استفاده از رگرسیون آماری و شبکه عصبی مصنوعی برای تعیین ارتفاع منطقه رها از تنش در سقف پهنه جبهه‌کار طولانی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشیار؛ دانشکده‌ی مهندسی، گروه مهندسی معدن، دانشگاه کردستان

2 استادیار؛ بخش مهندسی معدن، مجتمع آموزش عالی زرند، دانشگاه شهید باهنر کرمان

3 دانشیار؛ گروه مهندسی معدن، دانشگاه صنعتی همدان

چکیده

ارتفاع منطقه رها از تنش (HDZ) در سقف پهنه جبهه‌کار طولانی پارامتر مهمی در تعیین میزان تنش ناشی از استخراج پهنه و بارهای انتقالی به اطراف‌ آن است. لذا تخمین دقیق HDZ به‌منظور تحلیل تنش در اطراف پهنه، طراحی ایمن سیستم نگهداری ورودی‌ها و پیش‌بینی نشست سطح زمین، ضروری می‌باشد. به‌منظور تعیین HDZ در این تحقیق، از دو مدل رگرسیون آماری و شبکه عصبی مصنوعی استفاده و نتایج حاصله با همدیگر و با داده‌های واقعی مقایسه شد. برای طراحی و ارزیابی مدل‌ها، از ۱۲۰ سری داده مستخرج از منابع معتبر استفاده گردید. پارامترهای ارتفاع روباره، ضخامت لایه زغال‌سنگ استخراجی، وزن مخصوص، مدول الاستیسیته، ضریب پواسون، مقاومت فشاری تک محوری و فاکتور حجمی توده‌سنگ سقف به‌عنوان متغیرهای ورودی برای پیش‌بینی HDZ در نظر گرفته شد. در فرآیند ارزیابی مدل‌ها بر اساس داده‌های واقعی، مقادیر ضریب تصمیم‌گیری، میانگین خطای مطلق و میانگین خطای نسبی به‌ترتیب برای مدل آماری برابر با %77/22، 5/66 متر و %20/43 و برای شبکه عصبی برابر با %96/04، 2/53 متر و %7/32 به‌دست آمد. نتایج فوق نشان‌دهنده دقت بیش‌تر و خطای کم‌تر شبکه عصبی نسبت به مدل آماری و تطابق بهتر خروجی‌های آن با داده‌های واقعی است. تحلیل حساسیت نتایج مدل آماری نشان داد که وزن مخصوص و ضریب پواسون توده‌سنگ به‌ترتیب با مقدار ضریب استاندارد شدة 0/524 و 0/01 بیش‌ترین و کمترین تأثیر را بر HDZ دارند. در نهایت، تحلیل اهمیت متغیر نتایج شبکه عصبی نشان داد که ارتفاع روباره و ضریب پواسون به‌ترتیب با میزان اهمیت 0/949 و 0/879 دارای بیش‌ترین و کم‌ترین تأثیر بر HDZ هستند.

