بررسی تاثیر پارامترهای اجرایی ماشین TBM بر نرخ نفوذ آن با استفاده از روش شبکه‌های عصبی مصنوعی- مطالعه‌ی موردی تونل بلند زاگرس

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشجوی دکترای تخصصی؛ رشته‌ی مهندسی معدن؛ گرایش مکانیک سنگ؛ دانشکده‌ی مهندسی معدن؛ دانشگاه صنعتی اصفهان

2 استادیار؛ دانشکده‌ی مهندسی معدن؛ دانشگاه صنعتی اصفهان

چکیده

نرخ نفوذ یکی از پارامترهای مهم در تعیین مدت زمان حفاری در عملیات تونلسازی است. از آنجا که عملیات حفاری اندرکنش میان زمین و ماشین است؛ بنابراین دو دسته‌ی کلی پارامتر موثر بر نرخ نفوذ وجود دارد. از طرفی در شرایط یکسان زمین، به دلیل پارامترهای اجرایی متفاوت ماشین، مقدار نرخ نفوذ متفاوت است. بنابراین در این مقاله به بررسی اثر پارامترهای ماشین بر نرخ نفوذ با استفاده از روش شبکه‌های عصبی مصنوعی پرداخته شده است. پس از انتخاب پارامترهای موثر بر نرخ نفوذ و ایجاد شبکه‌ی عصبی بهینه، تحلیل حساسیت بر روی پارامتر نیروی محوری پیشران و گشتاور انجام شده‌است. نتایج تحلیل‌ها نشان می‌دهد که نیروی محوری پیشران و گشتاور در یک محدوده‌ی بهینه، سبب افزایش نرخ نفوذ می‌شود و به منظور دستیابی به نرخ نفوذ حداکثر می‌توان از زوج نیروی محوری پیشران و گشتاور بهینه استفاده نمود.

کلیدواژه‌ها


عنوان مقاله [English]

The Effect of Operational Parameters on Penetration Rate of a TBM Using Artificial Neural Networks- A case study: Zagros Tunnel

نویسندگان [English]

  • Seyed Mosleh Eftekhari 1
  • Ali Reza baghbanan 2
  • Raheb bagherpour 2
1 PhD Candidate; Department of Mining Engineering; Isfahan University of Technology
2 Assistant Professor; Department of Mining Engineering; Isfahan University of Technology
چکیده [English]

The ANNs are a form of artificial intelligence which attempt to mimic the function of the human brain and nervous system. ANNs could take into account the impact of all important parameters for predicting a phenomenon. In this study, the obtained data from an excavated tunnel with a length of 10 km in Zagros region in Iran were analyzed, and the penetration rate of a TBM was predicted by taking the ANNs approach in a MATLAB program used for this purpose.
 
Introduction
Performance analysis and accurate prediction of Penetration Rate (PR) of a tunnel boring machine have been the ultimate goals of many research works. A reliable prediction of a TBM performance is necessary in budget control and also time schedule planning in underground excavation projects. Evaluating the optimum operational parameters of machine using artificial neural networks method is the main objective of this research work which has not been estimated and reported in previous studies in this field of study.
 
Methodology and Approaches
For predicting the PR of a TBM, mechanical properties of intact rock and rock masses and also operational parameters such as recorded values of torque and thrust are required in ANN modeling. The obtained simulation results of the tested sets show that the network with 8 neurons in its hidden layer is the most appropriate network structure for predicting the PR in this study. The correlation coefficient (R-value) between the outputs of the network and the actual PR is 83%.The designed ANN model was then applied for the next excavated 0.5 km of the tunnel that had not been previously considered by the ANN model. The calculated correlation coefficient between the outputs of the network and actual PR for the new set of data was 79% indicating that the designed ANN in this study worked quite well. A sensitivity analysis on the effect of two important operational parameters of TBM namely thrust and torque was conducted. Based on the results, the optimum ranges for both operational parameters were determined.
 
Results and Conclusions
The results of this study show that the developed ANN method is very efficient for predicting the PR in the investigated tunnel. The maximum PR is achieved when optimum values of thrust and torque of TBM are applied.

کلیدواژه‌ها [English]

  • Tunnel Boring Machine (TBM)
  • Penetration Rate (PR)
  • artificial neural networks (ANNs)
  • Thrust
  • Torque
[1]     Roxborough, F. F., & Phillips, H. R. (1975). Rock Excavation by Disc Cutter. International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts, 12(12), 361-366. http://dx.doi.org/10.1016/0148-9062(75)90547-1.

