Evaluation of rockburst potential in kimberlite using fruit fly optimization algorithm and generalized regression neural networks

• Autorzy: Pu Yuanyuan , Apel Derek B. , Pourrahimian Yashar , Chen Jie

Identyfikatory

DOI

10.24425/ams.2019.128683

Warianty tytułu

PL

Ocena stanu zagrożenia tąpania i wyrzutów skał w kimeberlite z wykorzystaniem algorytmu muszki owocowej i sieci neuronowej realizującej uogólnioną regresję (GRNN)

• Języki publikacji: EN

Abstrakty

EN

Rockburst is a common engineering geological hazard. In order to evaluate rockburst liability in kimberlite at an underground diamond mine, a method combining generalized regression neural networks (GRNN) and fruit fly optimization algorithm (FOA) is employed. Based on two fundamental premises of rockburst occurrence, depth, σθ, σc, σt, B1, B2, SCF, Wet are determined as indicators of rockburst, which are also input vectors of GRNN model. 132 groups of data obtained from rockburst cases from all over the world are chosen as training samples to train the GRNN model; FOA is used to seek the optimal parameter σ that generates the most accurate GRNN model. The trained GRNN model is adopted to evaluate burst liability in kimberlite pipes. The same eight rockburst indicators are acquired from lab tests, mine site and FEM model as test sample features. Evaluation results made by GRNN can be confirmed by a rockburst case at this mine. GRNN do not require any prior knowledge about the nature of the relationship between the input and output variables and avoid analyzing the mechanism of rockburst, which has a bright prospect for engineering rockburst potential evaluation.

PL

Tąpnięcia skał są powszechnym i ogólnie znanym zagrożeniem dla środowiska geologicznego oraz dla budowli. Do oceny skłonności skał do tąpania w podziemnej kopalni diamentów w Kimberlite zastosowano metodę stanowiącą połączenie sieci neuronowych realizujących uogólnioną regresję i algorytm muszki owocowej. W oparciu o dwie podstawowe przesłanki wystąpienia tąpnięcia, głębokość oraz σθ, σc, σt, wielkości B1, B2, SCF, Wet określone zostały jako wskaźniki wystąpienia tąpnięcia i następnie wy-korzystane jako wektory wejściowe w modelu sieci neuronowych GRNN. Zestawiono 132 zbiory danych o przypadkach tapnięć z całego świata i wykorzystano je jako zbiory uczące dla modelu sieci neuronowej realizującej uogólnioną regresję. Algorytm muszki owocowej wykorzystano do znalezienia optymalnej wartości parametru σ który umożliwi wygenerowanie najbardziej dokładnego modelu sieci neuronowej GRNN. Po treningu, model sieci GRNN wykorzystany został do oceny możliwości wystąpienia tąpnięcia w Kimberlite. Te same osiem wskaźników oceny skłonności wyrzutowej skały otrzymano na podstawie badań laboratoryjnych, z analiz prowadzonych w kopalni oraz w oparciu o metodę elementów skończonych, wyniki te wykorzystano następnie jako próbki danych. Wyniki uzyskane przy zastosowaniu sieci neuronowych realizujących regresję uogólnioną potwierdzone zostały przez wyniki uzyskane w trakcie wyrzutu w kopalni. Metoda sieci neuronowych nie wymaga uprzedniej wiedzy o naturze zależności pomiędzy zmiennymi wejściowymi i wyjściowymi i pozwala uniknąć analiz mechanizmu wyrzutu i tąpnięcia, co jest cechą pożądaną z punktu widzenia inżynierów odpowiedzialnych za ocenę skłonności skał do wyrzutu.

Słowa kluczowe

EN

rockburst potential evaluation; generalized regression neural networks (GRNN); fruit fly algorithm; backpropagation neural network (BPNN)

PL

ocena możliwości wystąpienia wyrzutów skał; sieć neuronowa realizująca regresję uogólnioną (GRNN); algorytm muszki owocowej; sieć neuronowa realizującą propagację wsteczną (BPNN)

• Wydawca: Instytut Mechaniki Górotworu PAN
• Czasopismo: Archives of Mining Sciences
• Rocznik: 2019
• Tom: Vol. 64, no. 2
• Strony: 279--296
• Opis fizyczny: Bibliogr. 60 poz., fot., rys., tab., wykr.