کلیدواژه‌ها

موضوعات


Abdollahi, M. S., Najafi, M., Yarahmadi Bafghi, A., & Rafiee, R. (2024). A New method for stability analysis of chain pillar in longwall mining by using Coulmann graphical method. Journal of Mining and Environment, 15(4), 1461–1476. Retrieved from https://doi.org/10.22044/jme.2024.13754.2548
Aghababaei, S., Jalalifar, H., Hosseini, A., Chinaei, F., & Najafi, M. (2024). Prediction of Roof Failure in Pre-driven Entries and Selecting a Suitable Type of Recovery Room Method in Longwall Mining. Journal of Mining and Environment, 15(1), 223–237. Retrieved from https://doi.org/10.22044/jme.2023.12787.2321
Asadizadeh, M., & Rezaei, M. (2021). Surveying the mechanical response of non-persistent jointed slabs subjected to compressive axial loading utilising GEP approach. International Journal of Geotechnical Engineering, 15(10), 1312–1324. Retrieved from https://doi.org/10.1080/19386362.2019.1596610
Ceryan, N., Okkan, U., & Kesimal, A. (2012). Prediction of unconfined compressive strength of carbonate rocks using artificial neural networks. Environmental Earth Sciences, 68(3), 807–819. Retrieved from https://doi.org/10.1007/s12665-012-1783-z
Demuth, H., Beal, M., & Hagan, M. (1996). Neural network toolbox 5 user’s guide. Natick, MA: The Math Work, Inc.
Gao, F., Stead, D., & Coggan, J. (2014). Evaluation of coal longwall caving characteristics using an innovative UDEC Trigon approach. Computers and Geotechnics, 55, 448–460. Retrieved from https://doi.org/10.1016/j.compgeo.2013.09.020
He, C., Lu, W., Zha, W., & Wang, F. (2021). A geomechanical method for predicting the height of a water-flowing fractured zone in a layered overburden of longwall coal mining. International Journal of Rock Mechanics & Mining Sciences, 143, 104798. Retrieved from https://doi.org/10.1016/j.ijrmms.2021.104798
Liu, S., Chang, R., Zuo, J., Webber, R. J., Xiong, F., & Dong, Na. (2021). Application of Artificial Neural Networks in Construction Management: Current Status and Future Directions. Applied Sciences, 11, 9616. Retrieved from https://doi.org/10.3390/app11209616
Mahdevari, S., Shahriar, K., Sharifzadeh, M., & Tannant, D. D. (2017) Stability prediction of gate roadways in longwall mining using artificial neural networks. Neural Computing & Applications, 28(11), 3537–3555. Retrieved from https://doi.org/10.1007/s00521-016-2263-2
Majdi, A., Hassani, F. P., & Yousef Nasiri, M. (2012). Prediction of the height of destressed zone above the mined panel roof in longwall coal mining. International Journal of Coal Geology, 62, 62–72. Retrieved from https://doi.org/10.1016/j.coal.2012.04.005
Majdi, A., & Rezaei, M. (2013a). Application of artificial neural networks for predicting the height of destressed zone above the mined panel in longwall coal mining. 47th U.S. rock mechanics/geomechanics symposium, (pp. 1665–1673). San Francisco, California, USA.
Majdi, A., & Rezaei, M. (2013b). Prediction of unconfined compressive strength of rock surrounding a roadway using artificial neural network. Neural Computing & Applications, 23(2), 381–389. Retrieved from https://doi.org/10.1007/s00521-012-0925-2
Menhaj, M. B. (2000). Fundamentals of neural networks. Amirkabir University of Technology publication, 1st ed., 1st Vol.
Mohammadi, H., Ebrahimi Farsangi, M. A., Jalalifar, H., Ahmadi, A. R., & Javaheri, A. (2016). Extension of excavation damaged zone due to longwall working effect. Journal of Mining and Environment, 7(1), 13–24. Retrieved from https://doi.org/10.22044/jme.2016.369
Mondal, D., Roy, P. N. S., & Kumar, M. (2020). Monitoring the strata behavior in the Destressed Zone of a shallow Indian longwall panel with hard sandstone cover using Mine-Microseismicity and Borehole Televiewer data. Engineering Geology, 271, 105593. Retrieved from https://doi.org/10.1016/j.enggeo.2020.105593
Mulumba, D. M., Liu, J., Hao, J., Zheng, Y., & Liu, H (2023). Application of an Optimized PSO-BP Neural Network to the Assessment and Prediction of Underground Coal Mine Safety Risk Factors. Applied Sciences, 13, 5317. Retrieved from https://doi.org/10.3390/app13095317
Palchik, V. 2003. Formation of fractured zones in overburden due to longwall mining. Environmental Geology, 44(1), 28–38. Retrieved from https://doi.org/10.1007/s00254-002-0732-7
Rezaei, M. (2018). Development of an intelligent model to estimate the height of caving–fracturing zone over the longwall gobs. Neural Computing & Applications, 30(7), 2145–2158. Retrieved from https://doi.org/10.1007/s00521-016-2809-3
Rezaei, M. (2019). Forecasting the stress concentration coefficient around the mined panel using soft computing methodology. Engineering with Computers, 35, 451–466. Retrieved from https://doi.org/10.1007/s00366-018-0608-4
 Rezaei, M. (2020). Feasibility of novel techniques to predict the elastic modulus of rocks based on the laboratory data. International Journal of Geotechnical Engineering, 14(1), 25–34. Retrieved from https://doi.org/10.1080/19386362.2017.1397873
