پیش‌بینی گشتاور چرخشی موردنیاز برای انجام عملیات حفاری انحرافی در لایه‌های سنگی با استفاده از ترکیب شبکه عصبی مصنوعی و الگوریتم بهینه‌سازی مبتنی بر جغرافیای زیستی

فتاحی, هادی; بیات زاده, زهره

doi:10.29252/anm.7.13.59

پیش‌بینی گشتاور چرخشی موردنیاز برای انجام عملیات حفاری انحرافی در لایه‌های سنگی با استفاده از ترکیب شبکه عصبی مصنوعی و الگوریتم بهینه‌سازی مبتنی بر جغرافیای زیستی

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشکده مهندسی معدن، دانشگاه صنعتی اراک

10.29252/anm.7.13.59

چکیده

امروزه عملیات حفاری انحرافی به‌طور گسترده‌ای در انواع شرایط زمین‌شناسی به کار می‌رود، اما استفاده بهینه از این فنّاوری در شرایط سنگی و سخت به دانش و تجربه بالای مهندسی نیاز دارد. مقدار گشتاور چرخشی یکی از پارامترهای بسیار مهمی است که باید برای انجام عملیات حفاری انحرافی پیش‌بینی شود. در این پژوهش جهت ارائه راهکار جدید برای پیش‌بینی گشتاور چرخشی موردنیاز برای انجام عملیات حفاری انحرافی در لایه‌های سنگی از روش ترکیب شبکه عصبی مصنوعی و الگوریتم بهینه‌سازی مبتنی بر جغرافیای زیستی استفاده شده است. درواقع برای بهینه‌سازی وزن‌های شبکه عصبی مصنوعی و بالا بردن توانایی‌های شبکه از الگوریتم مبتنی بر جغرافیای زیستی بهره گرفته شده است. هم‌چنین از نیروی محوری، سرعت چرخش مته، طول رشته حفاری، تغییر زاویه کلی گمانه، قطر iامین برقو، سرعت جریان گل و ویسکوزیته گل حفاری به‌عنوان پارامترهای ورودی مدل برای پیش‌بینی گشتاور چرخشی استفاده شده است. برای ارزیابی توانایی مدل در پیش‌بینی گشتاور چرخشی، از داده‌های پروژه انتقال گاز طبیعی غرب به شرق چین استفاده شده است. تعداد کل داده‌ها در این پروژه 84 داده است که از این تعداد به‌طور تصادفی، 75 درصد داده‌ها برای آموزش مدل و 25 درصد داده‌ها برای آزمون مدل استفاده شده است. نتایج حاصل از این مطالعه بیانگر آن است که مدل پیشنهادی می‌تواند به‌عنوان یک ابزار قدرتمند برای مدلسازی مسائل حفاری انحرافی مورد استفاده قرار گیرد.

کلیدواژه‌ها

موضوعات

مکانیک سنگ

عنوان مقاله [English]

Prediction of Rotational Torque to Operate Drilling Using Hybrid ANN with Biogeography-Based Optimization Algorithm

نویسندگان [English]

Hadi Fattahi
Zohre Bayatzade

Dept. of Mining, Arak University of Technology, Iran

چکیده [English]

Summary
Horizontal directional drilling (HDD) is a popular method for installation of both steel and plastic underground pipelines. Besides selecting the appropriate type and size of reamers the rotational torque is another important parameters that must be predicted for performing the reaming operation. In this study, hybrid artificial neural networks (ANN) with biogeography-based optimization (ANN-BBO) model were applied for predicting rotational torque. In fact BBO was used to better regulate the weights and biases of the ANN model. In this study, axial force on the cutter/bit, rotational speed of the bit, the length of drill string in the borehole, the total angular change of the borehole, the radius for the i^th reaming operation, the mud flow rate and the mud viscosity are applied as input variables to predict the rotational torque. To assess the ability of the model to predict the rotational torque, West–East Natural Gas Transmission project in China was used. Results indicate that this model has high potentials for estimating the rotational torque using a set of listed input parameters.

Introduction
A major concern of many HDD projects is prediction of required rotation torque. It has been established that the required rotational torque at the drill rig depends on various factors, including geological conditions, drilling method, reamer cutter/bit size and type, rotary speed, axial force on bit, drilling mud properties, borehole diameter, length of drill string in the borehole, and borehole trajectory. In this area in recent years, studies have been done using traditional statistical methods, but this study focuses on the application of artificial intelligence in this field.