Twórcy

autor

Pu Yuanyuan

• State Key Laborary of Coal Mine Disaster Dynamics and Control, Chongqing University, Chon-Gqing 400044, China

autor

Apel Derek B.

• School of Mining and Petroleum Engineering, University of Alberta, Edmonton, Canada

autor

Pourrahimian Yashar

• School of Mining and Petroleum Engineering, University of Alberta, Edmonton, Canada

autor

Chen Jie

• State Key Laborary of Coal Mine Disaster Dynamics and Control, Chongqing University, Chon-Gqing 400044, China

Bibliografia

• [1] Baltz R., Hucke A., 2008. Rockburst prevention in the German coal industry. In Proceedings of the 27th international conference on ground control in mining. West Virginia University, Morgantown, WV, 46-50.
• [2] Blake W., Hedley D.G., 2003. Rockbursts: case studies from North American hard-rock mines: SME.
• [3] Brownlee J., 2018. Why One-Hot Encode Data in Machine Learning. Dostopno na: https://machinelearningmastery. com/why-one-hot-encode-data-in-machine-learning/, ogled.
• [4] Bukowska M., 2012. The rockbursts in the upper silesian coal basin in Poland. Journal of Mining Science 48 (3), 445-456.
• [5] Cai M., 2016. Prediction and prevention of rockburst in metal mines – A case study of Sanshandao gold mine. Journal of Rock Mechanics and Geotechnical Engineering 8 (2), 204-211, doi:10.1016/j.jrmge.2015.11.002.
• [6] Cai W., Dou L., Si G., Cao A., He J., Liu S., 2016. A principal component analysis/fuzzy comprehensive evaluation model for coal burst liability assessment. International Journal of Rock Mechanics and Mining Sciences 81, 62-69.
• [7] Cigizoglu H.K., Alp M., 2006. Generalized regression neural network in modelling river sediment yield. Advances In Engineering Software 37 (2), 63-68.
• [8] Dershowitz W.S., Einstein H.H., 1984. Application of artificial intelligence to problems of rock mechanics. In The 25th US Symposium on Rock Mechanics (USRMS), American Rock Mechanics Association.
• [9] Dong L., Li X., Peng K. 2013. Prediction of rockburst classification using Random Forest. Transactions of Nonferrous Metals Society of China 23 (2), 472-477.
• [10] Feng X., Wang L., 1994. Rockburst prediction based on neural networks. Transactions of Nonferrous Metals Society of China 4 (1), 7-14.
• [11] Gao D., 1998. On Structure of Supervised Linear Basis Function Feedforward Three-Layered Neural Networks (in Chinese). Chinese J. Computer 21 (1), 80-86.
• [12] Gao W., 2015. Forecasting of rockbursts in deep underground engineering based on abstraction ant colony clustering algorithm. Natural Hazard 76 (3), 1625-1649.
• [13] Gibowicz S.J., 2009. Seismicity induced by mining: Recent research. Advances in Geophysics 51, 1-53.
• [14] He J., Dou L., Gong S., Li J., Ma Z., 2017. Rock burst assessment and prediction by dynamic and static stress analysis based on micro-seismic monitoring. International Journal of Rock Mechanics and Mining Sciences 93, 46-53.
• [15] Iannacchione A.T., Zelanko J.C., 1993. Occurrence and remediation of coal mine bumps: a historical review.
• [16] Jia Y., Lv Q., Shang Y., 2013. Rockburst Prediction Using Particle Swarm Optimization Algorithm and General Regression Neural Network (in Chinese). Chinese Journal of Rock Mechanics and Engineering 32 (2), 343-348.
• [17] Kidybiński A., 1981. Bursting liability indices of coal. In International Journal of Rock Mechanics and Mining Science & Geomechanics Abstracts 18, 295-304.
• [18] Kiefa M.A., 1998. General regression neural networks for driven piles in cohesionless soils. Journal of Geotechnical and Geoenvironmental Engineering 124 (12), 1177-1185.
