پیش بینی مقاومت فشاری تک محوری و مدول الاستیک ماسه سنگ ها با استفاده از شبکه عصبی مصنوعی و آنالیز رگرسیون چند متغیره

نوع مقاله: مقاله پژوهشی

نویسندگان

گروه زمین‌شناسی، دانشکده علوم پایه، دانشگاه لرستان، خرم‌آباد

10.22084/nfag.2019.17545.1341

چکیده

تعیین دقیق ویژگی­های ژئومکانیکی سنگ­ها از جمله مقاومت فشاری تک­محوری و مدول­الاستیک با استفاده از روش­های مرسوم آزمایشگاهی، بسیار مشکل و نیازمند صرف زمان و هزینه زیادی می­باشد. این موضوع به­خصوص در مورد سنگ­های ناهمسانگرد، با سطوح لایه­بندی، متخلخل و ضعیف مطرح می­باشد. به­منظور غلبه بر این مشکلات، توسعه روابط و مدل­های پیش­بینی کننده برای تخمین این پارامترها در مهندسی سنگ ضروری به نظر می­رسد. هدف از این مطالعه، پیش­بینی مقاومت فـشاری تک­مـحوری و مـدول­الاستیـک ماسه­سنگ­ها با استفاده از شبکه عصبی مصنوعی و آنالیز رگرسیون چند متغیره می­باشد. به­همین منظور، تعداد 130 نمونه مغزه سنگی تهیه شده و آزمایش­های جامعی بر روی آن­ها انجام شده است. برای توسعه مدل شبکه عصبی پیش­بینی کننده، ویژگی­های فیزیکی سنگ­های مورد مطالعه شامل سرعت موج، تخلخل، دانسیته خشک، شاخص دوام و درصد جذب آب به عنوان داده­های ورودی در نظر گرفته شده­اند، در حالی­که مقاومت فشاری تک­محوری و مدول­الاستیک پارامترهای خروجی می­باشند. عملکرد پیش­بینی مدل شبکه عصبی پیشنهاد شده و آنالیز رگرسیون چند متغیره با استفاده از شاخص­های آماری از قبیل R، RMSE و VAF ارزیابی شده است. مقایسه نتایج نشان می­دهد که عملکرد شبکه عصبی مصنوعی پیشنهاد شده در پیش­بینی مقاومت فشاری تک­محوری و مدول­الاستیک به مراتب بهتر از آنالیز رگرسیون می­باشد.

کلیدواژه‌ها


عنوان مقاله [English]

Prediction of uniaxial compressive strength and modulus of elasticity of sandstones using artificial neural network and multiple regression analysis

نویسندگان [English]

  • Y. Abdi
  • A. Ghasemi Dehnavi
چکیده [English]

Determining UCS and E using standard laboratory tests is a difficult, expensive and time consuming task. This is particularly true for thinly bedded, highly fractured, foliated, highly porous and weak rocks. Consequently, prediction models become an attractive alternative for engineering geologists. The main purpose of this study is to develop an artificial neural network (ANN) and multiple regression analysis (MLR) models in order to predict UCS and E of sandstones. For this, a database of laboratory tests (including 130 sandstone samples) was prepared, which includes porosity, P-wave velocity, dry density, slake durability index, and water absorption as input parameters and UCS and E as output parameter. The performance of the MLR and ANN models are evaluated by comparing statistic parameters, including correlation coefficient (r), root mean square error (RMSE), and variance account for (VAF). Comparison of the multiple linear regressions and ANNs results indicated that respective ANN models were more acceptable for predicting UCS and E than the other.

کلیدواژه‌ها [English]

  • Uniaxial compressive strength
  • Modulus of elasticity
  • Artificial neural network
  • Regression analysis
  • Sandstone
Abdi, Y., Taheri-Garavand, A., Zarei-Sahamieh, A (2018) Prediction of strength parameters of sedimentary rocks using artificial neural networks and regression analysis. Arabian Journal of Geosciences, 11:587. https://doi.org/10.1007/s12517-018-3929-0.

Ahmadi, M. A., Ebadi, M., Shokrollahi, A., Majidi, SMJ (2013) Evolving artificial neural network and imperialist competitive algorithm for prediction oil flow rate of the reservoir. Applied Soft Computing, 13: 1085–1098.

Atkinson, P. M., Tatnall, ARL (1997) Neural networks in remote sensing. International Journal of Remote Sensing, 18: 699–709.

Bejarbaneh, B. Y., Bejarbaneh, E. Y., Amin, M. F. M., Fahimifar, A., Jahed Armaghani, D., Majid, MZA (2018) Intelligent modelling of sandstone deformation behaviour using fuzzy logic and neural network systems. Bulletin of Engineering Geology and the Environment, 77: 345–361.

