. (Eds.), Artificial Neural Networks, an Introduction to ANN Theory and Practice. Lecture Notes in Computer Science, Berlin : Springer, pp. 37–66.

Hertz, J., Krogh, A., Palmer, R.G., 1991. Introduction to the Theory of Neural Computation. Reading MA: Addison-Wesley.

Hush, D.R., 1989, Classification with neural networks: a performance Analysis. Proceedings of the IEEE international conference on systems Engineering Dayton Ohia, USA, pp. 277–280.

Hoek, E., Brown E.T., 1997. Practical estimates of rock mass strength. International Journal of Rock Mechanica and Mining Sciences, 34: 1165–1186.

Majdi, A., Beiki, M., 2010. Evolving neural network using a genetic algorithm for predicting the Deformation modulus of rock masses. International Journal of Rock Mechanics and Mining Sciences, 47(2): 246–253.

Meulenkamp, F., Alvarez Grima, M., 1999. Application of neural networks for the prediction of the unconfined compressive strength (UCS) from equotip hardness. International Journal of Rock Mechanica and Mining Sciences, 36:29–39.

Mitri, H.S., Edrissi, R., Henning, J., 1994. Finite element modeling of cable bolted stops in hard rock ground mines; Presented at the SME Annual Meeting.New Mexico:  Albuquerque, pp. 94–116.

Osman, M.S., Abo-Sinna, M.A., Mousa, A.A., 2005. Combined genetic algorithm-fuzzy logic controller (GA-FLC) in nonlinear programming. Journal of Applied Mathematics and Computing, 170(2): 821–840.

Palonen, M., Hasan, A., Siren, K., 2009. A genetic algorithm for optimization of building envelope and HVAC system parameters.  Eleventh International IBPSA Conference Glasgow, Scotland, pp. 27-30.

Paola,  J.D., 1994. Neural Network Classification of Multispectral Imagery., MSc thesis, The University of Arizona, USA.

Read S.A.L., Richard L.R., Perrin N.D., 1999. Applicability of the Hoek-Brown failure criterion to New Zealand gerywack rocks. In: Vouille G, berest, P. (Eds.): Proceeding of the  Nineth International Congeress on Rock Mechanics; Paris, 2: pp. 655-660.

Serafim, J.L., Pereira, J.P., 1983.  Considerations on the geomechanical classification of Bieniawski. Proceedings of the Symposium on Engineering Geology and Underground Openings; Lisboa,Portugal, pp. 1133–1144.

Sietsma, J., Dow, R.J.F., 1991. Creating artificial neural network that generalize. Neural Networks,  4: 67–69.

Sonmez, H., Gokceoglu, C., Nefeslioglu, H.A., Kayabasi, A., 2006. Estimation of rock modulus for intact rocks with an artificial neural network and for rock masses with a new empirical equation. International Journal of Rock Mechanica and Mining Sciences, 43: 224–235.

Staufer, P., Fisher, M.M. , 1997. Specral pattern recognition by a two-layer perceptron: effects of training set size. In: Kanellopoulos, I., Wilkinson, G.G., Roli F., Austin J. (Eds.): Neuro-Computation in Remote Sensing Data Analysis. London: Springer, pp. 105–116.

Tahmasebi, P., Hezarkhani, A., 2009. Application of adaptive neuro-fuzzy inference system for grade estimation, case study, Sarcheshmeh porphyry copper deposit, Kerman, Iran. Australian Journal of Basic and Applied Sciences, 4(3): 408-420.

Wang, C. , 1994. A Theory of Generalization in Learning Machines with Neural Application., PhD thesis, The University of Pennsylvania, US.