ارزیابی عملکرد شبکه‌های عصبی مصنوعی تلفیق شده با الگوریتم های فراابتکاری وال و مورچگان در تخمین نرخ نفوذ حفاری و مقایسه با شبکه های عصبی ساده و مدل های ریاضی مرسوم

نوع مقاله : مقاله کامپیوتر

نویسنده

فارغ التحصیل مهندسی نفت، دانشگاه ازاد اسلامی واحد علوم و تحقیقات.

چکیده

تخمین نرخ نفوذ (ROP) در یک فرایند حفاری از آن جهت که سبب انتخاب بهینه پارامترهای حفاری و کاهش هزینه های مصرفی عملیات میشود بسیار حائز اهمیت است. هدف اصلی از این مقاله، مدلسازی و تخمین ROP با استفاده از شبکه های عصبی پرسپترون چند لایه بهینه شده با الگوریتم وال (WOA-MLPNN)، شبکه های عصبی بهینه شده با الگوریتم مورچگان (ACO-MLPNN)، شبکه های عصبی پس انتشار خطا (BP-MLPNN) و دو مدل ریاضی شامل مدل بورگوان و یانگ (BYM) و مدل بینگهام میباشد. داده های مورد نیاز برای توسعه مدلها، از واحد نمودار گیری گل و گزارشات پایانی سه چاه حفاری شده در یک میدان نفتی واقع در جنوب غربی ایران جمع اوری شده است، که نخست به منظور حذف نقاط خارج از محدوده و کاهش نویز پیش پردازش شدند. در ادامه، از اطلاعات مقطع 12.25 اینچ دو حلقه چاه که شامل یک توالی مشابه از سازند های حفاری شده میباشند به منظور آموزش و آزمایش مدلها استفاده گردید و سپس مدلهای تولید شده، توسط اطلاعات چاه سوم مورد اعتبار سنجی قرار گرفتند. در پایان، عملکرد مدلها بوسیله شاخص های اماری و ابزار های گرافیکی مختلفی مورد ارزیابی قرار گرفت. نتایج این مطالعه نشان داد که روش های آموزش ماشین نسبت به مدلهای ریاضی مرسوم بسیار دقیقتر میباشند. همچنین، بررسی های بیشتر ثابت کرد که مدل WOA-MLPNN با مقادیر AAPRE برابر 3.19، 5.48 و 9.31 به ترتیب برای سه بخش آموزش، آزمایش و اعتبار سنجی بالاترین عملکرد را نسبت به سایر مدله ها دارا میباشد.

کلیدواژه‌ها


عنوان مقاله [English]

Evaluation of the performance of artificial neural networks integrated with whale optimization and ant colony optimization algorithms in estimating the drilling rate of penetration and compare with simple neural networks and mathematical conventional models

نویسنده [English]

  • Ehsan Brenjkar
Masters degree of Petroleum Engineering, Science and Research Branch, Islamic Azad University, Tehran-Iran
چکیده [English]

Rate of penetration (ROP) estimation in a drilling process is very important because it leads to the optimal selection of drilling parameters and reduction of the operating costs. The main purpose of this paper is to modeling and estimating ROP using optimized multilayer perceptron neural network with whale optimization algorithm (WOA-MLPNN), optimized multilayer perceptron neural network with ant colony optimization algorithm (ACO-MLPNN), back propagation multilayer perceptron neural network (BP-MLPNN) and two mathematical models including Bourgoyne and Young model (BYM) and Bingham model. The data required for development of the models were collected from the mud logging unit and the final reports of three drilled wells in an oil field located in southwestern Iran, which were first pre-processed to remove outliers and reduce noise. In the following, 12.25” hole-section information of two wells containing a similar sequence of drilled formations was used to train and test the models, and then the generated models were validated by the third well information. In the end, the performance of models was evaluated by statistical indicators and various graphical tools. The results of this study showed that the machine learning methods are much more accurate than conventional mathematical models. Also, more detailed studies showed that the WOA-MLPNN model with AAPRE values of 3.19, 5.48 and 9.31 for the three sections of training, testing and validation, respectively, has the highest performance compared to other models.

