Advertisement

An improved particle swarm algorithm to optimize PID neural network for pressure control strategy of managed pressure drilling

  • He ZhangEmail author
  • Xiru Yuan
Deep Learning for Big Data Analytics
  • 64 Downloads

Abstract

The bottom hole pressure (BHP) of managed pressure drilling (MPD) is a typically unstable object with hysteresis that is difficult to be directly controlled. However, at the present stage, BHP control still focuses on conventional PID control and simple intelligent control, requiring repeated data alignment. There are some related problems, such as lack of control over BHP, longer working hours and high cost of drilling. In order to increase economic effects of MPD, this paper analyzes the MPD system and utilizes wellhead back pressure as the controlled variable. According to throttle valve features, basic parameters and boundary conditions of MPD, a mathematical model of throttle valve is also calculated. Besides, this paper focuses on studying the control model and proposes an improved particle swarm algorithm to optimize PID neural network (IPSOPIDNN) model. This model is improved based on inertia weight and fitness function of conventional particle swarm algorithm. Moreover, the particle swarm algorithm is used to optimize the initial weight value of PID neural network, shorten the search time for optimal value of particle swarm, and reduce the chance of local minimum. The real-time control results of IPSO-PIDNN are compared with results of traditional particle swarm optimization PID neural network (PSO-PIDNN) and particle swarm optimization PID neural network (PSO-PIDNN). IPSO-PIDNN control system has some advantages, including favorable self-learning, optimization quality, high levels of control precision, no overshoot, rapid response and short setting time. In this way, advanced automation control of BHP is conducted during managed pressure drilling process, thus providing technical support for the well control safety of managed pressure drilling.

Keywords

Managed pressure drilling Wellhead back pressure Pressure control Throttle valve 

Notes

Acknowledgements

This work was supported by Sichuan Province Applied Basic Research Project (No. 2016JY0049).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. 1.
    Nie X, Chen Y, Meng Y, Yang C, Yan J, Wang Z (2010) Current status and development strategy of managed pressure drilling technology. Drill Prod Technol 02:38–39Google Scholar
  2. 2.
    Yang X, Zhou Y, Fang S, Liu W (2011) Design and laboratory test of hierarchical intelligent control system for managed pressure drilling. Pet Drill Tech 04:13–18Google Scholar
  3. 3.
    Liu W, Shi L, Wang K, Fang S, Guo Q, Yan X, Zhu W (2015) A method for real-time correction of wellbore pressure. China Patent: 201510567464.5Google Scholar
  4. 4.
    Zhang X, Jiang Y, Zhou Y, Liu W, Wang W, Wang K, Yan X (2014) Simulation calculation method for gas-liquid two-phase flow in managed pressure drilling. Chinese Patent: 201410371178.7Google Scholar
  5. 5.
    Davoudi M, Smith JR, Chirinos JE et al (2011) Evaluation of alternative initial responses to kicks taken during managed-pressure drilling. SPE Drill Complet 26(02):169–181CrossRefGoogle Scholar
  6. 6.
    Kernche F, Hannegan D, Sammat E (2011) Managed pressure drilling enables drilling beyond the conventional limit on an HP/HT deepwater well. SPE142312Google Scholar
  7. 7.
    Mammadov E, Kinik K, Ameen Rostami S et al (2015) Case study of managed pressure tripping operation through abnormal formations in West Canadian sedimentary basin. SPE 174073-MSGoogle Scholar
  8. 8.
    Alimuddin S, Kumar N, Gandhi K (2011) Optimization of drilling and production operations by application of MPD technique on indian offshore basins—a strategic approach. SPE 15414 - MSGoogle Scholar
  9. 9.
    Patel B, Grayson B, Gans H (2013) Optimized unconventional shale development with MPD techniques. SPE-164565-MSGoogle Scholar
  10. 10.
    Liang H, Li H (2016) Control model of throttle back pressure of managed pressure drilling. J Comput Theor Nanosci 13(10):7603–7609CrossRefGoogle Scholar
  11. 11.
    Cai W (2014) Research on safety real-time monitoring and control analysis system for managed pressure drilling. Southwest Petroleum UniversityGoogle Scholar
  12. 12.
    Lyons JL (1991) Valve technical manual. Yuan Yuqiu, translated. Mechanical Industry Press, Beijing, pp 57–70Google Scholar
  13. 13.
    (2014) Pressure regulation characteristics of automatic choke manifold in managed pressure drilling. Pet Drill Technol 42(2):18–22Google Scholar
  14. 14.
    Shu H (2006) PID neural network and its control system. National Defense Industry Press, BeijingGoogle Scholar
  15. 15.
    Dong F (2015) PID controller parameter tuning based on Ziegler–Nichols rule. Autom Instrum 07:105–107Google Scholar
  16. 16.
    Hu S (2007) Automatic control theory, 5th edn. Science Press, BeijingGoogle Scholar
  17. 17.
    Yang H, Yang Y, Yang L, Dong D (2016) Swarm optimization algorithm with particle selection and memory. Appl Res Comput 04:1039–1043Google Scholar
  18. 18.
    Li J, Li X, Pian J (2014) Annealing furnace temperature control and improvement of PSO based on fuzzy RBF neural network. J Nanjing Univ Sci Technol 38(3):337–341Google Scholar
  19. 19.
    Wang X, Liang X (2014) Network traffic prediction based BPSO-RBF neural network. Comput Appl Softw 31(9):102–105Google Scholar
  20. 20.
    Hua C, Yi R, Shao G (2011) Algorithm researching of RBF neural network based on improved PSO. Adv Mater Res 104:233–238Google Scholar
  21. 21.
    Nan J, Wang X (2017) Particle swarm optimization algorithm with improved inertia weight. J Xi’an Polytech Univ 31(6):835–840MathSciNetGoogle Scholar
  22. 22.
    Taherkhani M, Safabahsh R (2016) A novel stability-based adaptive inertia weight for particle swarm optimization. Appl Soft Comput 1(38):281–295CrossRefGoogle Scholar
  23. 23.
    Liang H, Zou J, Liang W (2017) An early intelligent diagnosis model for drilling overflow based on GA–BP algorithm. Clust Comput 2:1–20Google Scholar
  24. 24.
    Ge L, Hu P, Xie X, Hu Z, Zeng Q, Liao J (2016) Study on high precision swill-cooked dirty oil detection system based on date fusion technology. Oxid Commun 39(1):317–330Google Scholar
  25. 25.
    Liang HB, Huang XQ, Sun YQ, Chen XZ (2016) A diagnostic model based on support vector machine for the collapse of horizontal well borehole wall. J Residuals Sci Technol 13:167–175Google Scholar
  26. 26.
    Ge L, Hu Z, Ping C et al (2014) Research on overflow monitoring mechanism based on downhole microflow detection. Math Probl Eng 2014:1–6Google Scholar
  27. 27.
    Rossomando FG, Soria CM (2015) Identification and control of nonlinear dynamics of a mobile robot in discrete time using an adaptive technique based on neural PID. Neural Comput Appl 26(5):1179–1191CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Mechanic EngineeringSouthwest Petroleum UniversityChengduChina

Personalised recommendations