تخمین دقیق پارامترهای چاه‌آزمایی با استفاده از یک الگوریتم ترکیبی و مقایسه آن با یک نرم‌افزار رایج صنعتی

نوع مقاله: مقاله پژوهشی

نویسندگان

دانشکده مهندسی نفت، دانشگاه صنعتی امیرکبیر، تهران، ایران

10.22078/pr.2019.3661.2671

چکیده

تراوایی، ضریب پوسته و ضریب ذخیره چاه سه پارامتر اساسی مخزن و چاه هستند. روش معمول برای به‌دست آوردن مقادیر این پارامترها چاه‌آزمایی است. در این روش داده‌های فشاری به‌دست آمده براساس زمان در منحنی‌های نیمه لگاریتمی و لگاریتمی رسم شده و با روش ها و فرمول‌های مشخص این مقادیر محاسبه می‌شود. در این مطالعه یک روش جدید برای به‌دست آوردن پارامترهای چاه‌آزمایی با استفاده از هوش مصنوعی معرفی می‌شود. ابتدا با استفاده از پارامترهای مربوط به دو چاه واقعی، داده‌های فشار- زمان به‌وسیله نرم‌افزار چاه‌آزمایی سفیر 10/4 تولید می‌شود. چون مقادیر به‌دست آمده دارای پراکندگی زیاد هستند، داده‌ها توسط تبدیل موجک دوبیشز نویززدایی شده و تحلیل و بررسی داده‌ها راحت‌تر صورت می‌پذیرد. سپس با ترکیب الگوریتم‌های ژنتیک و لونبرگ مارکارد پارامترهای اساسی مخزن محاسبه می‌شوند. در مرحله آخر داده‌های فشاری در نرم‌افزار رایج چاه‌آزمایی سفیر 10/4 وارد گردیده و مقادیر تراوایی، ضریب پوسته و ضریب ذخیره چاه محاسبه شد. الگوریتم ترکیبی توانست مقادیر تراوایی، ضریب پوسته، ضریب ذخیره چاه و شعاع خارجی را به‌ترتیب با خطای میانگین 565/1%، 60/3%، 06/1% و 553/1% نسبت به نرم‌افزار چاه‌آزمایی سفیر 10/4 محاسبه کند.
 

کلیدواژه‌ها


عنوان مقاله [English]

Accurate Estimation of the Well Test Parameters By Using a Hybrid Algorithm and Comparing It With Conventional Industrial Software

نویسندگان [English]

  • Ehsan Khamehchi
  • Mehrdad Ghasemi
  • Mohammad Kashi
Departmet of Petroleum Engineering, Amirkabir University of Technology, Tehran, Iran
چکیده [English]

Permeability, skin factor, and wellbore storage coefficient are three essential parameters for well and reservoir. Moreover, well testing is the conventional method for determining these parameters. In this method, pressure data are plotted versus time in semilogarithmic and logarithmic scales, and specified relations determine well test parameters. In this study, a new approach is introduced to obtain well test parameters using artificial intelligence. First, using endpoints related to two real wells, pressure data are produced by reservoir simulator software. Because the data have a lot of noises, the additional data are removed, and analyzing the data is more comfortable. Then, with the combination of a genetic algorithm and the Levenberg Marquardt algorithm, the basic parameters of the reservoir have been calculated. In the last step, the pressure data are entered into standard software, and their values are calculated. Finally, the combined algorithm with excellent accuracy has been able to calculate these parameters in comparison with the conventional Saphir 4.10 well testing software.
 

کلیدواژه‌ها [English]

  • Permeability
  • Skin Factor
  • Wellbore storage coefficient
  • Artificial Intelligence
  • Well Testing
[1]. Theis C. V., “The relation between the lowering of the piezometric surface and the rate and duration of discharge of a well using groundwater storage,” Eos, Transactions American Geophysical Union, Vol. 16, No. 2, pp. 519-524, 1935. ##

[2]. Muskat M., “Use of data oil the build-up of bottom-hole pressures,” Transactions of the AIME, Vol. 123, No. 01, pp. 44-48, 1937. ##