کلیدواژه‌ها [English]

  • Rate of penetration
  • Bourgoyne and Young model
  • Bingham model
  • Whale optimization algorithm
  • Ant colony optimization algorithm
  • Multilayer perceptron neural network
[1] M. M. Amer, A. S. Dahab, and A.A. H. El-Sayed, “An ROP Predictive Model in Nile Delta Area Using Artificial Neural Networks”, Society of Petroleum Engineers, June 2017.
[2] S. Z. Lashari, A. Takbiri-Borujeni, E. Fathi, T. Sun, R. Rahmani, and M. Khazaeli, “Drilling performance monitoring and optimization: a data-driven approach”, Journal of Petroleum Exploration and Production Technology, Vol. 9, No. 4, December 2019, pp. 2747-2756.
[3] A. K. Abbas, S. Rushdi, and M. Alsaba, “Modeling Rate of Penetration for Deviated Wells Using Artificial Neural Network”, Abu Dhabi International Petroleum Exhibition and Conference, November 2018.
[4] A. K. Abbas, S. Rushdi, M. Alsaba, and M. F. Al Dushaishi, “Drilling Rate of Penetration Prediction of High-Angled Wells Using Artificial Neural Networks”, Journal of Energy Resources Technology, Vol. 141, No. 11, May 2019, p. 112904.
[5] M. Ayoub, G. Shien, D. Diab, and Q. Ahmed, “Modeling of drilling rate of penetration using adaptive neuro-fuzzy inference system”, International Journal of Applied Engineering Research, Vol. 12, 2017, pp. 12880-12891.
[6] E. M. Galle and H. B. Woods, “Best Constant Weight and Rotary Speed for rotary Rock Bits”, Drilling and Production Practice. American Petroleum Institute, p. 26, 1963, Accessed: June 2019.
[7] M. G. Bingham, “A new approach to interpreting rock drillability”, Petroleum Pub. Co., 1965.
[8] A. T. Bourgoyne and F. S. Young, “A Multiple Regression Approach to Optimal Drilling and Abnormal Pressure Detection”, Society of Petroleum Engineers, Vol. 14, No. 04, August 1974, pp. 371-384.
[9] A. A. Jabbar, S. Elkatatny, M. Mahmoud, K. Abdelgawad, and A. Al-Majed, “A Robust Rate of Penetration Model for Carbonate Formation”, Journal of Energy Resources Technology, Vol. 141, No. 4, November 2018.
[10] E. Wiktorski, A. Kuznetcov, and D. Sui, “ROP Optimization and Modeling in Directional Drilling Process”, SPE Bergen One Day Seminar, April 2017.
[11] A. K. Darwesh, T. M. Rasmussen, and N. Al, “Controllable drilling parameter optimization for roller cone and polycrystalline diamond bits”, Journal of Petroleum Exploration and Production Technology, Vol. 10, No. 4, 2020, pp. 1657-1674.
[12] M. Anemangely, A. Ramezanzadeh, and B. Tokhmechi, “Determination of constant coefficients of Bourgoyne and Young drilling rate model using a novel evolutionary algorithm”, Journal of Mining and Environment, Vol. 8, No. 4, 2017, pp. 693-702.
[13] Y. Li and R. Samuel, “Prediction of Penetration Rate Ahead of the Bit through Real-Time Updated Machine Learning Models”, SPE/IADC International Drilling Conference and Exhibition, Mar. 2019.
[14] M. R. Youcefi, A. Hadjadj, A. Bentriou, and F. S. Boukredera, “Rate of penetration modeling using hybridization extreme learning machine and whale optimization algorithm”, Earth Science Informatics, 2020.
[15] A. Ahmed s, S. Elkatatny, A. Abdulraheem, M. Mahmoud, A. Z. Ali, and I. M. Mohamed, “Prediction of Rate of Penetration of Deep and Tight Formation Using Support Vector Machine”, Society of Petroleum Engineers, August 2018.
[16] A. Al-Abduljabbar, H. Gamal, and S. Elkatatny, “Application of artificial neural network to predict the rate of penetration for S-shape well profile”, Arabian Journal of Geosciences, Vol. 13, No. 16, 2020.
