پیش بینی نرخ نفوذ مته به کمک شبکه‌های عصبی و بررسی تاثیر وزن دهی پارامترهای ورودی به کمک فرآیند تحلیل سلسله مراتبی فازی برای یکی از میادین غرب ایران

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده مهندسی نقشه برداری و اطلاعات مکانی، پردیس دانشکده های فنی دانشگاه تهران

2 دانشکده مهندسی معدن، پردیس دانشکده های فنی دانشگاه تهران

چکیده

تعیین نرخ نفوذ مته یکی از موارد پر اهمیت در صنعت حفاری می‌باشد. عموما، دو روش برای مدل‌سازی نرخ نفوذ مته وجود دارد که عبارتند از مدل‌های فیزیکی و مدل‌های مبتنی بر شبکه‌های عصبی. کارایی مدل‌های فیزیکی با توجه به نقاط ضعفی مانند استفاده از ضرایب تجربی، نیاز به داده‌های جانبی زیاد، مورد تردید می‌باشد. از سوی دیگر، شبکه‌های عصبی می‌توانند با توجه به محدودیت داده‌های در درسترس، ابزاری مناسب جهت پیش‌بینی نرخ نفوذ مته ‌باشند. در این مقاله نرخ نفوذ مته به کمک حدود 2000 روز داده‌های حفاری، با استفاده از شبکه‌های عصبی پرسپترون چند لایه و المان مدلسازی شد. در هردوشبکه‌ی مذکور تعداد 7 نرون به عنوان نرون بهینه در تنها لایه‌ی پنهان تعیین شد که نتایج نشانگر میزان همبستگی 1/77%، 7/76% و میانگین مربعات خطای 31/1، 33/1 به ترتیب در شبکه‌ی پرسپترون چندلایه و شبکه‌ی المان بود. سپس، به منظور ارتقاء نتایج هردو شبکه‌ی عصبی، پارامترهای ورودی به کمک نظرات کارشناسان و با استفاده از رویه‌ی تحلیل سلسله مراتبی وزن دهی شد و مجددا مدلسازی نرخ نفوذ صورت گرفت که باعث بهبود نتایج هردو شبکه‌ی عصبی شد. نتایج حاصل از این پژوهش نشانگر برتری شبکه‌ی پرسپترون چندلایه جهت تخمین نرخ حفاری می‌باشد که موید این واقعیت است که شبکه‌های عصبی با دقت مناسبی قابلیت پیش بینی نرخ نفوذ مته را بر اساس داده‌های در دسترس دارند

کلیدواژه‌ها


عنوان مقاله [English]

The Prediction of the Rate of Penetration Using Artificial Neural Networks and applying the Fuzzy AHP Method for Weighting Input Parameters in One of the Western Oilfields of Iran

نویسندگان [English]

  • Parham Pahlavani 1
  • Ali Mohamad Pakdaman 2
  • Mahdi Mehranpour 2
1 School of Surveying and Geospatial Eng., College of Eng., University of Tehran
2 School of Mining, College of Eng., University of Tehran
چکیده [English]

Determination of the rate of penetration is one of the most important factors in oil industries. Generally, two methods have been proposed for modeling the rate of penetration which include physical and artificial neural networks methods. ََArtificial neural networks can be used accurately in order to predict the rate of penetration in which the prediction of the rate of penetration does not include experimental coefficients and bit specifications. Furthermore, in this method, the rate of penetration only depends on the input data.
In this paper, the rate of penetration using almost 2000 daily drilling reports and rock mechanical properties was applied. These data were reduced to approximately 1800 data according to data preprocessing. The rate of penetration was modeled by two artificial neural networks including a Multi-Layer Perceptron and an Elman with a hidden layer. After preprocessing the input data and sensitivity analysis of the number of neurons in the hidden layer, seven neurons were chosen as the optimized number of neurons in the Multi-Layer Perceptron with the correlation and mean square error of 77.1% and 1.31, respectively. Also, the Elman neural network showed the correlation and mean square error of 77.6% and 1.33, respectively. Thereafter, the fuzzy AHP method was applied for imposing weights, gaining by expert comments, on the input data resulted in improvements of the artificial neural networks. The results of this investigation have shown insignificant superiority of the Multi-Layer Perceptron neural network for prediction of the rate of penetration comparing to the Elman neural networks. Therefore, the proposed weighted Multi-Layer Perceptron neural network models the rate of penetration accurately and appropriately using available data.

کلیدواژه‌ها [English]