Methodology and Approaches
In this study, ANN method and BBO algorithm is used. We used BBO to better regulate the weights and biases of the ANN model. BBO is an evolutionary algorithm that is inspired by biogeography. In BBO, a biogeography habitat indicates a candidate optimization problem solution, and it is comprised of a set of features, which are also called decision variables, or independent variables. BBO consists of two main steps: migration and mutation.

Results and Conclusions
In this paper, 75% of the data sets were assigned for training purposes while 25% was used for testing of the network performance. Network with 7-8-1 structure is optimized and the results indicate that this model has high potentials for estimating the rotational torque.

کلیدواژه‌ها [English]

Horizontal Directional Drilling (HDD)
rotational torque (M)
Artificial Neural Networks (ANN)
Biogeography-Based optimization (BBO)

مراجع

[1]. Ariaratnam ST, Harbin BC, Stauber RL. 2007. Modeling of annular fluid pressures in horizontal boring. Tunnelling and Underground Space Technology 22, pp. 610-619.

[2]. Hair JD. 1989. River crossing technology. Pipeline & Gas Journal 216, pp. 29-35.

[3]. Allouche EN. 2001. Implementing quality control in HDD projects—a North American prospective. Tunnelling and Underground Space Technology 16, pp. 3-12.

[4]. Najafi M. , 2005, Trenchless technology: pipeline and utility design, construction, and renewal: McGraw Hill Professional.

[5]. David A. , 2005, Horizontal Directional Drilling–Utility and Pipeline Applications. McGraw-Hill Company Inc., New York.

[6]. Bennett D, Ariaratnam ST, Consortium H. , 2008, Horizontal Directional Drilling: Good Practices Guidelines: North American Society for Trenchless Technology.

[7]. Lesso W, Chau M, Lesso W., 1999, Quantifying bottomhole assembly tendency using field directional drilling data and a finite element model. SPE/IADC drilling conference.

[8]. Polak MA, Lasheen A. 2001. Mechanical modelling for pipes in horizontal directional drilling. Tunnelling and Underground Space Technology 16, pp. 47-55.

[9]. Cheng E, Polak MA. 2007. Theoretical model for calculating pulling loads for pipes in horizontal directional drilling. Tunnelling and Underground Space Technology 22, pp. 633-643.

[10]. Ma B, Najafi M. 2008. Development and applications of trenchless technology in China. Tunnelling and Underground Space Technology 23, pp. 476-480.

[11]. Lan H, Ma B, Shu B, Wu Z. 2011. Prediction of rotational torque and design of reaming program using horizontal directional drilling in rock strata. Tunnelling and Underground Space Technology 26, pp. 415-421.

[12]. Maidla EE, Wojtanowicz AK. 1988. A field method for assessing borehole friction for directional well casing. Journal of Petroleum Science and Engineering 1, pp. 323-333.

[13]. Niżnik D, Gonet A. 2007. Identification of rotational torque and power in HDD. Archives of Mining Sciences 52, pp. 49-60.

[14]. Kecman V. , 2001, Learning and soft computing: support vector machines, neural networks, and fuzzy logic models: MIT press.

[15]. Rigol-Sanchez J, Chica-Olmo M, Abarca-Hernandez F. 2003. Artificial neural networks as a tool for mineral potential mapping with GIS. International Journal of Remote Sensing 24, pp. 1151-1156.

[16]. Brown WM, Gedeon T, Groves D, Barnes R. 2000. Artificial neural networks: a new method for mineral prospectivity mapping. Australian Journal of Earth Sciences 47, pp. 757-770.

[17]. Van der Baan M, Jutten C. 2000. Neural networks in geophysical applications. Geophysics 65, pp. 1032-1047.

[18]. Stange W. 1993. Using artificial neural networks for the control of grinding circuits. Minerals engineering 6, pp. 479-489.

[19]. Fattahi H. 2016. Application of improved support vector regression model for prediction of deformation modulus of a rock mass. Engineering with Computers pp. 1-14.

[20]. Fattahi H. 2016. Indirect estimation of deformation modulus of an in situ rock mass: an ANFIS model based on grid partitioning, fuzzy c-means clustering and subtractive clustering. Geosciences Journal pp. 1-10.

[21]. Fattahi H. 2016. A hybrid support vector regression with ant colony optimization algorithm in estimation of safety factor for circular failure slope. International Journal of Optimization in Civil Engineering 6, pp. 63-75.

[22]. Irani R, Nasimi R. 2011. Application of artificial bee colony-based neural network in bottom hole pressure prediction in underbalanced drilling. Journal of Petroleum Science and Engineering 78, pp. 6-12.