[17] C. Gan et al., “Prediction of drilling rate of penetration (ROP) using hybrid support vector regression: A case study on the Shennongjia area, Central China”, Journal of Petroleum Science and Engineering, Vol. 181, October 2019.
[18] S. B. Ashrafi, M. Anemangely, M. Sabah, and M. J. Ameri, “Application of hybrid artificial neural networks for predicting rate of penetration (ROP): A case study from Marun oil field”, Journal of Petroleum Science and Engineering, Vol. 175, December 2018, pp. 604–623.
[19] K. Al-Azani, S. Elkatatny, A. Ali, E. Ramadan, and A. Abdulraheem, “Cutting concentration prediction in horizontal and deviated wells using artificial intelligence techniques”, Journal of Petroleum Exploration and Production Technology, Vol. 9, No. 4, December 2019, pp. 2769-2779.
 [20]حدیث بی باک، جهانگیر خزایی و حسین مویدی، "پیش بینی طرح اختلاط بهینه برای بهسازی خاک رس نرم با استفاده از شبکه های عصبی مصنوعی"،  نشریه مدل سازی در مهندسی، دوره 17، شماره 57، تابستان 1398، صفحه 13-1.
[21] D. Toghraie, N. Sina, N. A. Jolfaei, M. Hajian, and M. Afrand, “Designing an Artificial Neural Network (ANN) to predict the viscosity of Silver/Ethylene glycol nanofluid at different temperatures and volume fraction of nanoparticles”, Physica A: Statistical Mechanics and its Applications, Vol. 534, p. 122142, Nov. 2019.
[22] N. F. Hordri, S. S. Yuhaniz, S. M. Shamsuddin, and A. Ali, “Hybrid Biogeography Based Optimization-Multilayer Perceptron for Application in Intelligent Medical Diagnosis”, Advanced Science Letters, Vol. 23, No. 6, June 2017, pp. 5304-5308.
[23] C. Soares and K. Gray, “Real-time predictive capabilities of analytical and machine learning rate of penetration (ROP) models”, Journal of Petroleum Science and Engineering, Vol. 172, January 2019, pp. 934-959.
[24] S. Mirjalili and A. Lewis, “The Whale Optimization Algorithm”, Advances in Engineering Software, Vol. 95, 2016, pp. 51-67.
[25] A. Heydari, D. Astiaso Garcia, F. Keynia, F. Bisegna, and L. De Santoli, “Hybrid intelligent strategy for multifactor influenced electrical energy consumption forecasting”, Energy Sources, Part B: Economics, Planning, and Policy, Vol. 14, No. 10-12, December 2019, pp. 341-358.
[26] W. Chen et al., “Spatial Prediction of Landslide Susceptibility Using GIS-Based Data Mining Techniques of ANFIS with Whale Optimization Algorithm (WOA) and Grey Wolf Optimizer (GWO)”, Applied Sciences, Vol. 9, No. 18, September 2019, p. 3755.
[27] D. Tien Bui, M. M. Abdullahi, S. Ghareh, H. Moayedi, and H. Nguyen, “Fine-tuning of neural computing using whale optimization algorithm for predicting compressive strength of concrete”, Engineering with Computers, August 2019.
[28] M. Dorigo, V. Maniezzo, and A. Colorni, “Ant system: optimization by a colony of cooperating agents”, IEEE Transactions on Systems, Vol. 26, No. 1, 1996, pp. 29-41.
[29] امیر سقط فروش، مسعود منجزی و جعفر خادمی حمیدی، "بهینه سازی عملیات انفجار با استفاده از روش ترکیبی عصبی-مورچگان (مطالعه موردی: معدن سنگ آهن دلکن) "، نشریه مدل سازی در مهندسی، دوره 15، شماره 48، بهار 1396، صفحه 269-259.
[30] P. Li, H. Nie, L. Qiu, and R. Wang, “Energy optimization of ant colony algorithm in wireless sensor network”, International Journal of Distributed Sensor Networks, Vol. 13, No. 4, April 2017.
[31] K. Socha and M. Dorigo, “Ant colony optimization for continuous domains”, European Journal of Operational Research, Vol. 185, No. 3, March 2008, pp. 1155-1173.
