Developing a Hybrid Data-Driven, Mechanistic Virtual Flow Meter - a Case Study

Virtual flow meters, mathematical models predicting production flow rates in petroleum assets, are useful aids in production monitoring and optimization. Mechanistic models based on first-principles are most common, however, data-driven models exploiting patterns in measurements are gaining popularity. This research investigates a hybrid modeling approach, utilizing techniques from both the aforementioned areas of expertise, to model a well production choke. The choke is represented with a simplified set of first-principle equations and a neural network to estimate the valve flow coefficient. Historical production data from the petroleum platform Edvard Grieg is used for model validation. Additionally, a mechanistic and a data-driven model are constructed for comparison of performance. A practical framework for development of models with varying degree of hybridity and stochastic optimization of its parameters is established. Results of the hybrid model performance are promising albeit with considerable room for improvements.

[1]  Mahmoud Meribout,et al.  A NEURAL NETWORK ALGORITHM FOR DENSITY MEASUREMENT OF MULTIPHASE FLOW , 2012 .

[2]  Johannes Jäschke,et al.  First Principles and Machine Learning Virtual Flow Metering: A Literature Review , 2020 .

[3]  Sebastião Feyo de Azevedo,et al.  Hybrid semi-parametric modeling in process systems engineering: Past, present and future , 2014, Comput. Chem. Eng..

[4]  Bjarne Grimstad,et al.  A Simple Data-Driven Approach to Production Estimation and Optimization , 2016 .

[5]  Gioia Falcone,et al.  Multiphase Flow Metering: Current Trends and Future Developments , 2002 .

[6]  Antonio Sala,et al.  A Systematic Grey-Box Modeling Methodology via Data Reconciliation and SOS Constrained Regression , 2019, Processes.

[7]  Lyle H. Ungar,et al.  A hybrid neural network‐first principles approach to process modeling , 1992 .

[8]  James P. Brill,et al.  Multiphase Flow Through Chokes , 1969 .

[9]  Mohd Azmin Ishak,et al.  Virtual multiphase flow metering using diverse neural network ensemble and adaptive simulated annealing , 2018, Expert Syst. Appl..

[10]  Craig Dickson Marshall,et al.  Maximising Economic Recovery - A Review of Well Test Procedures in the North Sea , 2015 .

[11]  Eric D. Toskey.  Improvements to Deepwater Subsea Measurements RPSEA Program: Evaluation of Flow Modelling , 2012 .

[12]  Yoshua Bengio,et al.  Practical Recommendations for Gradient-Based Training of Deep Architectures , 2012, Neural Networks: Tricks of the Trade.

[13]  Gioia Falcone,et al.  Multiphase Flow Metering: Current Trends and Future Developments , 2002 .

[14]  Cenk Temizel,et al.  Status of Data-Driven Methods and their Applications in Oil and Gas Industry , 2018, Day 3 Wed, June 13, 2018.

[15]  P. J. Waltrich,et al.  Performance Evaluation Of Multiphase Flow Models Applied To Virtual Flow Metering , 2016 .

[16]  Enrico Zio,et al.  A Hybrid Ensemble-Based Approach for Process Parameter Estimation and Degradation Assessment in Offshore Oil Platforms , 2014 .

[17]  Xiaomin Li,et al.  Wet Gas Metering Using a Revised Venturi Meter and Soft-Computing Approximation Techniques , 2011, IEEE Transactions on Instrumentation and Measurement.

[18]  Kjetil Fjalestad,et al.  Stabilized and Increased Well Production Using Automatic Choke Control , 2014 .

[19]  M. Kramer,et al.  Embedding Theoretical Models in Neural Networks , 1992, American Control Conference.

[20]  Jorge Nocedal,et al.  Optimization Methods for Large-Scale Machine Learning , 2016, SIAM Rev..

[21]  Manuel Remelhe,et al.  Between the Poles of Data‐Driven and Mechanistic Modeling for Process Operation , 2017 .

[22]  R. P. Sutton.  Compressibility Factors for High-Molecular-Weight Reservoir Gases , 1985 .

[23]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.