[23]. Aryafar A, Gholami R, Rooki R, Ardejani FD. 2012. Heavy metal pollution assessment using support vector machine in the Shur River, Sarcheshmeh copper mine, Iran. Environmental earth sciences 67, pp. 1191-1199.

[24]. Mohammadi L, Meech JA. 2013. AFRA–Heuristic expert system to assess the atmospheric risk of sulphide waste dumps. Journal of Loss Prevention in the Process Industries 26, pp. 261-271.

[25]. Pourjabbar A, Sârbu C, Kostarelos K, Einax J, Büchel G. 2014. Fuzzy hierarchical cross-clustering of data from abandoned mine site contaminated with heavy metals. Computers & Geosciences 72, pp. 122-133.

[26]. Mitchell TM. Machine learning. WCB. McGraw-Hill Boston, MA:, 1997.

[27]. Betrie GD, Sadiq R, Morin KA, Tesfamariam S. 2014. Uncertainty quantification and integration of machine learning techniques for predicting acid rock drainage chemistry: A probability bounds approach. Science of the Total Environment 490, pp. 182-190.

[28]. Dmuth H, Beale M. 2000. Neural Network Toolbox for use with Matlab, User’s Guide. Natick, MA pp.

[29]. Thomas G, Wilmot T, Szatmary S, Simon D, Smith W. 2013. Evolutionary optimization of artificial neural networks for prosthetic knee control. Efficiency and Scalability Methods for Computational Intellect 7, pp. 142-161.

[30]. Bazdar H, Fattahi H, Ghadimi F. Hybrid ANN with Invasive Weed Optimization Algorithm, a New Technique for Prediction of Gold and Silver in Zarshuran Gold Deposit, Iran. Journal of Tethys: Vol 3, pp. 273-286.

[31]. Shen C, Wang L, Li Q. 2007. Optimization of injection molding process parameters using combination of artificial neural network and genetic algorithm method. Journal of Materials Processing Technology 183, pp. 412-418.

[32]. Sivagaminathan RK, Ramakrishnan S. 2007. A hybrid approach for feature subset selection using neural networks and ant colony optimization. Expert Systems with Applications 33, pp. 49-60.

[33]. Mirjalili S, Hashim SZM, Sardroudi HM. 2012. Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm. Applied Mathematics and Computation 218, pp. 11125-11137.

[34]. Simon D. 2008. Biogeography-based optimization. Evolutionary Computation, IEEE Transactions on 12, pp. 702-713.

[35]. Simon D. 2011. A probabilistic analysis of a simplified biogeography-based optimization algorithm. Evolutionary computation 19, pp. 167-188.

[36]. Sinha A, Das S, Panigrahi BK. 2011. A linear state-space analysis of the migration model in an island biogeography system. Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on 41, pp. 331-337.

[37]. Simon D, Ergezer M, Du D, Rarick R. 2011. Markov models for biogeography-based optimization. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on 41, pp. 299-306.

[38]. Simon D. 2011. A dynamic system model of biogeography-based optimization. Applied Soft Computing 11, pp. 5652-5661.

[39]. Simon D, Omran MG, Clerc M. 2014. Linearized biogeography-based optimization with re-initialization and local search. Information Sciences 267, pp. 140-157.

[40]. Guo W, Chen M, Wang L, Ge S, Wu Q. Design of migration operators for biogeography-based optimization and markov analysis. Submitted to Information Sciences pp.

[41]. Guo W, Wang L, Wu Q. 2014. An analysis of the migration rates for biogeography-based optimization. Information Sciences 254, pp. 111-140.

[42]. Ma H. 2010. An analysis of the equilibrium of migration models for biogeography-based optimization. Information Sciences 180, pp. 3444-3464.

[43]. MacArthur R, Wilson E. 1967. The theory of biogeography. Princeton University Press, New Jersey pp. 19-67.

[44]. Ma H, Simon D, Fei M. 2014. On the convergence of biogeography-based optimization for binary problems. Mathematical Problems in Engineering 2014, pp.

[45]. Guo W, Wang L, Wu Q, Ge SS, Ren H. Drift Analysis of Mutation for Biogeography-Based Optimization. pp.

[46]. Gong W, Cai Z, Ling CX, Li H. 2010. A real-coded biogeography-based optimization with mutation. Applied Mathematics and Computation 216, pp. 2749-2758.

[47]. Ma H, Simon D. 2011. Analysis of migration models of biogeography-based optimization using Markov theory. Engineering Applications of Artificial Intelligence 24, pp. 1052-1060.