[2]     Sanio, H. (1985). Prediction of the Performance of Disc Cutters in Anisotropic Rock. International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts, 22(3), 153-161. http://dx.doi.org/10.1016/0148-9062(85)93229-2.

[3]     Nilson, B., & Ozdemir, L. (1993). Hard Rock Tunnel Boring Prediction and Field Performance. In L. D. Bowerman & J. E. Monsees (Ed.), Proceeding of Rapid Excavation and Tunneling Conference (pp. 833-852). Boston: Society for Mining Metallurgy. ISBN: 9780873351270.

[4]     Tarkoy, P. J. (1974). Prediction TBM Penetration Rate in Selected Rock Types. Proceeding of the Ninth Canadian Rock Mechanics symposium (pp. 257-269). Montreal: Mines Branch, Department of Energy, Mines and Resources.

[5]     Graham, P. C. (1976). Rock Exploration for Machine Manufacturers. In Z. T. Bieniawski (Ed.), Exploration for Rock Engineering: Proceedings of The Symposium on Exploration for Rock Engineering (pp.173-180). Johannesburg: A A Balkema. ISBN: 9780869610893.

[6]     Farmer, I. W., & Glossop, N. H. (1980). Mechanics of Disc Cutter Penetration. Tunnels and Tunneling International, 12, 622-625.

[7]     Nelson, P., O’Rourke, T. D., & Kulhawy, F. H. (1983). Factors Affecting TBM Penetration Rates in Sedimentary Rocks. In C. Christopher (Ed.), 24th U.S. Symposium on Rock Mechanics (pp. 227-237). Texas: American Rock Mechanics Association.

[8]     Cassinelli, F., Cina, S., Innaurato, N., Mancini, R., & Sampaolo, A. (1982). Power Consumption and Metal Wear in Tunnel-Boring Machines: Analysis of Tunnel-Boring Operation in Hard Rock. In M. J. Jones (Ed.), Tunnelling 82 (pp. 73-81). London: Institution of Mining and Metallurgy. ISBN:090048862X.

[9]     Innaurato, N., Mancini, A., Rondena, E., & Zaninetti, A. (1991). Forecasting and Effective TBM Performances in a Rapid Excavation of a Tunnel In Italy. 7th ISRM Congress (pp. 1009-1014). Aachen: International Society for Rock Mechanics.

[10] Park, C. W., Park, C., Synn, J. H., Sunwoo, C., & Chung, S. K. (2001). TBM Penetration Rate with Rock Mass Properties in Hard Rock. AITES-ITA 2001 World Tunnel Congress (pp. 413-419). Milano. ISBN: 9788855525947.

[11] Hassanpour, J., Rostami, J., & Zhao, J. (2011). A New Hard Rock TBM Performance Prediction Model for Project Planning. Tunnelling and Underground Space Technology, 26(5), 595-603. http://dx.doi.org/10.1016/j.tust.2011.04.004.

[12] Bruland, A. (2000). Hard Rock Tunnel Boring. Trondheim: Doctoral thesis, Norwegian University of Science and Technology, Engineering Science and Technology. ISBN:8247102811.

[13] Barton, N. R. (2000). TBM Tunnelling in Jointed and Faulted Rock. Rotterdam: A A Balkema. ISBN:9058093417.

[14]منهاج، م. ب. (1391).  مبانی شبکه‌های عصبی.تهران، ایران: انتشارات دانشگاه صنعتی امیرکبیر. شابک: 9789644630873.

[15] Grima, M. A., Bruines, P. A., & Verhoef, P. W. (2000). Modelling Tunnel Boring Machine Performance by Neuro-Fuzzy Methods. Tunnelling and Underground Space Technology, 15 (3), 259-269. http://dx.doi.org/10.1016/S0886-7798(00)00055-9.

[16]یاوری، ش. م.، و مهدوری، س. (1385). پیش‌بینی نرخ ‌نفوذ ماشین‌های تونل‌بری با استفاده از شبکه‌ی عصبی. نشریه‌ی دانشکده‌ی فنی، دانشگاه تهران، 40(1)، 115-121.