Cabalar, A. F., Cevik, A., Gokceoglu, C (2012) Some applications of adaptive neuro-fuzzy inference system (ANFIS) in geotechnical engineering. Computer and Geotechnics, 40: 14–33.

Dehghan, S., Sattari, G. H., Chehre-Chelgani, S., Aliabadi, MA (2010) Prediction of uniaxial compressive and modulus of elasticity for travertine sample using regression and artificial neural networks. International journal of Mining Science and Technology, 20: 41–46.

ISRM (1981) Rock characterization, testing and monitoring, ISRM suggested methods. International Society for Rock Mechanics, 211pp.

Kahraman, S., Gunaydin, O., Alber, M., Fener, M (2009) Evaluating the strength and deformability properties of misis fault breccia using artificial neural networks. Expert Systems Applications, 36: 6874–6878.

Lindquist, E. S., Goodman, RE (1994) Strength and deformation properties of a physical model melange. In: Nelson PP, Laubach SE (ed) Proceedings of the 1st North American rock mechanics symposium. Balkema, Rotterdam, 843–850.

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: 246–253.

Majidi, A., Rezaei, M (2013) Prediction of unconfined compressive strength of rock surrounding a roadway using artificial neural network. Neural Computing & Applications, 23: 381–389.

Ozcelik, Y., Bayram, F., Yasitli, NE (2013) Prediction of engineering properties of rocks from microscopic data. Arabian Journal of Geosciences, 6: 3651–3668.

Rajesh-Kumar, B., Vardhan, H., Govindaraj, M., Vijay, GS (2013) Regression analysis and ANN models to predict rock properties from sound levels produced during drilling. International Journal of Rock Mechanics and Mining Sciences, 58: 61–72.

Sarkar, K., Tiwary, A., Singh, TN (2010) Estimation of strength parameters of rock using artificial neural networks. Bulletin of Engineering Geology and the Environment, 69: 599–606.

Singh, R., Kainthola, A., Singh, TN (2012) Estimation of elastic constant of rocks using an ANFIS approach. Applied Soft Computeing, 12(1): 40–45.

Singh, T.N., Dubey, RK (2000) A study of transmission velocity of primary wave (P-Wave) in Coal Measures sandstone. Journal of Scientific and Industrial Research, 59: 482–486.

Sonmez, H., Gokceoglu, C., Nefeslioglu, HA., 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 Mechanics and Mining Sciences, 43: 224–235.

Taheri-Garavand, A., Ahmadi, H., Omid, M., Mohtasebi, S.S., Mollazade, K., Russell-Smith, J.R., Carlomagno, GM (2015) An intelligent approach for cooling radiator fault diagnosis based on infrared thermal image processing technique. Applied Thermal Engineering, 87: 434-443.

Tiryaki, B (2008) Predicting intact rock strength for mechanical excavation using multivariate statistics, artificial neural networks and regression trees. Engineering Geology, 99: 51–60.

Tonnizam-Mohamad, E., Jahed-Armaghani, D., Momeni, E., Alavi-Nezhad-Khalil-Abad, SV (2015) Prediction of the unconfined compressive strength of soft rocks: a PSO-based ANN approach. Bulletin of Engineering Geology and the Environment, 74: 745–757.

Torabi-Kaveh, M., Naseri, F., Sanei, S., Sarshari, B (2014) Application of artificial neural networks and multivariate statistics to predict UCS and E using physical properties of Asmari limestones. Arabian Journal of Geosciences, 8 (5): 2889-2897.

Yagiz, S., Sezer, E. A., Gokceoglu, C (2012) Artificial neural networks and nonlinear regression techniques to assess the influence of slake durability cycles on the prediction of uniaxial compressive strength and modulus of elasticity for carbonate rocks. International Journal for Numerical and Analytical Methods in Geomechanics, 36 (14): 1636-1650.

Yesiloglu-Gultekin, N., Gokceoglu, C., Sezer, EA (2013) Prediction of uniaxial compressive strength of granitic rocks by various nonlinear tools and comparison of their performances. International Journal of Rock Mechanics and Mining Sciences, 62: 113–122.

Yılmaz, I., Yuksek, AG (2008) An example of artificial neural network (ANN) application for indirect estimation of rock parameters. Rock Mechanics and Rock Engineering, 41(5): 781–795.

Yilmaz, I., Yuksek, AG (2009) Prediction of the strength and elasticity modulus of gypsum using multiple regression, ANN and ANFIS models. International Journal of Rock Mechanics and Mining Sciences, 46(4): 803–810.