• [19] Leveille P., Sepehri M., Apel D.B., 2016. Rockburst Potential of Kimberlite: A Case Study of Diavik Diamond Mine. Rock Mechanics and Rock Engineering, 1-9.
• [20] Li C.H., Lee C., 1993. Minimum cross entropy thresholding. Pattern Recognition 26 (4), 617-625.
• [21] Li S.L., 2000. Study on rockburst proneness and strata control technology for deep mines with hard rock. Ph.D Thesis, Northeastern University, Shengyang, China.
• [22] Liu J., 2011. Studies on relationship between Microseism time-space evolution and ground pressure activities in deep mine. Ph.D’s Thesis, Northeastern University, Shengyang, China.
• [23] Mansurov V., 2001. Prediction of rockbursts by analysis of induced seismicity data. International Journal of Rock Mechanics and Mining Sciences 38 (6), 893-901.
• [24] Manual M., 1995. the MathWorks. Inc., Natick, MA.
• [25] Martin C., Kaiser P., McCreath D., 1999. Hoek-Brown parameters for predicting the depth of brittle failure around tunnels. Canadian Geotechnical Journal 36 (1), 136-151.
• [26] Mitri H.S., Hughes R., Zhang Y., 2011. New rock stress factor for the stability graph method. International Journal of Rock Mechanics and Mining Sciences 48 (1), 141-145.
• [27] Ni S., Lu P., Juang C., 1996. A fuzzy neural network approach to evaluation of slope failure potential. Computer-Aided Civil and Infrastructure Engineering 11 (1), 59-66.
• [28] Nikbakhtan B., Apel D., Ahangari K. 2015. Jet grouting: Using artificial neural networks to predict soilcrete column diameter К Part II. [Article]. International Journal of Mining and Mineral Engineering 6 (1), 57-71, doi:10.1504/IJMME.2015.067951.
• [29] Pan W., 2011. Using Fruit Fly Optimization Algorithm Optimized General Regression Neural Network to Construct the Operating Performance of Enterprises Model. Journal of Taiyuan University of Technology (Social Science Edition) (in Chinese) 29 (4), 1-5.
• [30] Patyńska R., Kabiesz J., 2009. Scale of seismic and rock burst hazard in the Silesian companies in Poland. Mining Science and Technology (China) 19 (5), 604-608.
• [31] Potvin Y., Hudyma M., Jewell R.J., 2000. Rockburst and seismic activity in underground Australian mines-an introduction to a new research project. In ISRM International Symposium, International Society for Rock Mechanics.
• [32] Pu Y., Apel D., Xu H., 2018a. A Principal Component Analysis/Fuzzy Comprehensive Evaluation for Rockburst Potential in Kimberlite. Pure and Applied Geophysics, 1-11.
• [33] Pu Y., Apel D.B., Lingga B., 2018b. Rockburst prediction in kimberlite using decision tree with incomplete data. Journal of Sustainable Mining.
• [34] Pu Y., Apel D.B., Wang C., Wilson B., 2018c. Evaluation of burst liability in kimberlite using support vector machine. Acta Geophysica, 1-10.
• [35] RioTinto, 2015. Serious potential incident review: Fall of Ground (pp. 35). Yellownife, Canada: Rio Tinto.
• [36] Russenes B., 1974. Analysis of rock spalling for tunnels in steep valley sides. Norwegian Institute of Technology, Deptartment of Geology, Trondheim Google Scholar.
• [37] Sepehri M., Apel D., Liu W., 2017. Stope Stability Assessment and Effect of Horizontal to Vertical Stress Ratio on the Yielding and Relaxation Zones Around Underground Open Stopes Using Empirical and Finite Element Methods. Archives of Mining Sciences 62 (3), 653-669.
• [38] Shi Q., Pan Y., Li Y., 2005. The Typical Cases and Analysis of Rockburst in China (in Chinese). Coal Mining Technology 10 (2), 13-17.
• [39] Singh S. 1987. The influence of rock properties on the occurrence and control of rockbursts. Mining Science and Technology 5 (1), 11-18.
• [40] Singh S.P., 1989. Classification of mine workings according to their rockburst proneness. Mining Science and Technology 8 (3), 253-262.