[17] Yagiza, S., Gokceoglu, C., Sezer, E., & Iplikci, S. (2009). Application of Two Non-Linear Prediction Tools to The Estimation of Tunnel Boring Machine Performance. Engineering Applications of Artificial Intelligence, 22 (4-5), 808-814. http://dx.doi.org/10.1016/j.engappai.2009.03.007.

[18] Gholamnejad, J., & Tayarani, N. (2010). Application of Artificial Neural Networks to The Prediction of Tunnel Boring Machine Penetration Rate. Mining Science and Technology(China), 20 (5), 727-733. http://dx.doi.org/10.1016/S1674-5264(09)60271-4.

[19] Torabi, S. R., Shirazi, H., Hajali, H., & Monjezi, M. (2011). Study of The Influence of Geotechnical Parameters on The TBM Performance in Tehran-Shomal Highway Project Using ANN and SPSS. Arabian Journal of Geosciences. http://dx.doi.org/10.1007/s12517-011-0415-3.

[20] Khademi Hamidi, J., Shahriar, K., Rezai, B., & Rostami, J. (2010). Performance Prediction of Hard Rock TBM Using Rock Mass Rating (RMR) System. Tunnelling and Underground Space Technology, 25 (4), 333-345. http://dx.doi.org/10.1016/j.tust.2010.01.008.

[21]مهندسین مشاور ساحل. (1386). مطالعات زمینشناسی مهندسی مسیر تونل. گزارش شماره‌ی 2026.

[22] Demuth, H., Beale, M., & Hagan, M. (2006). Neural Network Toolbox for Use with Matlab: User's Guide, 5th. Natick, Massachusetts, United States of America: The Mathworks, Inc.

[23]مهدوری، س. (1382). پیشبینی ضریب بهروری TBM‌های باز. تهران، ایران: پایان‌نامه‌ی کارشناسی ارشد، دانشگاه تهران.

[24]کیا، م. (1389). شبکه‌های عصبی در MATLAB. تهران، ایران: خدمات نشر کیان رایانه سبز. شابک: 9786005237009.

[25]افتخاری، س. م. (1389). تحلیل عددی تاثیر پارامترهای هندسی شکستگی‌های منفصل بر نرخ نفوذ دستگاهTBM  در توده‌سنگ شکسته-مطالعه‌ی موردی تونل بلند زاگرس. اصفهان، ایران:پایان‌نامه‌ی کارشناسی ارشد، دانشگاه صنعتی اصفهان.

[26] Eftekhari, M., Baghbanan, A., & Bayati, M. (2010). Predicting Penetration Rate of A Tunnel Boring Machine Using Artificial Neural Network. In K. G. Sharma (Ed.), ISRM International Symposium-6th Asian Rock Mechanics Symposium-Advances in Rock Engineering. New Delhi, India: International Society for Rock Mechanics.

[27] Hornik, K. (1989). Multilayer Feed Forward Networks Are Universal Approximators. Neural Networks, 2(5), 359-366. http://dx.doi.org/10.1016/0893-6080(89)90020-8.

[28] Hecht-Nielsen, R. (1989). Theory of The Back-Propagation Neural Network. International Joint Conference on Neural Networks (pp. 593-605). Washington, DC, USA: IEEE TAB Neural Network Conference. http://dx.doi.org/10.1109/IJCNN.1989.118638.

[29] Cybenko, G. (1989). Approximation by Superpositions of A Sigmoidal Function. Mathematics of Control, Signals and Systems, 2 (4), 303-314. http://dx.doi.org/10.1007/BF02551274.

[30] Basheer, I. A. (2000). Selection of Methodology for Neural Network Modeling of Constitutive Hystereses Behavior of Soils. Computer-Aided Civil and Infrastructure Engineering, 15(6), 445-463. http://dx.doi.org/10.1111/0885-9507.00206.

[31] Berke, L., & Hajela, P. (1991). Application of Neural Networks in Structural Optimization. NATO-DFG Advanced Study Institute on optimization of large structural systems (pp. 731-745). Berchtesgaden: Springer. ISBN:0792321294.

[32] Hecht-Nielsen, R. (1987). Kolmogrov's Mapping Neural Network Existence Theorem. In M. Caudill (Ed.), 1st IEEE International Conference on Neural Networks (pp. 11-14). San Diego. California.

[33] Caudill, M. (1988). Neural Networks Primer, Part III. AI Expert, 3 (6), 53-59. ISSN:0888-3785.