Rezaei, M., & Rajabi, M. (2021). Assessment of plastic zones surrounding the power station cavern using numerical, fuzzy and statistical models. Engineering with Computers, 37(2), 1499-1518. Retrieved from https://doi.org/10.1007/s00366-019-00900-3
Rezaei, M., Ahmadi, S. R., Hoang, N., & Jahed Armaghani, D., (2024a). Improved determination of the S-wave velocity of rocks in dry and saturated conditions: Application of machine-learning algorithms. Transportation Geotechnics, 49, 101371. Retrieved from https://doi.org/10.1016/j.trgeo.2024.101371
Rezaei, M., Habibi, H., & Asadizadeh, M. (2024b). Determination of the stress concentration factor adjacent an extracted underground coal panel using the CART and MARS algorithms. Earth Science Informatics, 17(6). 5733–5750. Retrieved from https://doi.org/10.1007/s12145-024-01476-3
 Rezaei, M., Hossaini, M. F., & Majdi, A. (2015a). A time-independent energy model to determine the height of destressed zone above the mined panel in longwall coal mining. Tunnelling and Underground Space Technology, 4, 81–92. Retrieved from https://doi.org/10.1016/j.tust.2015.01.001
Rezaei, M., Hossaini, M. F., & Majdi, A. (2015b). Determination of longwall mining-induced stress using the strain energy method. Rock Mechanics and Rock Engineering, 48(6), 2421–2433. Retrieved from https://doi.org/10.1007/s00603-014-0704-8
Rezaei, M., Hossaini, M. F., & Majdi, A. (2015c). Development of a time-dependent energy model to calculate the mining-induced stress over gates and pillars. Journal of Rock Mechanics and Geotechnical Engineering, 7(3), 306–317. Retrieved from https://doi.org/10.1016/j.jrmge.2015.01.001
Rezaei, M., Hossaini, M. F., Majdi, A., & Najmoddini, I. (2017). Determination of the height of destressed zone above the mined panel: An ANN model. International Journal of Mining and Geo-Engineering, 51(1), 1–7. Retrieved from https://doi.org/10.22059/ijmge.2017.62147
Rezaei, M., Majdi, A., Hossaini, M. F., & Najmoddini, I. (2018). Study the roof behavior over the longwall gob in long-term condition. Journal of Geology and Mining Research, 10(2), 15–27. Retrieved from https://doi.org/10.5897/JGMR2017.0284
Rezaei, M., Monjezi, M., Matinpoor, F., Mohammadi Bolbanabad, S., & Habibi, H. (2023).
Simulation of induced flyrock due to open-pit blasting using the PCA-CART hybrid modelling. Simulation Modelling Practice and Theory, 129, 102844. Retrieved from https://doi.org/10.1016/j.simpat.2023.102844
Shabanimashcool, M., & Charlie, C. L. (2012). Numerical modelling of longwall mining and stability analysis of the gates in a coal mine. International Journal of Rock Mechanics and Mining Sciences, 51, 24–34. Retrieved from https://doi.org/10.1016/j.ijrmms.2012.02.002
Shun, L., Xuehua, L., Yanxin, M., & Chengjun, L. (2013). Time-domain characteristics of overlying strata failure under condition of longwall ascending mining. International Journal of Mining Science and Technology, 23, 207–211. Retrieved from https://doi.org/10.1016/j.ijmst.2013.04.018
Van Dyke, M. A., Zhang, P., Dougherty, H., Su, D., & Kim, B. H. (2022). Identifying Longwall‑Induced Fracture Zone Height Through Core Drilling. Mining, Metallurgy & Exploration, 39, 1345–1355. Retrieved from https://doi.org/10.1007/s42461-022-00622-z
Wang, Y., Rezaei, M., Abdullah, R. A., & Hasanipanah, M. (2023). Developing Two Hybrid Algorithms for Predicting the Elastic Modulus of Intact Rocks. Sustainability, 15, 4230. Retrieved from https://doi.org/10.3390/su15054230
Wenbing, G., Youfeng, Z., & Quanlin, H., 2012. Fractured zone height of longwall mining and its effects on the overburden aquifers. International Journal of Mining Science and Technology, 22(5), 603–606. Retrieved from https://doi.org/10.1016/j.ijmst.2012.08.001
Xu, C., Zhou, K., Xiong, X., Gao, F., & Zhou, J. (2024). Research on height prediction of water-conducting fracture zone in coal mining based on intelligent algorithm combined with extreme. Expert Systems With Applications, 249, 123669. Retrieved from https://doi.org/10.1016/j.eswa.2024.123669
Yu, B., Wang, B. & Zhang, Y. (2024). Application of artificial intelligence in coal mine ultra-deep roadway engineering—a review. Artificial Intelligence Review, 57, 262. Retrieved from https://doi.org/10.1007/s10462-024-10898-w
Zhang, B., Liang, Y., Sun, H., Wang, K., Zou, Q., & Dai J. (2022). Evolution of mining‑induced fractured zone height above a mined panel in longwall coal mining. Arabian Journal of Geosciences, 15, 476. Retrieved from https://doi.org/10.1007/s12517-022-09768-y
Zhang, Y., Tu, S., Bai, Q., & Li, J. (2013). Overburden fracture evolution laws and water-controlling technologies in mining very thick coal seam under water-rich roof. International Journal of Mining Science and Technology, 23(5), 693–700. Retrieved from https://doi.org/10.1016/j.ijmst.2013.08.013