• [41] Sivakugan N., Eckersley J., Li H., 1998. Settlement predictions using neural networks. Australian Civil Engineering Transactions 40, 49.
• [42] Specht D.F., 1991. A general regression neural network. IEEE Transactions on Neural Networks 2 (6), 568-576.
• [43] Sun J., Wang L., Zhang H., Shen Y., 2009. Application of fuzzy neural network in predicting the risk of rock burst. Procedia Earth and Planetary Science 1 (1), 536-543.
• [44] Tan Y., 1992. Rockburst characteristics and structural effects of rock mass. Science in China Series B-Chemistry, Life Sciences & Earth Sciences 35 (8), 981-990.
• [45] Tang S., Wu Z., Chen, X., 2003. Approach to occurrence and mechanism of rockburst in deep underground mines [J]. Chinese Journal of Rock Mechanics and Engineering 8, 004.
• [46] Tutumluer E., Seyhan U., 1998. Neural network modeling of anisotropic aggregate behavior from repeated load triaxial tests. Transportation Research Record: Journal of the Transportation Research Board (1615), 86-93.
• [47] Wang J., Chen J., Yang J., Que J., 2009. Method of distance discriminant analysis for determination of classification of rockburst. Rock and Soil Mechanics 30 (7), 2203-2208.
• [48] Wang Y., Li W., Li Q., Xu Y., Tan G., 1998. Method of fuzzy comprehensive evaluations for rockburst prediction. Chinese Journal of Rock Mechanics and Engineerin 17 (5), 493-501.
• [49] Xie H., PariseauW.G., 1993. Fractal character and mechanism of rock bursts. In International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts 30, 343-350, 4: Elsevier.
• [50] Xu M., Du Z., Yao G., Liu Z., 2008. Rockburst prediction of chengchao iron mine during deep mining. Chinese Journal of Rock Mechanics and Engineering 27 (s1), 2921-2928.
• [51] Yang J., Li X., Zhou Z., Lin Y., 2010. A Fuzzy assessment method of rock-burst prediction based on rough set theory. Jinshu Kuangshan/Metal Mine (6), 26-29.
• [52] Yi Y., Cao P., Pu C., 2010. Multi-factorial Comprehensive Estimation for Jinchuan’s Deep Typical Rockburst Tendency. Keji Daobao/ Science & Technology Review 28 (2), 76-80.
• [53] Zhang C., Zhou H., Feng X.-T., 2011. An index for estimating the stability of brittle surrounding rock mass: FAI and its engineering application. Rock Mechanics and Rock Engineering 44 (4), 401.
• [54] Zhang J., Fu B., Li Z., Song S., Shang Y., 2011. Criterion and classification for strain mode rockbursts based on fivefactor comprehensive method. In 12th ISRM Congress, International Society for Rock Mechanics.
• [55] Zhang L., Li C., 2009. Study on tendency analysis of rockburst and comprehensive prediction of different types of surrounding rock.
• [56] Zhang Y., Yang Z., Yao X., Liang P., Tian B., Sun L., 2017. Experimental study of rockburst early warning method based on acoustic emission cluster analysis and neural network identification. Rock and Soil Mechanics 38 (S2), 89-98.
• [57] Zhang Z., 2002. Study on rockburst and large deformation of Xuefeng mountain tunnel of Shaohuai highway. Master’s Thesis, Chengdu University of Technology, Chengdu, China.
• [58] Zhou J., Li X., Shi X., 2012. Long-term prediction model of rockburst in underground openings using heuristic algorithms and support vector machines. Safety Science 50 (4), 629-644.
• [59] Zhou K., Gu D., 2004. Application of GIS-based neural network with fuzzy self-organization to assessment of rockburst tendency. Chinese Journal of Rock Mechanics and Engineering 23 (18), 3093-3097.
• [60] Zhu P., Wang Y., Li T., 1996. Griffith theory and the criteria of rock burst. Chinese Journal of Rock Mechanics and Engineering 15 (S1), 491-495.