[32] D. Zhao et al., “Chaotic random spare ant colony optimization for multi-threshold image segmentation of 2D Kapur entropy”, Knowledge-Based Systems, October 2020.
 [33] نوید فریدونی مهر و فواد نظری، "تحلیل پارامتری و بهینه سازی سیکل تبریداجکتوری فوق بحرانی همراه با سیال عامل های مختلف به کمک شبکه عصبی مصنوعی و الگوریتم بهینه سازی پرندگان"، نشریه مدل سازی در مهندسی، دوره 15، شماره 50، پاییز 1396، صفحه 133-122.
[34] M. Puig-Arnavat and J. C. Bruno, “Artificial Neural Networks for Thermochemical Conversion of Biomass”, Recent Advances in Thermo-Chemical Conversion of Biomass, 2015, pp. 133-156.
[35] M. Ahmadi and Z. Chen, “Machine learning-based models for predicting permeability impairment due to scale deposition”, Journal of Petroleum Exploration and Production Technology, Vol. 10, No. 7, October 2020, pp. 2873-2884.
 [36] حامد نوذری و فاطمه توکلی، "پیش بینی جریان با استفاده از مدل ماشین بردار پشتیبان بر مبنای سری های زمانی دبیو بارش در ایستگاه های بالادست(مطالعه موردی : ایستگاه هیدرومتری تله زنگ) "، نشریه مدل سازی در مهندسی، دوره 16، شماره 54، پاییز 1397، صفحه 104-96.
[37] J. W. Graham and N. L. Muench, “Analytical determination of optimum bit weight and rotary speed combinations”, Society of Petroleum Engineers, 1959.
[38] T. Miyora, M. Þ. Jónsson, and S. Þórhallsson, “Modelling of geothermal drilling parameters—a case study of well MW-17 in Menengai Kenya”, GRC Trans, 2015.
[39] F. Ecer, S. Ardabili, S. S. Band, and A. Mosavi, “Training multilayer perceptron with genetic algorithms and particle swarm optimization for modeling stock price index prediction”, Entropy, Vol. 22, N0. 11, pp. 1–20.
[40] Z. Hu, Y. Zhang, and L. Yao, “Radial Basis Function Neural Network with Particle Swarm Optimization Algorithms for Regional Logistics Demand Prediction”, Discrete Dynamics in Nature and Society, Vol. 2014, pp. 1–13, 2014.
[41] O. Kramer, “Genetic Algorithm Essentials”, Springer International Publishing, Vol. 679, 2017.
[42] K. Bamdad, M. E. Cholette, L. Guan, and J. Bell, “Ant colony algorithm for building energy optimisation problems and comparison with benchmark algorithms”, Energy and Buildings, Vol. 154, pp. 404–414, 2017.
[43] J. Nasiri, F. M. Khiyabani, and A. Yoshise, “A whale optimization algorithm (WOA) approach for clustering”, Cogent Mathematics & Statistics, Vol. 5, No. 1, p. 1483565, 2018.
[44] A. Karkevandi-Talkhooncheh, S. Hajirezaie, A. Hemmati-Sarapardeh, M. M. Husein, K. Karan, and M. Sharifi, “Application of adaptive neuro fuzzy interface system optimized with evolutionary algorithms for modeling CO2-crude oil minimum miscibility pressure”, Fuel, Vol. 205, October 2017, pp. 34-45.
[45] M. Anemangely, A. Ramezanzadeh, B. Tokhmechi, A. Molaghab, and A. Mohammadian, “Drilling rate
 
prediction from petrophysical logs and mud logging data using an optimized multilayer perceptron neural network”, Journal of Geophysics and Engineering, Vol. 15, No. 4, pp. 1146–1159, Aug. 2018.
[46] S. Elkatatny, “Development of a new rate of penetration model using self-adaptive differential evolution-artificial neural network”, Arabian Journal of Geosciences, Vol. 12, No. 2, 2019.
[47] Y. Zhao, A. Noorbakhsh, M. Koopialipoor, A. Azizi, and M. M. Tahir, “A new methodology for optimization and prediction of rate of penetration during drilling operations”, Engineering with Computers volume, pp. 1–9, Jan. 2019.