[3]. Van Everdingen A. and Hurst W., “The application of the laplace transformation to flow problems in reservoirs,” Journal of Petroleum Technology, Vol. 1, No. 12, pp. 305-324, 1949. ##

[4]. Gringarten A. C., “From straight lines to deconvolution: The evolution of the state of the art in well test analysis,” SPE Reservoir Evaluation & Engineering, Vol. 11, No. 01, pp. 41-62, 2008. ##

[5]. Bourdet D., Ayoub J. and Pirard Y., “Use of pressure derivative in well test interpretation,” SPE Formation Evaluation, Vol. 4, No. 02, pp. 293-302, 1989. ##

[6]. Tiab D., “Analysis of pressure and pressure derivative without type-curve matching—Skin and wellbore storage,” Journal of Petroleum Science and Engineering, Vol. 12, No. 3, pp. 171-181, 1995. ##

[7]. Allain O. F. and Horne R. N., “Use of artificial intelligence in well-test interpretation,” Journal of Petroleum Technology, Vol. 42, No. 03, pp. 342-349, 1990. ##

[8]. Al-Kaabl A. A.U., McVay D. A. and Lee J. W., “Using an expert system to identify a well-test-interpretation model,” Journal of Petroleum Technology, Vol. 42, No. 05, pp. 654-661, 1990. ##

[9]. Stewart G. and Du K. F., “Feature selection and extraction for well test interpretation by an artificial intelligence approach,” in SPE Annual Technical Conference and Exhibition, Society of Petroleum Engineers, San Antonio, 8-11 October Texas, 1989. ##

[10]. Holland J., “Adaptation in natural and artificial systems,” Univ. of Mich. Press. Ann Arbor, 1975. ##

[11]. Jeirani Z. and Mohebbi A., “Estimating the initial pressure, permeability and skin factor of oil reservoirs using artificial neural networks,” Journal of Petroleum Science and Engineering, Vol. 50, No. 1, pp. 11-20, 2006. ##

[12]. Soliman M., Ansah J., Stephenson S. and Mandal B., “Application of wavelet transform to analysis of pressure transient data,” in SPE Annual Technical Conference and Exhibition, Society of Petroleum Engineers, Vol. 6, Issue 02, 2003. ##

[13]. Sahni I. and Horne R. N., “Multiresolution wavelet analysis for improved reservoir description,” SPE Reservoir Evaluation & Engineering, Vol. 8, No. 01, pp. 53-69, 2005. ##

[14]. Mirzaei-Paiaman A., “An empirical correlation governing gas-condensate flow through chokes,” Petroleum Science and Technology, Vol. 31 No. 4, pp. 368-379, 2013. ##

[15]. Mirzaei-Paiaman A. and Salavati S., “A new empirical correlation for sonic simultaneous flow of oil and gas through wellhead chokes for Persian oil fields,” Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, Vol. 35, No. 9, pp. 817-825, 2013. ##

[16]. Shokir E. M., “A novel model for permeability prediction in uncored wells. SPE Reservoir Evaluation & Engineering,” Vol. 9, No. 03, pp. 266-273, 2006. ##

[17]. Mirzaei-Paiaman A. and Salavati S., “The application of artificial neural networks for the prediction of oil pro duction flow rate,” Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, Vol. 34, No. 19, pp. 1834-1843, 2012. ##

[18]. Abooali D. and Khamehchi E., “Toward predictive models for estimation of bubble-point pressure and formation Vol factor of crude oil using an intelligent approach,” Brazilian Journal of Chemical Engineering, Vol. 33, No. 4, pp. 1083-1090, 2016. ##

[19]. Miri R., Jorge H. B. Sampaio, Afshar M. and Lourenco A., “Development of artificial neural networks to predict differential pipe sticking in Iranian offshore oil fields,” in International Oil Conference and Exhibition in Mexico. Society of Petroleum Engineers, 27-30 June, Veracruz, Mexico 2007. ##

[20]. Naderi M. and Khamehchi E., “Application of optimized least square support vector machine and genetic programming for accurate estimation of drilling rate of penetration,” International Journal of Energy Optimization and Engineering (IJEOE), Vol. 7, No. 4, pp p. 92-108, 2018. ##