  • Rate of Penetration
  • MLP Artificial Neural Network
  • Elman Artificial Neural Network
  • Fuzzy AHP Method
  • Oil fields
Abbas A.K., Rushdi S., Alsaba M. (2018). Modeling rate of penetration for deviated wells using artificial neural networks. Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, UAE.
Aladjev, V., Aladjev, V.,(2014) General Statistics, International Academy of Noospher, the baltic branch,Tallin.
Al-Abduljabbar A., Elkatatny S., Abdulazeez Abdulraheem M.M. (2018). Predicting rate of penetration using artificial intelligence techniques. SPE Kingdom of Saudi Arabia Annual Technical Symposium and Exhibition. Dammam, Saudi Arabia: Society of Petroleum Engineers.
Amer M., Sattar D., Hashem A. (2017). An ROP predictive model in nile delta area using artificial neural networks. SPE Kingdom of Saudi Arabia Annual Technical Symposium and Exhibition. Dammam, Saudi Arabia: Society of Petroleum Engineers.
Anemangely M., Ramezanzadeh A., Tokhmechi B., (2017).Determination of constant coefficients of Bourgoyne and Young drilling rate model using a novel evolutionary algorithm, Jornal of Mining and Environment, 8(4), 693-702.
Anemangely M., Ramezanzadeh A., Tokhmechi B., Molaghab A., Mohammadian A.,(2018) Drilling rate prediction from petrophysical logs and mud logging data using an optimized multilayer perceptron neural network, Journal of Geophysics and Engineering, 15(4), 1146-1159.
Arabjamaloei, A., Shadizadeh, S. (2014). Modeling and optimizing rate of penetration using intelligent systems in an Iranian southern oil field (Ahwaz Oil Field). Petroleum Science and Technology, 29(16), 1637-1648.
Ashrafi B., Anemangely M., Sabah M., Ameri M. J., (2019) 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,175, 604-623.
Bataee, M., Kamyab, M., and Ashena, R. (2010). Investigation of various ROP models and optimization of drilling parameters for PDC and roller-cone bits in shadegan oil field. CPS/SPE International Oil & Gas Conference and Exhibition (p. SPE130932). Beijing,China: Society of Petroleum Engineers.
Bilgesu, H. I., Tetrick, L. T., Mohaghegh, S., Ameri, S. (1997). A new Approach fir the Prediction of Rate of Penetration Values. SPE Eastern Regional Meeting (pp. 175-179). Lexington: Society of Petroleum Engineers.
Bingham , M. (1964). How to interpret driling in the performance region. The Oil and Gas journal, 173-179.
Bingham , M. (1964-1965). A new approach to interpreting rock drillability . The Oil and Gas Journal.
Bingham, M. (1964). How rock properties are related to driling. The Oil and Gas Journal, 94-101.
Bourgoyne, A., & Young , F. (1974). A multiple regression approach to optimal drilling and abnormal pressure detection. Society of Petroleum Engineers Journal, 371-384.
Chang, Y. D. (1996). Application of the extent analysis method on fuzzy AHP. European Journal of Operational Research, 95, 649-655.
Demuth, H. Beale,M. (2000). Neural network toolbox. The MathWorks.
Elahifar, B. T., Thonhauser, G., Fruhwirth, R. K., Esmaeili, A. (2012). ROP modeling using neural networks and drill string vibration data, . SPE Kuwait International Petroleum Conference and Exhibition (pp. 1-8). Kuwait : Society of Petroleum Engineers.
Elkatatny, S.M., (2017). New approach to optimize the rate of penetration using artificial neural n etwork. Arabian Journal for Science and Engineering,.43(11), 6297-6304.
Elkatatny, S.M., Tariq, Z. and Mahmoud, M.A. Al-AbdulJabbar, A. (2017). Optimization of rate of penetration using artificial intelligent techniques. . 51st US Rock Mechanics Geomechanics Symposium held in San Francisco. California, USA.: American Rock Mechanics Association.
Engelbrecht, A. P. (2002). Computentinal Inteligence. John Wiley.
Gandelman, R. A. (2012). ROP prediction and real-time optimization of operational parameters on drilling offshore oil Wells. Brazil: Universidade Federal do Rio de Janeiro.
Gharechelou, S., Amini, A., Kadkhodaie-Ilkhchi, A, Moradi, M. (2015). An integrated approach for determination of pore-type distribution in carbonate-siliciclastic Asmari Reservoir, CheshmehKhosh Oilfield, SW Iran. Journal of Geophysics and Engineering, 12, 793-809.
Hareland, G., & Rampersad , P. (1994). Drag-bit model including wear. The Third Latin American/Caribben Petroleum Engineering Conference, (pp. 27-29). Buenos Aires.
Hegde, C., Diagle, H., Milwater, H., Gray, K. (2017). Analysis of rate of penetration (ROP) prediction in drilling using physics-based and data-driven models. Journal of Petroleum Science and Engineering, 159, 295-306.
Hegde, C., Soares, S., Gray, K. (2018). Rate of penetration modeling using hybrid models: Deterministic and machine learning, Unconventional Resources Technology Conference, Huston,Texas.
Khoukhi, A., Alarfaj I. (2012). Rate of penetration prediction and optimization using advances in artificial neural networks, a comparative study. . 4th International Joint Conference on Computational Intelligence, (pp. 647-652). K.S.A. .
Mantha, B., Samuel, R. (2016). ROP optimization using artificial intelligence techniques with statistical regression coupling. SPE Annual Technical Conference and Exhibition. Dubai, UAE: Society of Petroleum Engineers. 
Moran, D., Ibrahim, H., Purwanto, A. (2010). Sophisticated ROP prediction technologies based on neural network delivers accurate drill time results. Asia Pacific Drilling Technology Conference and Exhibition (pp. 1-8). Ho Chi Minh : Society of Petroleum Engineers.
Motahhari, H. R., Hareland, G., and James, J. A. (2010). Improved drilling efficiency technique using integrated PDM and PDC bit parameters. Journal of Canadian Petroleum Technology, 49(10), 45-52.
Rezaie, A., & Nogole-Sadat, M. (2004). Fracture modeling in Asmari reservoir of Rag-e Sefid. Iranian International Journal Of Science, 5, 107-121.
Soares, C., Daigle, H., Gray, K (2016). Evaluation of PDC bit ROP models and the effect of rock strength on model coefficients. Journal of Natural Gas Science and Engineering, 34, 1225-1236.
Van Laarhiven, P. J., Pedrycz, W. (1983). A fuzzy extension of Saatys priority theory. Fuzzy Sets and Systems, 11, 229-241.
Zhao Y., Noorbakhsh A., Tokhmechi B., Koopialipoor M., Aydin A., Tahir M. M., (2019) A new methodology for optimization and prediction of rate of penetration during drilling operations, Engineering with Computers, 1-9.