Advertisement

Comparison of Candidate-Well Selection Mathematical Models for Hydraulic Fracturing

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 367)

Abstract

The selection of a target well and formation is considered as the first step in hydraulic fracturing (HF) and naturally regarded as a critical decision-making throughout process of HF treatment. The candidate-well selection process for HF is taken as a complex, nonlinear and uncertainty system. Modern mathematical methods, such as Artificial Intelligence (AI), offer the opportunities to examine the sample data, clarify the relationships among effect factors, in other ways to maximize the concealed potential. However, the performance of these methods is not specified in the certain application of candidate-well selection in gas field. This paper aims to provide a comparison of three candidate-well selection techniques, including BP-ANN, GA-based FNN, and SVM, as well as make clear the most effective one among them to pick a target well for HF. The application result of X gas field shows that BP-ANN is not as effective as GA-based FNN. Despite the advantage of more simple and intuitive evaluation, SVM has its own limitation in the uncertain system.

Keywords

Hydraulic fracturing Candidate-well selection Nonlinear and uncertainty system BP-ANN FNN SVM 

Notes

Acknowledgments

The authors would like to acknowledge the support of the students’ extracurricular experiment project (No. KSZ14154) “Evaluation index system construction of candidate-well selection for hydraulic fracturing based on fuzzy methods” which sponsored by Southwest Petroleum University fund.

References

  1. 1.
    Rushing, J.A., Sullivan, R.B.: Evaluation of a hybrid water-frac stimulation technology in the Bossier tight gas sand play SPE annual technical conference and exhibition. Society of Petroleum Engineers (2003)Google Scholar
  2. 2.
    King, G.E.: Thirty years of gas shale fracturing: what have we learned? SPE annual technical conference and exhibition. Society of Petroleum Engineers (2010)Google Scholar
  3. 3.
    Daneshy, A.: Hydraulic fracturing to improve production. Way Ahead: Tech. 101(6), 3 (2010)Google Scholar
  4. 4.
    Samsuri, A., Zoveidavianpoor, M., Shadizadeh, S.R.: A review on conventional candidate-well selection for hydraulic fracturing in oil and gas wells. Int. J. Eng. Technol. 2(1), 51–60 (2012)Google Scholar
  5. 5.
    Saeedi, A., Camarda, K.V., Liang, J.: Using neural networks for candidate selection and well performance prediction in water-shutoff treatments using polymer gels-a field-case study. SPE Prod. Oper. 22(04), 417–424 (2007)CrossRefGoogle Scholar
  6. 6.
    Ouenes, A.: Practical application of fuzzy logic and neural networks to fractured reservoir characterization. Comput. Geosci-Uk 26(8), 953–962 (2000)CrossRefGoogle Scholar
  7. 7.
    Mohaghegh, S.: Virtual intelligence and its applications in petroleum engineering. J. Pet. Technol. Distinguished Author Series (2000)Google Scholar
  8. 8.
    Yang, W., Tian, F., Gong, S.: Optimized determination of fractured well layers based on support vector machine. Comput. Eng. 7, 87 (2006)CrossRefGoogle Scholar
  9. 9.
    Reeves, S.R., Hill, D.G., Hopkins, C.W., Conway, M.W., Tiner, R.L., Mohaghegh, S.: Restimulation technology for tight gas sand wells SPE annual technical conference (1999)Google Scholar
  10. 10.
    Cheng, K., Wei, Y., Wu, W., Holditch, S.A.: A novel optimization model for analyzing production DataSPE western regional meeting. Society of Petroleum Engineers (2010)Google Scholar
  11. 11.
    Guo, J., Xiao, Y., Zhu, H.: A new method for fracturing wells reservoir evaluation in fractured gas reservoir. Mathematical Problems in Engineering (2014)Google Scholar
  12. 12.
    Xiang-jun, X., Ting, Y.: Application of TS fuzzy model in candidate-well selection for hydraulic fracturing fuzzy information and engineering and operations research and management, pp. 563–570. Springer, New York (2014)Google Scholar
  13. 13.
    Zoveidavianpoor, M., Samsuri, A., Shadizadeh, S.R.: Hydraulic fracturing candidate-well selection by interval type-2 fuzzy set and system IPTC 2013: international petroleum technology conference (2013)Google Scholar
  14. 14.
    Zoveidavianpoor, M., Samsuri, A., Shadizadeh, S.R.: Fuzzy logic in candidate-well selection for hydraulic fracturing in oil and gas wells: a critical review. Int. J. Phys. Sci. 7(26), 4049–4060 (2012)Google Scholar
  15. 15.
    Esmaeili, R., Dashtbayazi, M.R.: Modeling and optimization for microstructural properties of Al/SiC nanocomposite by artificial neural network and genetic algorithm. Expert Syst. Appl. 41(13), 5817–5831 (2014)CrossRefGoogle Scholar
  16. 16.
    Zettler, A.H., Poisel, R., Reichl, I., Stadler, G.: Pressure sensitive grouting (PSG) using an artifical neural network combined with fuzzy logic. Int. J. Rock Mech. Min. 34(3), 351–358 (1997)Google Scholar
  17. 17.
    Zhang, M., Liu, X.: A soft sensor based on adaptive fuzzy neural network and support vector regression for industrial melt index prediction. Chemometr. Intell. Lab. 126, 83–90 (2013)CrossRefGoogle Scholar
  18. 18.
    Zhang, J., Qin, W., Wu, L.H., Zhai, W.B.: Fuzzy neural network-based rescheduling decision mechanism for semiconductor manufacturing. Comput. Ind. 65(8), 1115–1125 (2014)CrossRefGoogle Scholar
  19. 19.
    Benamrane, N., Aribi, A., Kraoula, L.: Fuzzy neural networks and genetic algorithms for medical images interpretation. In: IEEE Geometric Modeling And Imaging-new Trends, 2006, pp. 259–264 (1993)Google Scholar
  20. 20.
    Güraksın, G.E., Haklı, H., Uğuz, H.: Support vector machines classification based on particle swarm optimization for bone age determination. Appl. Soft Comput. 24, 597–602 (2014)CrossRefGoogle Scholar
  21. 21.
    Liu, P., Sun, J., Han, L., Wang, B.: Research on the construction of macro assets price index based on support vector machine. Procedia Comput. Sci. 29, 1801–1815 (2014)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Ting Yu
    • 1
  • Xiang-jun Xie
    • 1
  • Ling-na Li
    • 1
  • Wen-bin Wu
    • 1
  1. 1.School of ScienceSouthwest Petroleum UniversityChengduChina

Personalised recommendations