A novel PSO-LSSVM model for predicting liquid rate of two phase flow through wellhead chokes

Abstract Two-phase flow through chokes is common in oil industry. Wellhead chokes regulate and stabilize flow rate to prevent reservoir pressure declining, water coning and protecting downstream facilities against production flocculation. Choke liquid rate prediction is a basic requirement in production scheme and choke design. In this study, for the first time a least square support vector machine (LSSVM) model is developed for predicting liquid flow rate in two-phase flow through wellhead chokes. Particle swarm optimization (PSO) is applied to optimize tuning parameters of LSSVM model. Model inputs include choke upstream pressure, gas liquid ratio (GLR) and choke size which are surface measurable variables. Calculated flow rates from PSO-LSSVM model are excellently consistent with actual measured rates. Moreover, comparison between this model and related empirical correlations show accuracy and superiority of the model. Results of this work indicate PSO-LSSVM model is a powerful technique for predicting liquid rate of chokes in oil industry.

[1]  Alexander J. Smola,et al.  Learning with Kernels: support vector machines, regularization, optimization, and beyond , 2001, Adaptive computation and machine learning series.

[2]  F. E. Ashford,et al.  An Evaluation of Critical Multiphase Flow Performance Through Wellhead Chokes , 1974 .

[3]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Evolutionary tuning of SVM parameter values in multiclass problems , 2008, Neurocomputing.

[4]  R. Eberhart,et al.  Empirical study of particle swarm optimization , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[5]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[6]  Weimin Zhang,et al.  LSSVM Parameters Optimizing and Non-linear System Prediction Based on Cross Validation , 2009, 2009 Fifth International Conference on Natural Computation.

[7]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[8]  Jing Shi,et al.  Fine tuning support vector machines for short-term wind speed forecasting , 2011 .

[9]  B. De Moor,et al.  Least squares support vector machines and primal space estimation , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[10]  Boyun Guo.  5 – Choke Performance , 2007 .

[11]  Yan Zhou,et al.  Forecasting of coal seam gas content by using support vector regression based on particle swarm optimization , 2014 .

[12]  Russell C. Eberhart,et al.  Parameter Selection in Particle Swarm Optimization , 1998, Evolutionary Programming.

[13]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[14]  Peter J. Angeline,et al.  Evolutionary Optimization Versus Particle Swarm Optimization: Philosophy and Performance Differences , 1998, Evolutionary Programming.

[15]  Sayan Mukherjee,et al.  Choosing Multiple Parameters for Support Vector Machines , 2002, Machine Learning.

[16]  Jieping Ye,et al.  SVM versus Least Squares SVM , 2007, AISTATS.

[17]  Hamid Reza Nasriani,et al.  Two-phase flow choke performance in high rate gas condensate wells , 2011 .

[19]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[20]  F. Fortunati,et al.  Two-Phase Flow through Wellhead Chokes , 1972 .

[21]  Amir Safari,et al.  An e–E-insensitive support vector regression machine , 2014, Computational Statistics.

[22]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[23]  N. C. J. Ros,et al.  An analysis of critical simultaneous gas/liquid flow through a restriction and its application to flowmetering , 1960 .

[24]  H. H. Al-Attar,et al.  Revised Bean Performance Equation for East Baghdad Oil Wells , 1988 .

[25]  L. A. Wilson,et al.  Fireflood of the P2-3 Sand Reservoir in The Miga Field of Eastern Venezuela , 1975 .

[26]  H. S. Seifert,et al.  Compressibility Effects in Two‐Phase Flow , 1949 .

[27]  Asaad Ibrahim Al-Towailib.  A New correlation for two-phase flow through chokes , 1994 .

[28]  Abdolhossein Hemmati-Sarapardeh,et al.  On determination of natural gas density: Least square support vector machine modeling approach , 2015 .

[29]  W. E. Gilbert.  Flowing and Gas-lift well Performance , 1954 .

[30]  F. E. Ashford,et al.  Determining Multiphase Pressure Drops and Flow Capacities in Down-Hole Safety Valves , 1975 .

[31]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[32]  Alexander J. Smola,et al.  Support Vector Method for Function Approximation, Regression Estimation and Signal Processing , 1996, NIPS.

[33]  Yunqian Ma,et al.  Practical selection of SVM parameters and noise estimation for SVM regression , 2004, Neural Networks.

[34]  Alireza Bahadori,et al.  Prediction of natural gas flow through chokes using support vector machine algorithm , 2014 .

[35]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[36]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[37]  Alireza Baghban,et al.  Estimating hydrogen sulfide solubility in ionic liquids using a machine learning approach , 2014 .

[38]  Johan A. K. Suykens,et al.  Basic Methods of Least Squares Support Vector Machines , 2002 .

[39]  Gunnar Rätsch,et al.  Input space versus feature space in kernel-based methods , 1999, IEEE Trans. Neural Networks.