The paper describes an algorithm for step-by-step planning of repeated selective multistage hydraulic fracturing (MSHF) which enables motivated and prompt selection of potential well candidates from the total number of horizontal wells in the field. The field production and operation data was gathered and verified, and a statistical training sample was formed in Microsoft Excel. The geological and field analysis of downhole data was performed using the RN-KIN software. The production process parameters were estimated using the t-Navigator and RN-KIM software for 3D flow simulation. The objects of the study are horizontal wells introduced into operation with primary MSHF in VK1-3 reservoir of the Kamenny Area within the Krasnoleninsky Field. According to the result of testing the algorithm in industrial conditions, the total reduction in the sample of horizontal wells for the field in question was 80%, which made it possible to select reasonably the best wells from the total well stock. Repeated MSHF were implemented in all wells justified in the study, the oil rates and oil production volumes increased and demonstrated reasonable convergence of the estimated and actual values, which allows to draw a conclusion on the applicability and performance of the developed algorithm. The results of pilot field tests indicate that the use of a step-by-step planning algorithm enables the proper selection of potentially effective candidate wells for conducting MSHF based on a comprehensive consideration of a set of criteria and their weights, geological and field analysis and assessment of production potential using a 3D hydrodynamic model.
References
1. Ganiev B.G., Nasybullin A.V., Sattarov Ram.Z. et al., Application of machine learning method for planning of well drilling in producing oil formations (In Russ.), Neftjanoe hozjajstvo = Oil Industry, 2021, no. 7, pp. 23–27, DOI: https://doi.org/10.24887/0028-2448-2021-7-23-27
2. Kochnev A.A., Kozyrev N.D., Kochneva O.E., Galkin S.V., Development of a comprehensive methodology for the forecast of effectiveness of geological and technical measures based on machine learning algorithms (In Russ.), Georesursy, 2020, V. 22, no. 3, pp. 79–86, DOI: https://doi.org/10.18599/grs.2020.3.79-86
3. Rebrova O.Yu., Statisticheskiy analiz meditsinskikh dannykh. Primenenie paketa prikladnykh programm STATISTICA (Statistical analysis of medical data. Using the STATISTICA application package), Moscow: MediaSfera Publ., 2002, 312 p.
4. Nasybullin A.V., Bayburov R.R., Using statistical machine learning methods to optimize well operation (In Russ.), Neftyanaya provintsiya, 2021, no. 3 (27), pp. 84–94.
5. Lee J.W., Kim S.H., Using analytic network process and goal programming for interdependent information system project selection, Computers and Operations Research, 2000, no. 27, pp. 367-382, DOI: http://doi.org/10.1016/S0305-0548(99)00057-X
6. Wang J., Hwang W.-L., A fuzzy set approach for R&D portfolio selection using a real option valuation model, Omega, 2005, V. 35(3), pp. 247–257,
DOI: http://doi.org/10.1016/j.omega.2005.06.002
